{"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/prepare-prompts","entry":"prepare_prompts","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":11,"n_papers_ran":7,"n_papers_ran_no_instrument_failure":3,"n_papers_ran_instrument_only":4,"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":9,"n_samples_ran":7,"n_samples_constructed":0,"n_samples_ran_checked":3,"n_samples_instrument":4,"n_samples_unverified":2,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":6,"n_places_pointer_only_link_open":0,"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":4,"ran_fixture":0,"ran":3,"unverified":2},"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":"2604.27998","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2604-27998","title":"Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"DJC-GO-SOLO/Latent-SFT","path":"sglang_latent_reasoning_pkg/benchmark/bench_in_batch_prefix/bench_in_batch_prefix.py","file_url":"https://github.com/DJC-GO-SOLO/Latent-SFT/blob/HEAD/sglang_latent_reasoning_pkg/benchmark/bench_in_batch_prefix/bench_in_batch_prefix.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":"e5914c7114b177c6","code_sha256_prefix":"e5914c7114b177c6","mcp_get_code":{"code_sha256":"e5914c7114b177c6"}},{"arxiv_id":"2602.11683","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-11683","title":"THINKROUTER: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"eric-ai-lab/Soft-Thinking","path":"sglang_soft_thinking_pkg/benchmark/bench_in_batch_prefix/bench_in_batch_prefix.py","file_url":"https://github.com/eric-ai-lab/Soft-Thinking/blob/HEAD/sglang_soft_thinking_pkg/benchmark/bench_in_batch_prefix/bench_in_batch_prefix.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":"e5914c7114b177c6","code_sha256_prefix":"e5914c7114b177c6","mcp_get_code":{"code_sha256":"e5914c7114b177c6"}},{"arxiv_id":"2601.18999","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-18999","title":"Randomization Boosts KV Caching, Learning Balances Query Load: A Joint Perspective","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"fzwark/KVRouting","path":"sglang-0.4.6/benchmark/bench_in_batch_prefix/bench_in_batch_prefix.py","file_url":"https://github.com/fzwark/KVRouting/blob/HEAD/sglang-0.4.6/benchmark/bench_in_batch_prefix/bench_in_batch_prefix.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, fzwark/KVRouting when it was checked","code_sha256":"e5914c7114b177c6","code_sha256_prefix":"e5914c7114b177c6","mcp_get_code":{"code_sha256":"e5914c7114b177c6"}},{"arxiv_id":"2601.04537","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-04537","title":"Linear Dynamics in the RLVR Training of Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Miaow-Lab/RLVR-Linearity","path":"evaluation/inference_vllm_offline.py","file_url":"https://github.com/Miaow-Lab/RLVR-Linearity/blob/HEAD/evaluation/inference_vllm_offline.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":"6404f02a3872c91e","code_sha256_prefix":"6404f02a3872c91e","mcp_get_code":{"code_sha256":"6404f02a3872c91e"}},{"arxiv_id":"2412.07618","arxiv_id_is_arxiv":true,"paper":"/paper/adapting-to-non-stationary-environments-multi","title":"Adapting to Non-Stationary Environments: Multi-Armed Bandit Enhanced Retrieval-Augmented Generation on Knowledge Graphs","date":"2024-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"futureeeeee/dynamic-rag","path":"utils.py","file_url":"https://github.com/futureeeeee/dynamic-rag/blob/HEAD/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, futureeeeee/dynamic-rag when it was checked","code_sha256":"884fefcc0d37c80e","code_sha256_prefix":"884fefcc0d37c80e","mcp_get_code":{"code_sha256":"884fefcc0d37c80e"}},{"arxiv_id":"2410.10093","arxiv_id_is_arxiv":true,"paper":"/paper/how-to-leverage-demonstration-data-in","title":"How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tengxiao1/GSIL","path":"gsil/generate.py","file_url":"https://github.com/tengxiao1/GSIL/blob/HEAD/gsil/generate.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, tengxiao1/GSIL when it was checked","code_sha256":"65ab2e38274df088","code_sha256_prefix":"65ab2e38274df088","mcp_get_code":{"code_sha256":"65ab2e38274df088"}},{"arxiv_id":"2410.02760","arxiv_id_is_arxiv":true,"paper":"/paper/erasing-conceptual-knowledge-from-language","title":"Erasing Conceptual Knowledge from Language Models","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rohitgandikota/erasing-llm","path":"trainscripts/erase.py","file_url":"https://github.com/rohitgandikota/erasing-llm/blob/HEAD/trainscripts/erase.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, rohitgandikota/erasing-llm when it was checked","code_sha256":"822e559e4fe066e8","code_sha256_prefix":"822e559e4fe066e8","mcp_get_code":{"code_sha256":"822e559e4fe066e8"}},{"arxiv_id":"2406.02888","arxiv_id_is_arxiv":true,"paper":"/paper/hydra-model-factorization-framework-for-black","title":"HYDRA: Model Factorization Framework for Black-Box LLM Personalization","date":"2024-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"night-chen/HYDRA","path":"adapter/generate/generate.py","file_url":"https://github.com/night-chen/HYDRA/blob/HEAD/adapter/generate/generate.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, night-chen/HYDRA when it was checked","code_sha256":"a5c4afa103aa6d76","code_sha256_prefix":"a5c4afa103aa6d76","mcp_get_code":{"code_sha256":"a5c4afa103aa6d76"}},{"arxiv_id":"2405.17888","arxiv_id_is_arxiv":true,"paper":"/paper/getting-more-juice-out-of-the-sft-data-reward","title":"Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment","date":"2024-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jasonjiaxiangli/reward_learning_sft","path":"src/evaluate.py","file_url":"https://github.com/jasonjiaxiangli/reward_learning_sft/blob/HEAD/src/evaluate.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":"6c6b96dbc3ac9f5a","code_sha256_prefix":"6c6b96dbc3ac9f5a","mcp_get_code":{"code_sha256":"6c6b96dbc3ac9f5a"}},{"arxiv_id":"2405.17888","arxiv_id_is_arxiv":true,"paper":"/paper/getting-more-juice-out-of-the-sft-data-reward","title":"Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment","date":"2024-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jasonjiaxiangli/reward_learning_sft","path":"src/generate.py","file_url":"https://github.com/jasonjiaxiangli/reward_learning_sft/blob/HEAD/src/generate.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":"1eb55970dd4151b3","code_sha256_prefix":"1eb55970dd4151b3","mcp_get_code":{"code_sha256":"1eb55970dd4151b3"}},{"arxiv_id":"2405.03000","arxiv_id_is_arxiv":true,"paper":"/paper/medadapter-efficient-test-time-adaptation-of","title":"MedAdapter: Efficient Test-Time Adaptation of Large Language Models towards Medical Reasoning","date":"2024-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wshi83/MedAdapter","path":"reward_model/orm/orm_guide.py","file_url":"https://github.com/wshi83/MedAdapter/blob/HEAD/reward_model/orm/orm_guide.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, wshi83/MedAdapter when it was checked","code_sha256":"a5c4afa103aa6d76","code_sha256_prefix":"a5c4afa103aa6d76","mcp_get_code":{"code_sha256":"a5c4afa103aa6d76"}},{"arxiv_id":"2401.06853","arxiv_id_is_arxiv":true,"paper":"/paper/large-language-models-can-learn-temporal","title":"Large Language Models Can Learn Temporal Reasoning","date":"2024-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiongsiheng/tg-llm","path":"src/Example_accelerate_inference.py","file_url":"https://github.com/xiongsiheng/tg-llm/blob/HEAD/src/Example_accelerate_inference.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":"67e14cf8263186c1","code_sha256_prefix":"67e14cf8263186c1","mcp_get_code":{"code_sha256":"67e14cf8263186c1"}}],"record_sha256":"1f6170bed2fb03ec641aaf96614f53011b206ae3c1aba87dfd40f0d7644d96c4","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}