{"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/load-prompt","entry":"load_prompt","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":25,"n_papers_ran":19,"n_papers_ran_no_instrument_failure":4,"n_papers_ran_instrument_only":15,"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":24,"n_samples_ran":18,"n_samples_constructed":0,"n_samples_ran_checked":3,"n_samples_instrument":15,"n_samples_unverified":6,"n_samples_fingerprinted":3,"n_places":25,"n_places_pointer_only":18,"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":15,"ran_fixture":0,"ran":3,"unverified":6},"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":"2609.14796","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2609-14796","title":"AI Persuasion as a Threat to Human Control","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"AlignmentResearch/puc","path":"prompts/loader.py","file_url":"https://github.com/AlignmentResearch/puc/blob/HEAD/prompts/loader.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, AlignmentResearch/puc when it was checked","code_sha256":"45c510e0b8adafbc","code_sha256_prefix":"45c510e0b8adafbc","mcp_get_code":{"code_sha256":"45c510e0b8adafbc"}},{"arxiv_id":"2609.01888","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2609-01888","title":"Does Playing it Safe Count as Faithfulness? Reassessing LVLM Hallucination Mitigation Methods","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"mehrdadfazli/AssessHalVLM","path":"methods/after/utils.py","file_url":"https://github.com/mehrdadfazli/AssessHalVLM/blob/HEAD/methods/after/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, mehrdadfazli/AssessHalVLM when it was checked","code_sha256":"0d53582061af2e49","code_sha256_prefix":"0d53582061af2e49","mcp_get_code":{"code_sha256":"0d53582061af2e49"}},{"arxiv_id":"2607.27379","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2607-27379","title":"HSS-Synth: Humanities and Social Sciences Data Synthesis for LLMs","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"pengr/HSS-Synth","path":"code/baseline/syn_method/LongForm.py","file_url":"https://github.com/pengr/HSS-Synth/blob/HEAD/code/baseline/syn_method/LongForm.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, pengr/HSS-Synth when it was checked","code_sha256":"53c6e2a7675a4a40","code_sha256_prefix":"53c6e2a7675a4a40","mcp_get_code":{"code_sha256":"53c6e2a7675a4a40"}},{"arxiv_id":"2606.15307","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-15307","title":"Adapting Reinforcement Learning with Chain-of-Thought Supervision for Explainable Detection of Hateful and Propagandistic Memes","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"MohamedBayan/MemeReason","path":"data_prep/prepare_training_data.py","file_url":"https://github.com/MohamedBayan/MemeReason/blob/HEAD/data_prep/prepare_training_data.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, MohamedBayan/MemeReason when it was checked","code_sha256":"f291f6bb0f74ccc4","code_sha256_prefix":"f291f6bb0f74ccc4","mcp_get_code":{"code_sha256":"f291f6bb0f74ccc4"}},{"arxiv_id":"2606.02800","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-02800","title":"Cosmos 3: Omnimodal World Models for Physical AI NVIDIA","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"nvidia/cosmos","path":"evaluation/cosmos3/generator/unigenbench/ugb_scorer.py","file_url":"https://github.com/nvidia/cosmos/blob/HEAD/evaluation/cosmos3/generator/unigenbench/ugb_scorer.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, nvidia/cosmos (NOASSERTION)","code_sha256":"231096399f905d44","code_sha256_prefix":"231096399f905d44","mcp_get_code":{"code_sha256":"231096399f905d44"}},{"arxiv_id":"2605.13412","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-13412","title":"LLMs as annotators of credibility assessment in Danish asylum decisions: evaluating classification performance and errors beyond aggregated metrics","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"glhr/RAB-Cred","path":"llm_annotation/llm_utils.py","file_url":"https://github.com/glhr/RAB-Cred/blob/HEAD/llm_annotation/llm_utils.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, glhr/RAB-Cred when it was checked","code_sha256":"8e9614852bb8afd7","code_sha256_prefix":"8e9614852bb8afd7","mcp_get_code":{"code_sha256":"8e9614852bb8afd7"}},{"arxiv_id":"2605.08083","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-08083","title":"LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"zhengkid/AutoTTS","path":"efficient_reasoning_controller/workspace/controller_search/claude_proposer.py","file_url":"https://github.com/zhengkid/AutoTTS/blob/HEAD/efficient_reasoning_controller/workspace/controller_search/claude_proposer.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, zhengkid/AutoTTS when it was checked","code_sha256":"c66918620c0773fb","code_sha256_prefix":"c66918620c0773fb","mcp_get_code":{"code_sha256":"c66918620c0773fb"}},{"arxiv_id":"2604.19459","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2604-19459","title":"Do LLMs Game Formalization? Evaluating Faithfulness in Logical Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"koreankiwi99/formalization-gaming","path":"src/utils/prompts.py","file_url":"https://github.com/koreankiwi99/formalization-gaming/blob/HEAD/src/utils/prompts.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":"872d7c12ef1aca3f","code_sha256_prefix":"872d7c12ef1aca3f","mcp_get_code":{"code_sha256":"872d7c12ef1aca3f"}},{"arxiv_id":"2603.26469","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2603-26469","title":"UNIFERENCE: A Discrete Event Simulation Framework for Developing Distributed AI Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Dogacel/Uniference","path":"benchmarks/commons.py","file_url":"https://github.com/Dogacel/Uniference/blob/HEAD/benchmarks/commons.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, Dogacel/Uniference (NOASSERTION)","code_sha256":"f2c1a078e541b975","code_sha256_prefix":"f2c1a078e541b975","mcp_get_code":{"code_sha256":"f2c1a078e541b975"}},{"arxiv_id":"2602.11509","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-11509","title":"Multimodal Fact-Level Attribution for Verifiable Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"meetdavidwan/murgat","path":"src/program_utils.py","file_url":"https://github.com/meetdavidwan/murgat/blob/HEAD/src/program_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"f8d44f2e394301ff","code_sha256_prefix":"f8d44f2e394301ff","mcp_get_code":{"code_sha256":"f8d44f2e394301ff"}},{"arxiv_id":"2601.08955","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-08955","title":"Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"loyiv/ITP","path":"itp/orchestrator.py","file_url":"https://github.com/loyiv/ITP/blob/HEAD/itp/orchestrator.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":"21523634b7dd82f6","code_sha256_prefix":"21523634b7dd82f6","mcp_get_code":{"code_sha256":"21523634b7dd82f6"}},{"arxiv_id":"2601.05654","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-05654","title":"Learning to Retrieve User History and Generate User Profiles for Personalized Persuasiveness Prediction","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"holi-lab/ReCAP","path":"recap/profiler/profiler.py","file_url":"https://github.com/holi-lab/ReCAP/blob/HEAD/recap/profiler/profiler.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, holi-lab/ReCAP (NOASSERTION)","code_sha256":"40709e284e08c1e1","code_sha256_prefix":"40709e284e08c1e1","mcp_get_code":{"code_sha256":"40709e284e08c1e1"}},{"arxiv_id":"2510.20342","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2510-20342","title":"Teaching Language Models to Reason with Tools","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"ChengpengLi1003/CoRT","path":"infer/utils.py","file_url":"https://github.com/ChengpengLi1003/CoRT/blob/HEAD/infer/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ChengpengLi1003/CoRT when it was checked","code_sha256":"3bb02b5083de68fd","code_sha256_prefix":"3bb02b5083de68fd","mcp_get_code":{"code_sha256":"3bb02b5083de68fd"}},{"arxiv_id":"2503.05188","arxiv_id_is_arxiv":true,"paper":null,"title":"arXiv:2503.05188","date":null,"month_inferred_from_arxiv_id":"2025-03","title_source":null,"repo":"BugMakerzzz/CRISP","path":"crisp_reason.py","file_url":"https://github.com/BugMakerzzz/CRISP/blob/HEAD/crisp_reason.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, BugMakerzzz/CRISP when it was checked","code_sha256":"caa4cec487be6f06","code_sha256_prefix":"caa4cec487be6f06","mcp_get_code":{"code_sha256":"caa4cec487be6f06"}},{"arxiv_id":"2412.15529","arxiv_id_is_arxiv":true,"paper":"/paper/xrag-examining-the-core-benchmarking","title":"XRAG: eXamining the Core -- Benchmarking Foundational Components in Advanced Retrieval-Augmented Generation","date":"2024-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"docailab/xrag","path":"src/xrag/adaptive_rag/utils.py","file_url":"https://github.com/docailab/xrag/blob/HEAD/src/xrag/adaptive_rag/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":"71f8c85c5d4c825c","code_sha256_prefix":"71f8c85c5d4c825c","mcp_get_code":{"code_sha256":"71f8c85c5d4c825c"}},{"arxiv_id":"2411.09502","arxiv_id_is_arxiv":true,"paper":"/paper/golden-noise-for-diffusion-models-a-learning","title":"Golden Noise for Diffusion Models: A Learning Framework","date":"2024-11-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xie-lab-ml/golden-noise-for-diffusion-models","path":"training/dataset_collection.py","file_url":"https://github.com/xie-lab-ml/golden-noise-for-diffusion-models/blob/HEAD/training/dataset_collection.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":"94040482358d6999","code_sha256_prefix":"94040482358d6999","mcp_get_code":{"code_sha256":"94040482358d6999"}},{"arxiv_id":"2407.18064","arxiv_id_is_arxiv":true,"paper":"/paper/compeer-a-generative-conversational-agent-for","title":"ComPeer: A Generative Conversational Agent for Proactive Peer Support","date":null,"month_inferred_from_arxiv_id":"2024-07","title_source":"archive","repo":"liutj9/compeer","path":"src/tools.py","file_url":"https://github.com/liutj9/compeer/blob/HEAD/src/tools.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, liutj9/compeer when it was checked","code_sha256":"f3f8f7c9479f15e7","code_sha256_prefix":"f3f8f7c9479f15e7","mcp_get_code":{"code_sha256":"f3f8f7c9479f15e7"}},{"arxiv_id":"2402.16048","arxiv_id_is_arxiv":true,"paper":"/paper/llms-with-chain-of-thought-are-non-causal","title":"How Likely Do LLMs with CoT Mimic Human Reasoning?","date":"2024-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stevenzhb/cot_causal_analysis","path":"scripts/api_run.py","file_url":"https://github.com/stevenzhb/cot_causal_analysis/blob/HEAD/scripts/api_run.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, stevenzhb/cot_causal_analysis when it was checked","code_sha256":"7c56d76aa689e7f0","code_sha256_prefix":"7c56d76aa689e7f0","mcp_get_code":{"code_sha256":"7c56d76aa689e7f0"}},{"arxiv_id":"2402.11900","arxiv_id_is_arxiv":true,"paper":"/paper/investigating-multi-hop-factual-shortcuts-in","title":"Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Jometeorie/MultiHopShortcuts","path":"code/data_utils.py","file_url":"https://github.com/Jometeorie/MultiHopShortcuts/blob/HEAD/code/data_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GPL-3.0, as GitHub detects it on this paper's repository, Jometeorie/MultiHopShortcuts, is not in the permissive set Syntology serves inline","code_sha256":"f1273794d66182e4","code_sha256_prefix":"f1273794d66182e4","mcp_get_code":{"code_sha256":"f1273794d66182e4"}},{"arxiv_id":"2312.17115","arxiv_id_is_arxiv":true,"paper":"/paper/how-far-are-we-from-believable-ai-agents-a","title":"How Far Are LLMs from Believable AI? A Benchmark for Evaluating the Believability of Human Behavior Simulation","date":"2023-12-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"llmconference/emnlp_conference_2024","path":"benchmark/benchmark_file_util.py","file_url":"https://github.com/llmconference/emnlp_conference_2024/blob/HEAD/benchmark/benchmark_file_util.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, llmconference/emnlp_conference_2024 when it was checked","code_sha256":"099db8c2586d17b9","code_sha256_prefix":"099db8c2586d17b9","mcp_get_code":{"code_sha256":"099db8c2586d17b9"}},{"arxiv_id":"2309.17452","arxiv_id_is_arxiv":true,"paper":"/paper/tora-a-tool-integrated-reasoning-agent-for","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","date":"2023-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/tora","path":"src/utils/utils.py","file_url":"https://github.com/microsoft/tora/blob/HEAD/src/utils/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ChengpengLi1003/CoRT, and GitHub detected no licence in that repository when it was checked","code_sha256":"3bb02b5083de68fd","code_sha256_prefix":"3bb02b5083de68fd","mcp_get_code":{"code_sha256":"3bb02b5083de68fd"}},{"arxiv_id":"2305.20076","arxiv_id_is_arxiv":true,"paper":"/paper/decision-oriented-dialogue-for-human-ai","title":"Decision-Oriented Dialogue for Human-AI Collaboration","date":"2023-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jlin816/dialop","path":"dialop/play_gpt3.py","file_url":"https://github.com/jlin816/dialop/blob/HEAD/dialop/play_gpt3.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, jlin816/dialop (NOASSERTION)","code_sha256":"7e94d97091b55364","code_sha256_prefix":"7e94d97091b55364","mcp_get_code":{"code_sha256":"7e94d97091b55364"}},{"arxiv_id":"2305.11738","arxiv_id_is_arxiv":true,"paper":"/paper/critic-large-language-models-can-self-correct","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","date":"2023-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/ProphetNet","path":"CRITIC/src/program/critic.py","file_url":"https://github.com/microsoft/ProphetNet/blob/HEAD/CRITIC/src/program/critic.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":"d9d6df1c6dfcbd38","code_sha256_prefix":"d9d6df1c6dfcbd38","mcp_get_code":{"code_sha256":"d9d6df1c6dfcbd38"}},{"arxiv_id":"2210.03629","arxiv_id_is_arxiv":true,"paper":"/paper/react-synergizing-reasoning-and-acting-in","title":"ReAct: Synergizing Reasoning and Acting in Language Models","date":"2022-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liyuan24/nanodeepresearch","path":"agent/react_agent.py","file_url":"https://github.com/liyuan24/nanodeepresearch/blob/HEAD/agent/react_agent.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, liyuan24/nanodeepresearch when it was checked","code_sha256":"cb56e34b15e5e739","code_sha256_prefix":"cb56e34b15e5e739","mcp_get_code":{"code_sha256":"cb56e34b15e5e739"}},{"arxiv_id":"2208.11057","arxiv_id_is_arxiv":true,"paper":"/paper/prompting-as-probing-using-language-models","title":"Prompting as Probing: Using Language Models for Knowledge Base Construction","date":"2022-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hemile/iswc-challenge","path":"gpt3_baseline.py","file_url":"https://github.com/hemile/iswc-challenge/blob/HEAD/gpt3_baseline.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":"bc5c5e8713300ce5","code_sha256_prefix":"bc5c5e8713300ce5","mcp_get_code":{"code_sha256":"bc5c5e8713300ce5"}}],"record_sha256":"eafc548515a98bf20ab838ab1d061c9870609fa238470b9845ed1a8fb88564cc","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}