{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/code/flatten-dict","entry":"flatten_dict","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-10-05T00:36:11+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample = n_papers_ran_no_instrument_failure (papers with a run with no instrument failure) + n_papers_ran_instrument_only (papers where every run was a failure of Syntology's instrument); n_samples_ran = n_samples_ran_checked (honoured, violated, no contract) + n_samples_instrument (failures of Syntology's instrument, not of the code).","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":72,"n_papers_ran":45,"n_papers_ran_no_instrument_failure":17,"n_papers_ran_instrument_only":28,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":33,"n_samples_ran":26,"n_samples_constructed":0,"n_samples_ran_checked":12,"n_samples_instrument":14,"n_samples_unverified":7,"n_samples_fingerprinted":0,"n_places":74,"n_places_pointer_only":21,"n_places_pointer_only_link_open":1,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_places_pointer_only_link_open counts the places where this paper's link allows the text and the stored copy does not","by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":14,"ran_fixture":0,"ran":12,"unverified":7},"key_notes":{"n_samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2605.20670","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-20670","title":"LT2: Linear-Time Looped Transformers","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"chili-lab/LT2","path":"lingua/args.py","file_url":"https://github.com/chili-lab/LT2/blob/HEAD/lingua/args.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"15be2e56e073a228","code_sha256_prefix":"15be2e56e073a228","mcp_get_code":{"code_sha256":"15be2e56e073a228"}},{"arxiv_id":"2605.11974","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-11974","title":"Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Hyalinesky/DGAO","path":"trl/core.py","file_url":"https://github.com/Hyalinesky/DGAO/blob/HEAD/trl/core.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"dfd0ecd9cb25af69","code_sha256_prefix":"dfd0ecd9cb25af69","mcp_get_code":{"code_sha256":"dfd0ecd9cb25af69"}},{"arxiv_id":"2604.13565","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2604-13565","title":"UHR-BAT: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote Sensing","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"Yunkaidang/UHR","path":"with-SAM/longva/trl/core.py","file_url":"https://github.com/Yunkaidang/UHR/blob/HEAD/with-SAM/longva/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a51ae45a1f6c0b5b","code_sha256_prefix":"a51ae45a1f6c0b5b","mcp_get_code":{"code_sha256":"a51ae45a1f6c0b5b"}},{"arxiv_id":"2602.11543","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-11543","title":"Pretraining A Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"zjr2000/SPES","path":"spes/safetensors_util.py","file_url":"https://github.com/zjr2000/SPES/blob/HEAD/spes/safetensors_util.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"b593a4bbddcc66c3","code_sha256_prefix":"b593a4bbddcc66c3","mcp_get_code":{"code_sha256":"b593a4bbddcc66c3"}},{"arxiv_id":"2602.08389","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-08389","title":"Altruism and Fair Objective in Mixed-Motive Markov games","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"AkuBrains/altruistic-fair-MARL","path":"src/train_suite.py","file_url":"https://github.com/AkuBrains/altruistic-fair-MARL/blob/HEAD/src/train_suite.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"925f85148db8b0fe","code_sha256_prefix":"925f85148db8b0fe","mcp_get_code":{"code_sha256":"925f85148db8b0fe"}},{"arxiv_id":"2601.17868","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-17868","title":"VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"ziHoHe/VidLaDA","path":"train/trl/core.py","file_url":"https://github.com/ziHoHe/VidLaDA/blob/HEAD/train/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a51ae45a1f6c0b5b","code_sha256_prefix":"a51ae45a1f6c0b5b","mcp_get_code":{"code_sha256":"a51ae45a1f6c0b5b"}},{"arxiv_id":"2601.10710","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-10710","title":"Cross-Layer Injection for Deep Vision-Language Fusion","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"codefuse-ai/CLI","path":"trl/core.py","file_url":"https://github.com/codefuse-ai/CLI/blob/HEAD/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a51ae45a1f6c0b5b","code_sha256_prefix":"a51ae45a1f6c0b5b","mcp_get_code":{"code_sha256":"a51ae45a1f6c0b5b"}},{"arxiv_id":"2512.00239","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2512-00239","title":"Self-Supervised Dynamical System Representations for Physiological Time-Series","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"yuqinie98/PatchTST","path":"PatchTST_self_supervised/src/utils.py","file_url":"https://github.com/yuqinie98/PatchTST/blob/HEAD/PatchTST_self_supervised/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"4ac8e022e2aa0b43","code_sha256_prefix":"4ac8e022e2aa0b43","mcp_get_code":{"code_sha256":"4ac8e022e2aa0b43"}},{"arxiv_id":"2510.21706","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2510-21706","title":"Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"dynamical-inference/ebc","path":"groupcl/datajoint/sweep.py","file_url":"https://github.com/dynamical-inference/ebc/blob/HEAD/groupcl/datajoint/sweep.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dynamical-inference/ebc when it was checked","code_sha256":"f30ac4807ed6c8c5","code_sha256_prefix":"f30ac4807ed6c8c5","mcp_get_code":{"code_sha256":"f30ac4807ed6c8c5"}},{"arxiv_id":"2509.13760","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2509-13760","title":"Iterative Prompt Refinement for Safer Text-to-Image Generation","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"ku-dmlab/IPR","path":"trl/core.py","file_url":"https://github.com/ku-dmlab/IPR/blob/HEAD/trl/core.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"dfd0ecd9cb25af69","code_sha256_prefix":"dfd0ecd9cb25af69","mcp_get_code":{"code_sha256":"dfd0ecd9cb25af69"}},{"arxiv_id":"2509.12521","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2509-12521","title":"Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"Yifan-Lan/Phi","path":"trl/core.py","file_url":"https://github.com/Yifan-Lan/Phi/blob/HEAD/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a51ae45a1f6c0b5b","code_sha256_prefix":"a51ae45a1f6c0b5b","mcp_get_code":{"code_sha256":"a51ae45a1f6c0b5b"}},{"arxiv_id":"2507.11630","arxiv_id_is_arxiv":true,"paper":null,"title":"arXiv:2507.11630","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"AlignmentResearch/harmtune","path":"harmtune/utils/utils.py","file_url":"https://github.com/AlignmentResearch/harmtune/blob/HEAD/harmtune/utils/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, AlignmentResearch/harmtune when it was checked","code_sha256":"6784396112f94bd1","code_sha256_prefix":"6784396112f94bd1","mcp_get_code":{"code_sha256":"6784396112f94bd1"}},{"arxiv_id":"2506.14761","arxiv_id_is_arxiv":true,"paper":"/paper/from-bytes-to-ideas-language-modeling-with","title":"From Bytes to Ideas: Language Modeling with Autoregressive U-Nets","date":"2025-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/lingua","path":"lingua/args.py","file_url":"https://github.com/facebookresearch/lingua/blob/HEAD/lingua/args.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"15be2e56e073a228","code_sha256_prefix":"15be2e56e073a228","mcp_get_code":{"code_sha256":"15be2e56e073a228"}},{"arxiv_id":"2506.13752","arxiv_id_is_arxiv":true,"paper":"/paper/steering-llm-thinking-with-budget-guidance","title":"Steering LLM Thinking with Budget Guidance","date":"2025-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"umass-embodied-agi/budgetguidance","path":"3rdparty/trl/trl/core.py","file_url":"https://github.com/umass-embodied-agi/budgetguidance/blob/HEAD/3rdparty/trl/trl/core.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"dfd0ecd9cb25af69","code_sha256_prefix":"dfd0ecd9cb25af69","mcp_get_code":{"code_sha256":"dfd0ecd9cb25af69"}},{"arxiv_id":"2505.24625","arxiv_id_is_arxiv":true,"paper":"/paper/learning-from-videos-for-3d-world-enhancing","title":"Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors","date":"2025-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LaVi-Lab/Video-3D-LLM","path":"trl/core.py","file_url":"https://github.com/LaVi-Lab/Video-3D-LLM/blob/HEAD/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a51ae45a1f6c0b5b","code_sha256_prefix":"a51ae45a1f6c0b5b","mcp_get_code":{"code_sha256":"a51ae45a1f6c0b5b"}},{"arxiv_id":"2505.16839","arxiv_id_is_arxiv":true,"paper":"/paper/lavida-a-large-diffusion-language-model-for","title":"LaViDa: A Large Diffusion Language Model for Multimodal Understanding","date":"2025-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jacklishufan/lavida","path":"trl/core.py","file_url":"https://github.com/jacklishufan/lavida/blob/HEAD/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a51ae45a1f6c0b5b","code_sha256_prefix":"a51ae45a1f6c0b5b","mcp_get_code":{"code_sha256":"a51ae45a1f6c0b5b"}},{"arxiv_id":"2505.15656","arxiv_id_is_arxiv":true,"paper":"/paper/be-careful-when-fine-tuning-on-open-source","title":"Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-coai/backdoor-data-extraction","path":"train/trl/core.py","file_url":"https://github.com/thu-coai/backdoor-data-extraction/blob/HEAD/train/trl/core.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"dfd0ecd9cb25af69","code_sha256_prefix":"dfd0ecd9cb25af69","mcp_get_code":{"code_sha256":"dfd0ecd9cb25af69"}},{"arxiv_id":"2505.15404","arxiv_id_is_arxiv":true,"paper":"/paper/how-should-we-enhance-the-safety-of-large","title":"How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-coai/lrm-safety-study","path":"trl/trl/core.py","file_url":"https://github.com/thu-coai/lrm-safety-study/blob/HEAD/trl/trl/core.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"dfd0ecd9cb25af69","code_sha256_prefix":"dfd0ecd9cb25af69","mcp_get_code":{"code_sha256":"dfd0ecd9cb25af69"}},{"arxiv_id":"2505.09655","arxiv_id_is_arxiv":true,"paper":"/paper/dra-grpo-exploring-diversity-aware-reward","title":"DRA-GRPO: Exploring Diversity-Aware Reward Adjustment for R1-Zero-Like Training of Large Language Models","date":"2025-05-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiwenc1/dra-grpo","path":"src/open_r1/trl/core.py","file_url":"https://github.com/xiwenc1/dra-grpo/blob/HEAD/src/open_r1/trl/core.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"dfd0ecd9cb25af69","code_sha256_prefix":"dfd0ecd9cb25af69","mcp_get_code":{"code_sha256":"dfd0ecd9cb25af69"}},{"arxiv_id":"2504.20157","arxiv_id_is_arxiv":true,"paper":"/paper/toward-evaluative-thinking-meta-policy","title":"Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models","date":"2025-04-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"minnesotanlp/mpo","path":"trl/core.py","file_url":"https://github.com/minnesotanlp/mpo/blob/HEAD/trl/core.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"Apache-2.0, as GitHub detects it on this paper's repository, minnesotanlp/mpo, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it","code_sha256":"dfd0ecd9cb25af69","code_sha256_prefix":"dfd0ecd9cb25af69","mcp_get_code":{"code_sha256":"dfd0ecd9cb25af69"}},{"arxiv_id":"2503.18866","arxiv_id_is_arxiv":true,"paper":"/paper/reasoning-to-learn-from-latent-thoughts","title":"Reasoning to Learn from Latent Thoughts","date":"2025-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ryoungj/BoLT","path":"lingua/args.py","file_url":"https://github.com/ryoungj/BoLT/blob/HEAD/lingua/args.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"15be2e56e073a228","code_sha256_prefix":"15be2e56e073a228","mcp_get_code":{"code_sha256":"15be2e56e073a228"}},{"arxiv_id":"2501.09620","arxiv_id_is_arxiv":true,"paper":"/paper/beyond-reward-hacking-causal-rewards-for","title":"Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment","date":"2025-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tatsu-lab/alpaca_farm","path":"src/alpaca_farm/common.py","file_url":"https://github.com/tatsu-lab/alpaca_farm/blob/HEAD/src/alpaca_farm/common.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"f5ff77db7757bc92","code_sha256_prefix":"f5ff77db7757bc92","mcp_get_code":{"code_sha256":"f5ff77db7757bc92"}},{"arxiv_id":"2501.06911","arxiv_id_is_arxiv":true,"paper":"/paper/risk-averse-finetuning-of-large-language","title":"Risk-Averse Finetuning of Large Language Models","date":"2025-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sapanachaudhary/ra-rlhf","path":"trl/core.py","file_url":"https://github.com/sapanachaudhary/ra-rlhf/blob/HEAD/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"1782ce5551146615","code_sha256_prefix":"1782ce5551146615","mcp_get_code":{"code_sha256":"1782ce5551146615"}},{"arxiv_id":"2501.00656","arxiv_id_is_arxiv":true,"paper":"/paper/2-olmo-2-furious","title":"2 OLMo 2 Furious","date":"2024-12-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/olmo","path":"olmo/safetensors_util.py","file_url":"https://github.com/allenai/olmo/blob/HEAD/olmo/safetensors_util.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"b593a4bbddcc66c3","code_sha256_prefix":"b593a4bbddcc66c3","mcp_get_code":{"code_sha256":"b593a4bbddcc66c3"}},{"arxiv_id":"2412.09764","arxiv_id_is_arxiv":true,"paper":"/paper/memory-layers-at-scale","title":"Memory Layers at Scale","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/memory","path":"lingua/args.py","file_url":"https://github.com/facebookresearch/memory/blob/HEAD/lingua/args.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, facebookresearch/memory when it was checked","code_sha256":"15be2e56e073a228","code_sha256_prefix":"15be2e56e073a228","mcp_get_code":{"code_sha256":"15be2e56e073a228"}},{"arxiv_id":"2412.07689","arxiv_id_is_arxiv":true,"paper":"/paper/drivemm-all-in-one-large-multimodal-model-for","title":"DriveMM: All-in-One Large Multimodal Model for Autonomous Driving","date":"2024-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhijian11/DriveMM","path":"trl/core.py","file_url":"https://github.com/zhijian11/DriveMM/blob/HEAD/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a51ae45a1f6c0b5b","code_sha256_prefix":"a51ae45a1f6c0b5b","mcp_get_code":{"code_sha256":"a51ae45a1f6c0b5b"}},{"arxiv_id":"2412.03248","arxiv_id_is_arxiv":true,"paper":"/paper/aim-adaptive-inference-of-multi-modal-llms","title":"AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning","date":"2024-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lavi-lab/aim","path":"trl/core.py","file_url":"https://github.com/lavi-lab/aim/blob/HEAD/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a51ae45a1f6c0b5b","code_sha256_prefix":"a51ae45a1f6c0b5b","mcp_get_code":{"code_sha256":"a51ae45a1f6c0b5b"}},{"arxiv_id":"2411.15024","arxiv_id_is_arxiv":true,"paper":"/paper/dycoke-dynamic-compression-of-tokens-for-fast","title":"DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models","date":"2024-11-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kd-tao/dycoke","path":"trl/core.py","file_url":"https://github.com/kd-tao/dycoke/blob/HEAD/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a51ae45a1f6c0b5b","code_sha256_prefix":"a51ae45a1f6c0b5b","mcp_get_code":{"code_sha256":"a51ae45a1f6c0b5b"}},{"arxiv_id":"2411.11909","arxiv_id_is_arxiv":true,"paper":"/paper/symdpo-boosting-in-context-learning-of-large","title":"SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization","date":"2024-11-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"APiaoG/SymDPO","path":"trl/core.py","file_url":"https://github.com/APiaoG/SymDPO/blob/HEAD/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, APiaoG/SymDPO when it was checked","code_sha256":"a51ae45a1f6c0b5b","code_sha256_prefix":"a51ae45a1f6c0b5b","mcp_get_code":{"code_sha256":"a51ae45a1f6c0b5b"}},{"arxiv_id":"2411.11360","arxiv_id_is_arxiv":true,"paper":"/paper/ccexpert-advancing-mllm-capability-in-remote","title":"CCExpert: Advancing MLLM Capability in Remote Sensing Change Captioning with Difference-Aware Integration and a Foundational Dataset","date":"2024-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"meize0729/ccexpert","path":"trl/core.py","file_url":"https://github.com/meize0729/ccexpert/blob/HEAD/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a51ae45a1f6c0b5b","code_sha256_prefix":"a51ae45a1f6c0b5b","mcp_get_code":{"code_sha256":"a51ae45a1f6c0b5b"}},{"arxiv_id":"2411.05238","arxiv_id_is_arxiv":true,"paper":"/paper/generating-highly-designable-proteins-with","title":"Generating Highly Designable Proteins with Geometric Algebra Flow Matching","date":"2024-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hits-mli/gafl","path":"gafl/experiment_utils.py","file_url":"https://github.com/hits-mli/gafl/blob/HEAD/gafl/experiment_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, hits-mli/gafl (NOASSERTION)","code_sha256":"262dce4f87fc7ad0","code_sha256_prefix":"262dce4f87fc7ad0","mcp_get_code":{"code_sha256":"262dce4f87fc7ad0"}},{"arxiv_id":"2410.17637","arxiv_id_is_arxiv":true,"paper":"/paper/mia-dpo-multi-image-augmented-direct","title":"MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models","date":"2024-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liuziyu77/mia-dpo","path":"LLaVA-Hound-DPO/llava_hound_dpo/trl/core.py","file_url":"https://github.com/liuziyu77/mia-dpo/blob/HEAD/LLaVA-Hound-DPO/llava_hound_dpo/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a51ae45a1f6c0b5b","code_sha256_prefix":"a51ae45a1f6c0b5b","mcp_get_code":{"code_sha256":"a51ae45a1f6c0b5b"}},{"arxiv_id":"2410.16198","arxiv_id_is_arxiv":true,"paper":"/paper/improve-vision-language-model-chain-of","title":"Improve Vision Language Model Chain-of-thought Reasoning","date":"2024-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"riflezhang/llava-hound-dpo","path":"llava_hound_dpo/trl/core.py","file_url":"https://github.com/riflezhang/llava-hound-dpo/blob/HEAD/llava_hound_dpo/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, riflezhang/llava-hound-dpo when it was checked","code_sha256":"a51ae45a1f6c0b5b","code_sha256_prefix":"a51ae45a1f6c0b5b","mcp_get_code":{"code_sha256":"a51ae45a1f6c0b5b"}},{"arxiv_id":"2410.15221","arxiv_id_is_arxiv":true,"paper":"/paper/intersectionzoo-eco-driving-for-benchmarking","title":"IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning","date":"2024-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mit-wu-lab/IntersectionZoo","path":"code/policy_evaluation.py","file_url":"https://github.com/mit-wu-lab/IntersectionZoo/blob/HEAD/code/policy_evaluation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"15be2e56e073a228","code_sha256_prefix":"15be2e56e073a228","mcp_get_code":{"code_sha256":"15be2e56e073a228"}},{"arxiv_id":"2410.14673","arxiv_id_is_arxiv":true,"paper":"/paper/self-supervised-contrastive-learning-performs","title":"Self-supervised contrastive learning performs non-linear system identification","date":"2024-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dynamical-inference/dcl","path":"dcl/datajoint/sweep.py","file_url":"https://github.com/dynamical-inference/dcl/blob/HEAD/dcl/datajoint/sweep.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from dynamical-inference/ebc, and GitHub detected no licence in that repository when it was checked","code_sha256":"f30ac4807ed6c8c5","code_sha256_prefix":"f30ac4807ed6c8c5","mcp_get_code":{"code_sha256":"f30ac4807ed6c8c5"}},{"arxiv_id":"2410.08827","arxiv_id_is_arxiv":true,"paper":"/paper/do-unlearning-methods-remove-information-from","title":"Do Unlearning Methods Remove Information from Language Model Weights?","date":"2024-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aghyad-deeb/unlearning_evaluation","path":"pipeline.py","file_url":"https://github.com/aghyad-deeb/unlearning_evaluation/blob/HEAD/pipeline.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, aghyad-deeb/unlearning_evaluation when it was checked","code_sha256":"0260364dcc364961","code_sha256_prefix":"0260364dcc364961","mcp_get_code":{"code_sha256":"0260364dcc364961"}},{"arxiv_id":"2410.06101","arxiv_id_is_arxiv":true,"paper":"/paper/coevolving-with-the-other-you-fine-tuning-llm","title":"Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Harry67Hu/CORY","path":"trl/core.py","file_url":"https://github.com/Harry67Hu/CORY/blob/HEAD/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a51ae45a1f6c0b5b","code_sha256_prefix":"a51ae45a1f6c0b5b","mcp_get_code":{"code_sha256":"a51ae45a1f6c0b5b"}},{"arxiv_id":"2410.05757","arxiv_id_is_arxiv":true,"paper":"/paper/temperature-optimization-for-bayesian-deep","title":"Temperature Optimization for Bayesian Deep Learning","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weiyaw/tempered-posteriors","path":"visual_utils.py","file_url":"https://github.com/weiyaw/tempered-posteriors/blob/HEAD/visual_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"91345e63f4999e0e","code_sha256_prefix":"91345e63f4999e0e","mcp_get_code":{"code_sha256":"91345e63f4999e0e"}},{"arxiv_id":"2410.01380","arxiv_id_is_arxiv":true,"paper":"/paper/knowledge-entropy-decay-during-language-model","title":"Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition","date":"2024-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kaistAI/Knowledge-Entropy","path":"olmo/safetensors_util.py","file_url":"https://github.com/kaistAI/Knowledge-Entropy/blob/HEAD/olmo/safetensors_util.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"b593a4bbddcc66c3","code_sha256_prefix":"b593a4bbddcc66c3","mcp_get_code":{"code_sha256":"b593a4bbddcc66c3"}},{"arxiv_id":"2409.20353","arxiv_id_is_arxiv":true,"paper":"/paper/cableinspect-ad-an-expert-annotated-anomaly","title":"CableInspect-AD: An Expert-Annotated Anomaly Detection Dataset","date":"2024-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mila-iqia/cableinspect-ad-code","path":"src/enhanced-patchcore/post_processing/post_processing_unsupervised_results.py","file_url":"https://github.com/mila-iqia/cableinspect-ad-code/blob/HEAD/src/enhanced-patchcore/post_processing/post_processing_unsupervised_results.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"94bd9041d52daa8d","code_sha256_prefix":"94bd9041d52daa8d","mcp_get_code":{"code_sha256":"94bd9041d52daa8d"}},{"arxiv_id":"2408.17355","arxiv_id_is_arxiv":true,"paper":"/paper/bidirectional-decoding-improving-action","title":"Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling","date":"2024-08-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jubayer-hamid/bid_lerobot","path":"lerobot/common/datasets/utils.py","file_url":"https://github.com/jubayer-hamid/bid_lerobot/blob/HEAD/lerobot/common/datasets/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e2adf71cdd509f3e","code_sha256_prefix":"e2adf71cdd509f3e","mcp_get_code":{"code_sha256":"e2adf71cdd509f3e"}},{"arxiv_id":"2407.10240","arxiv_id_is_arxiv":true,"paper":"/paper/xlstmtime-long-term-time-series-forecasting","title":"xLSTMTime : Long-term Time Series Forecasting With xLSTM","date":"2024-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"muslehal/xLSTMTime","path":"src/utils.py","file_url":"https://github.com/muslehal/xLSTMTime/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"4ac8e022e2aa0b43","code_sha256_prefix":"4ac8e022e2aa0b43","mcp_get_code":{"code_sha256":"4ac8e022e2aa0b43"}},{"arxiv_id":"2406.19371","arxiv_id_is_arxiv":true,"paper":"/paper/suri-multi-constraint-instruction-following","title":"Suri: Multi-constraint Instruction Following for Long-form Text Generation","date":"2024-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chtmp223/suri","path":"ft/lib/trl_mod/core.py","file_url":"https://github.com/chtmp223/suri/blob/HEAD/ft/lib/trl_mod/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, chtmp223/suri when it was checked","code_sha256":"a51ae45a1f6c0b5b","code_sha256_prefix":"a51ae45a1f6c0b5b","mcp_get_code":{"code_sha256":"a51ae45a1f6c0b5b"}},{"arxiv_id":"2406.11280","arxiv_id_is_arxiv":true,"paper":"/paper/i-srt-aligning-large-multimodal-models-for","title":"ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yonseivnl/vlm-rlaif","path":"RLAIF/data_utils/common_utils.py","file_url":"https://github.com/yonseivnl/vlm-rlaif/blob/HEAD/RLAIF/data_utils/common_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"f5ff77db7757bc92","code_sha256_prefix":"f5ff77db7757bc92","mcp_get_code":{"code_sha256":"f5ff77db7757bc92"}},{"arxiv_id":"2406.11280","arxiv_id_is_arxiv":true,"paper":"/paper/i-srt-aligning-large-multimodal-models-for","title":"ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"snumprlab/SRT","path":"trl/core.py","file_url":"https://github.com/snumprlab/SRT/blob/HEAD/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, snumprlab/SRT when it was checked","code_sha256":"a51ae45a1f6c0b5b","code_sha256_prefix":"a51ae45a1f6c0b5b","mcp_get_code":{"code_sha256":"a51ae45a1f6c0b5b"}},{"arxiv_id":"2406.05213","arxiv_id_is_arxiv":true,"paper":"/paper/on-subjective-uncertainty-quantification-and","title":"On Subjective Uncertainty Quantification and Calibration in Natural Language Generation","date":"2024-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"meta-inf/suq-nlg","path":"generation/utils.py","file_url":"https://github.com/meta-inf/suq-nlg/blob/HEAD/generation/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"6afd679238dc532d","code_sha256_prefix":"6afd679238dc532d","mcp_get_code":{"code_sha256":"6afd679238dc532d"}},{"arxiv_id":"2405.15589","arxiv_id_is_arxiv":true,"paper":"/paper/efficient-adversarial-training-in-llms-with","title":"Efficient Adversarial Training in LLMs with Continuous Attacks","date":"2024-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sophie-xhonneux/continuous-advtrain","path":"src/database_handling.py","file_url":"https://github.com/sophie-xhonneux/continuous-advtrain/blob/HEAD/src/database_handling.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"15be2e56e073a228","code_sha256_prefix":"15be2e56e073a228","mcp_get_code":{"code_sha256":"15be2e56e073a228"}},{"arxiv_id":"2403.06754","arxiv_id_is_arxiv":true,"paper":"/paper/alarm-align-language-models-via-hierarchical","title":"ALaRM: Align Language Models via Hierarchical Rewards Modeling","date":"2024-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"halfrot/ALaRM","path":"trl/trl/core.py","file_url":"https://github.com/halfrot/ALaRM/blob/HEAD/trl/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"1782ce5551146615","code_sha256_prefix":"1782ce5551146615","mcp_get_code":{"code_sha256":"1782ce5551146615"}},{"arxiv_id":"2402.18059","arxiv_id_is_arxiv":true,"paper":"/paper/token-specific-watermarking-with-enhanced","title":"Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mignonjia/ts_watermark","path":"utils/submitit.py","file_url":"https://github.com/mignonjia/ts_watermark/blob/HEAD/utils/submitit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, mignonjia/ts_watermark when it was checked","code_sha256":"55a42447218367a6","code_sha256_prefix":"55a42447218367a6","mcp_get_code":{"code_sha256":"55a42447218367a6"}},{"arxiv_id":"2402.11078","arxiv_id_is_arxiv":true,"paper":"/paper/model-editing-by-pure-fine-tuning","title":"Model Editing by Standard Fine-Tuning","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"au-revoir/model-editing-ft","path":"trl/core.py","file_url":"https://github.com/au-revoir/model-editing-ft/blob/HEAD/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, au-revoir/model-editing-ft when it was checked","code_sha256":"1782ce5551146615","code_sha256_prefix":"1782ce5551146615","mcp_get_code":{"code_sha256":"1782ce5551146615"}},{"arxiv_id":"2402.05133","arxiv_id_is_arxiv":true,"paper":"/paper/personalized-language-modeling-from","title":"Personalized Language Modeling from Personalized Human Feedback","date":"2024-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"humainlab/personalized_rlhf","path":"evaluate/alpaca_farm/common.py","file_url":"https://github.com/humainlab/personalized_rlhf/blob/HEAD/evaluate/alpaca_farm/common.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"f5ff77db7757bc92","code_sha256_prefix":"f5ff77db7757bc92","mcp_get_code":{"code_sha256":"f5ff77db7757bc92"}},{"arxiv_id":"2311.07222","arxiv_id_is_arxiv":true,"paper":"/paper/neural-general-circulation-models","title":"Neural General Circulation Models for Weather and Climate","date":"2023-11-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"neuralgcm/neuralgcm","path":"neuralgcm/reference_code/train_utils.py","file_url":"https://github.com/neuralgcm/neuralgcm/blob/HEAD/neuralgcm/reference_code/train_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"4e71b8bf4cde8432","code_sha256_prefix":"4e71b8bf4cde8432","mcp_get_code":{"code_sha256":"4e71b8bf4cde8432"}},{"arxiv_id":"2310.14503","arxiv_id_is_arxiv":true,"paper":"/paper/diversify-question-generation-with-retrieval","title":"Diversify Question Generation with Retrieval-Augmented Style Transfer","date":"2023-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gouqi666/RAST","path":"rag/core.py","file_url":"https://github.com/gouqi666/RAST/blob/HEAD/rag/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, gouqi666/RAST when it was checked","code_sha256":"ddf7639e1bf7edf8","code_sha256_prefix":"ddf7639e1bf7edf8","mcp_get_code":{"code_sha256":"ddf7639e1bf7edf8"}},{"arxiv_id":"2310.11564","arxiv_id_is_arxiv":true,"paper":"/paper/personalized-soups-personalized-large","title":"Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging","date":"2023-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"joeljang/rlphf","path":"gpt4_evaluate/alpaca_farm/common.py","file_url":"https://github.com/joeljang/rlphf/blob/HEAD/gpt4_evaluate/alpaca_farm/common.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, joeljang/rlphf when it was checked","code_sha256":"f5ff77db7757bc92","code_sha256_prefix":"f5ff77db7757bc92","mcp_get_code":{"code_sha256":"f5ff77db7757bc92"}},{"arxiv_id":"2309.17130","arxiv_id_is_arxiv":true,"paper":"/paper/grande-gradient-based-decision-tree-ensembles","title":"GRANDE: Gradient-Based Decision Tree Ensembles for Tabular Data","date":"2023-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"s-marton/gradtree","path":"experiments_paper_gradtree/utilities/utilities_GDT.py","file_url":"https://github.com/s-marton/gradtree/blob/HEAD/experiments_paper_gradtree/utilities/utilities_GDT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"5cd213cdf1030eee","code_sha256_prefix":"5cd213cdf1030eee","mcp_get_code":{"code_sha256":"5cd213cdf1030eee"}},{"arxiv_id":"2309.09055","arxiv_id_is_arxiv":true,"paper":"/paper/exploring-the-impact-of-low-rank-adaptation","title":"Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF","date":"2023-09-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"simengsun/alpaca_farm_lora","path":"alpaca_farm/src/alpaca_farm/common.py","file_url":"https://github.com/simengsun/alpaca_farm_lora/blob/HEAD/alpaca_farm/src/alpaca_farm/common.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"f5ff77db7757bc92","code_sha256_prefix":"f5ff77db7757bc92","mcp_get_code":{"code_sha256":"f5ff77db7757bc92"}},{"arxiv_id":"2307.12375","arxiv_id_is_arxiv":true,"paper":"/paper/in-context-learning-in-large-language-models","title":"In-Context Learning Learns Label Relationships but Is Not Conventional Learning","date":"2023-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jlko/in_context_learning","path":"llm/plot_utils.py","file_url":"https://github.com/jlko/in_context_learning/blob/HEAD/llm/plot_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, jlko/in_context_learning when it was checked","code_sha256":"8e87d24bb6fec877","code_sha256_prefix":"8e87d24bb6fec877","mcp_get_code":{"code_sha256":"8e87d24bb6fec877"}},{"arxiv_id":"2307.06306","arxiv_id_is_arxiv":true,"paper":"/paper/locally-adaptive-federated-learning-via","title":"Locally Adaptive Federated Learning","date":"2023-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IssamLaradji/sps","path":"src/utils.py","file_url":"https://github.com/IssamLaradji/sps/blob/HEAD/src/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, IssamLaradji/sps when it was checked","code_sha256":"0e62b13e0a76c17b","code_sha256_prefix":"0e62b13e0a76c17b","mcp_get_code":{"code_sha256":"0e62b13e0a76c17b"}},{"arxiv_id":"2305.18290","arxiv_id_is_arxiv":true,"paper":"/paper/direct-preference-optimization-your-language","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","date":"2023-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"padlex/trl","path":"trl/core.py","file_url":"https://github.com/padlex/trl/blob/HEAD/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a51ae45a1f6c0b5b","code_sha256_prefix":"a51ae45a1f6c0b5b","mcp_get_code":{"code_sha256":"a51ae45a1f6c0b5b"}},{"arxiv_id":"2304.13774","arxiv_id_is_arxiv":true,"paper":"/paper/distance-weighted-supervised-learning-for","title":"Distance Weighted Supervised Learning for Offline Interaction Data","date":"2023-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jhejna/dwsl","path":"research/algs/dwsl.py","file_url":"https://github.com/jhejna/dwsl/blob/HEAD/research/algs/dwsl.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"0954fb2e0809ee19","code_sha256_prefix":"0954fb2e0809ee19","mcp_get_code":{"code_sha256":"0954fb2e0809ee19"}},{"arxiv_id":"2206.00761","arxiv_id_is_arxiv":true,"paper":"/paper/on-reinforcement-learning-and-distribution","title":"On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting","date":"2022-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver/gdc","path":"cdpg/cdpg/core.py","file_url":"https://github.com/naver/gdc/blob/HEAD/cdpg/cdpg/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, naver/gdc (NOASSERTION)","code_sha256":"8826b925c6d6132e","code_sha256_prefix":"8826b925c6d6132e","mcp_get_code":{"code_sha256":"8826b925c6d6132e"}},{"arxiv_id":"2205.07477","arxiv_id_is_arxiv":true,"paper":"/paper/manifold-characteristics-that-predict","title":"Manifold Characteristics That Predict Downstream Task Performance","date":"2022-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bytefuse/representation-manifold-quality-metric","path":"src/utils.py","file_url":"https://github.com/bytefuse/representation-manifold-quality-metric/blob/HEAD/src/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"ab7cb2f6ec7f6e67","code_sha256_prefix":"ab7cb2f6ec7f6e67","mcp_get_code":{"code_sha256":"ab7cb2f6ec7f6e67"}},{"arxiv_id":"2106.04815","arxiv_id_is_arxiv":true,"paper":"/paper/chacha-for-online-automl","title":"ChaCha for Online AutoML","date":"2021-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/FLAML","path":"flaml/tune/scheduler/online_scheduler.py","file_url":"https://github.com/microsoft/FLAML/blob/HEAD/flaml/tune/scheduler/online_scheduler.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"fbb7d311c959569d","code_sha256_prefix":"fbb7d311c959569d","mcp_get_code":{"code_sha256":"fbb7d311c959569d"}},{"arxiv_id":"2105.06422","arxiv_id_is_arxiv":true,"paper":"/paper/causally-motivated-shortcut-removal-using","title":"Causally motivated Shortcut Removal Using Auxiliary Labels","date":"2021-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mymakar/causally_motivated_shortcut_removal","path":"shared/train_utils.py","file_url":"https://github.com/mymakar/causally_motivated_shortcut_removal/blob/HEAD/shared/train_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"3e2e16445f6f92e6","code_sha256_prefix":"3e2e16445f6f92e6","mcp_get_code":{"code_sha256":"3e2e16445f6f92e6"}},{"arxiv_id":"2105.03418","arxiv_id_is_arxiv":true,"paper":"/paper/deep-learning-hamiltonian-monte-carlo","title":"Deep Learning Hamiltonian Monte Carlo","date":"2021-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"saforem2/l2hmc-qcd","path":"src/l2hmc/configs.py","file_url":"https://github.com/saforem2/l2hmc-qcd/blob/HEAD/src/l2hmc/configs.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"3e2181383d727aba","code_sha256_prefix":"3e2181383d727aba","mcp_get_code":{"code_sha256":"3e2181383d727aba"}},{"arxiv_id":"2104.05344","arxiv_id_is_arxiv":true,"paper":"/paper/how-sensitive-are-meta-learners-to-dataset","title":"How Sensitive are Meta-Learners to Dataset Imbalance?","date":"2021-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mattochal/imbalanced_fsl_public","path":"generator.py","file_url":"https://github.com/mattochal/imbalanced_fsl_public/blob/HEAD/generator.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"0b2f8809055e38f5","code_sha256_prefix":"0b2f8809055e38f5","mcp_get_code":{"code_sha256":"0b2f8809055e38f5"}},{"arxiv_id":"2101.02523","arxiv_id_is_arxiv":true,"paper":"/paper/few-shot-learning-with-class-imbalance","title":"Few-Shot Learning with Class Imbalance","date":"2021-01-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","code_sha256":"0b2f8809055e38f5","code_sha256_prefix":"0b2f8809055e38f5","mcp_get_code":{"code_sha256":"0b2f8809055e38f5"}},{"arxiv_id":"2012.11635","arxiv_id_is_arxiv":true,"paper":"/paper/2012-11635","title":"A Distributional Approach to Controlled Text Generation","date":"2020-12-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver/gdc","path":"dpg/gdc/gdc/core.py","file_url":"https://github.com/naver/gdc/blob/HEAD/dpg/gdc/gdc/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, naver/gdc (NOASSERTION)","code_sha256":"2f2b2a8fe27dcc79","code_sha256_prefix":"2f2b2a8fe27dcc79","mcp_get_code":{"code_sha256":"2f2b2a8fe27dcc79"}},{"arxiv_id":"2012.11635","arxiv_id_is_arxiv":true,"paper":"/paper/2012-11635","title":"A Distributional Approach to Controlled Text Generation","date":"2020-12-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","code_sha256":"8826b925c6d6132e","code_sha256_prefix":"8826b925c6d6132e","mcp_get_code":{"code_sha256":"8826b925c6d6132e"}},{"arxiv_id":"2011.02952","arxiv_id_is_arxiv":true,"paper":"/paper/generalized-negative-correlation-learning-for","title":"Generalized Negative Correlation Learning for Deep Ensembling","date":"2020-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sbuschjaeger/Pysembles","path":"pysembles/Utils.py","file_url":"https://github.com/sbuschjaeger/Pysembles/blob/HEAD/pysembles/Utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"9920339eff7f6691","code_sha256_prefix":"9920339eff7f6691","mcp_get_code":{"code_sha256":"9920339eff7f6691"}},{"arxiv_id":"1703.02628","arxiv_id_is_arxiv":true,"paper":"/paper/global-optimization-of-lipschitz-functions","title":"Global optimization of Lipschitz functions","date":"2017-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Sycor4x/lipo","path":"benchmarks.py","file_url":"https://github.com/Sycor4x/lipo/blob/HEAD/benchmarks.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"9bbabe0c6fef21bb","code_sha256_prefix":"9bbabe0c6fef21bb","mcp_get_code":{"code_sha256":"9bbabe0c6fef21bb"}},{"arxiv_id":"Zhong_AIM_Adaptive_Inference_of_Multi-Modal_LLMs_via_Token_Merging_and_ICCV_2025_paper","arxiv_id_is_arxiv":false,"paper":null,"title":"CVF open access id Zhong_AIM_Adaptive_Inference_of_Multi-Modal_LLMs_via_Token_Merging_and_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"LaVi-Lab/AIM","path":"trl/core.py","file_url":"https://github.com/LaVi-Lab/AIM/blob/HEAD/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a51ae45a1f6c0b5b","code_sha256_prefix":"a51ae45a1f6c0b5b","mcp_get_code":{"code_sha256":"a51ae45a1f6c0b5b"}},{"arxiv_id":"2025.findings-acl.359","arxiv_id_is_arxiv":false,"paper":null,"title":"ACL Anthology id 2025.findings-acl.359","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"G-JWLee/TAMP","path":"trl/core.py","file_url":"https://github.com/G-JWLee/TAMP/blob/HEAD/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a51ae45a1f6c0b5b","code_sha256_prefix":"a51ae45a1f6c0b5b","mcp_get_code":{"code_sha256":"a51ae45a1f6c0b5b"}},{"arxiv_id":"2024.acl-long.732","arxiv_id_is_arxiv":false,"paper":null,"title":"ACL Anthology id 2024.acl-long.732","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"wchrepo/mulfe","path":"evaluation/utils.py","file_url":"https://github.com/wchrepo/mulfe/blob/HEAD/evaluation/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"fc1cb4f8e17c39aa","code_sha256_prefix":"fc1cb4f8e17c39aa","mcp_get_code":{"code_sha256":"fc1cb4f8e17c39aa"}}],"record_sha256":"92c55a85a469c455b579eb9029a46f75632ede1ea8310e1dfd89d6b40627ffe8","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}