{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/code/build-messages","entry":"build_messages","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+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.","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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":17,"n_papers_ran":6,"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":18,"n_samples_ran":6,"n_samples_fingerprinted":3,"n_places":18,"n_places_pointer_only":9,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":5,"unverified":12},"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":"2608.31108","paper":"/paper/arxiv-2608-31108","title":"Stress-Testing Efficient Responsible-AI Evaluation: When Compute Savings Change Benchmark Conclusions","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"VectorInstitute/sustainable-rai-evaluation","path":"src/evaluation_has_a_footprint/inference.py","file_url":"https://github.com/VectorInstitute/sustainable-rai-evaluation/blob/HEAD/src/evaluation_has_a_footprint/inference.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f1880abc92187acb","mcp_get_code":{"code_sha256":"f1880abc92187acb"}},{"arxiv_id":"2608.30156","paper":"/paper/arxiv-2608-30156","title":"Reactivating Test-Time Scaling for Plane Geometry Problem Solving","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"Jason8Kang/ReTTS-PGPS","path":"src/retts_pgp/eval/evaluate.py","file_url":"https://github.com/Jason8Kang/ReTTS-PGPS/blob/HEAD/src/retts_pgp/eval/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"a3a6cfa2487b4ab6","mcp_get_code":{"code_sha256":"a3a6cfa2487b4ab6"}},{"arxiv_id":"2608.03063","paper":"/paper/arxiv-2608-03063","title":"SeqLLM: Augmenting LLMs with Behavioral-Sequence Modeling for High-Stakes Decisions at WeChat Pay","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"125jx/SeqLLM","path":"evaluation/eval_merchant_risk/eval_qwen.py","file_url":"https://github.com/125jx/SeqLLM/blob/HEAD/evaluation/eval_merchant_risk/eval_qwen.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a9d547ed25699663","mcp_get_code":{"code_sha256":"a9d547ed25699663"}},{"arxiv_id":"2608.01875","paper":"/paper/arxiv-2608-01875","title":"ReasonCast: Towards Explainable Time Series Forecasting with Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"seunghan96/reasoncast","path":"reasoncast/train/train_reasoning_sft.py","file_url":"https://github.com/seunghan96/reasoncast/blob/HEAD/reasoncast/train/train_reasoning_sft.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"053a3f22e2840fa6","mcp_get_code":{"code_sha256":"053a3f22e2840fa6"}},{"arxiv_id":"2607.17486","paper":"/paper/arxiv-2607-17486","title":"SALT: Salience-Aware Lexical Trie for Long-Context Compression","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"oteomamo/SALT","path":"salt/agents/delegate.py","file_url":"https://github.com/oteomamo/SALT/blob/HEAD/salt/agents/delegate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d1f4954d72388c6d","mcp_get_code":{"code_sha256":"d1f4954d72388c6d"}},{"arxiv_id":"2607.13433","paper":"/paper/arxiv-2607-13433","title":"When Rubrics Change: Cross-Rubric Generalization for Critical Thinking Essay Scoring","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"umass-ml4ed/generalization-in-essay-scoring","path":"infer_traits.py","file_url":"https://github.com/umass-ml4ed/generalization-in-essay-scoring/blob/HEAD/infer_traits.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"CC0-1.0","inline_ok":true,"code_sha256_prefix":"5f467ab96140f274","mcp_get_code":{"code_sha256":"5f467ab96140f274"}},{"arxiv_id":"2606.26790","paper":"/paper/arxiv-2606-26790","title":"OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"jinyangwu/OPID","path":"utils/prompt_builder.py","file_url":"https://github.com/jinyangwu/OPID/blob/HEAD/utils/prompt_builder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d5573e2aaa360199","mcp_get_code":{"code_sha256":"d5573e2aaa360199"}},{"arxiv_id":"2606.14580","paper":"/paper/arxiv-2606-14580","title":"Persuasion Index: A Theory-Guided Framework for Persuasion Analysis","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"krystalgong/Persuasion_Index_Code","path":"lexicons/LLM_expansion/generation_prompts.py","file_url":"https://github.com/krystalgong/Persuasion_Index_Code/blob/HEAD/lexicons/LLM_expansion/generation_prompts.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c18f2c089df0bf5a","mcp_get_code":{"code_sha256":"c18f2c089df0bf5a"}},{"arxiv_id":"2605.22714","paper":"/paper/arxiv-2605-22714","title":"AMEL: Accumulated Message Effects on LLM Judgments","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"chutapp/amel","path":"src/conversation.py","file_url":"https://github.com/chutapp/amel/blob/HEAD/src/conversation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"da3095058bb7db5c","mcp_get_code":{"code_sha256":"da3095058bb7db5c"}},{"arxiv_id":"2605.15726","paper":"/paper/arxiv-2605-15726","title":"Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"tally0818/NudgeRL","path":"src/train/NudgeRLTrainer.py","file_url":"https://github.com/tally0818/NudgeRL/blob/HEAD/src/train/NudgeRLTrainer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7a369205c90fceef","mcp_get_code":{"code_sha256":"7a369205c90fceef"}},{"arxiv_id":"2604.11048","paper":"/paper/arxiv-2604-11048","title":"A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"cjia7/DPR","path":"src/npti/neuron/apply_neuron_steering.py","file_url":"https://github.com/cjia7/DPR/blob/HEAD/src/npti/neuron/apply_neuron_steering.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d3120aa76158afc9","mcp_get_code":{"code_sha256":"d3120aa76158afc9"}},{"arxiv_id":"2603.28387","paper":"/paper/arxiv-2603-28387","title":"Prompts Without Evidence: How Neuroimaging Mentions Shift Clinical Vision-Language Model Predictions","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"long21wt/scaffold-effect","path":"src/preamble_search.py","file_url":"https://github.com/long21wt/scaffold-effect/blob/HEAD/src/preamble_search.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dca19f51d4c241fd","mcp_get_code":{"code_sha256":"dca19f51d4c241fd"}},{"arxiv_id":"2602.02444","paper":"/paper/arxiv-2602-02444","title":"RANKVIDEO: Reasoning Reranking for Text-to-Video Retrieval","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"tskow99/RANKVIDEO-Reasoning-Reranker","path":"rankvideo/train_reranker.py","file_url":"https://github.com/tskow99/RANKVIDEO-Reasoning-Reranker/blob/HEAD/rankvideo/train_reranker.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2e15b025fc5ea900","mcp_get_code":{"code_sha256":"2e15b025fc5ea900"}},{"arxiv_id":"2602.02139","paper":"/paper/arxiv-2602-02139","title":"EvoMU: Evolutionary Machine Unlearning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Batorskq/EvoMU","path":"generate_muse.py","file_url":"https://github.com/Batorskq/EvoMU/blob/HEAD/generate_muse.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a5ca2afdff6f10e1","mcp_get_code":{"code_sha256":"a5ca2afdff6f10e1"}},{"arxiv_id":"2601.22661","paper":"/paper/arxiv-2601-22661","title":"Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"y-ren16/MCLP","path":"generate_roleplay_stepaudio2_multigpu.py","file_url":"https://github.com/y-ren16/MCLP/blob/HEAD/generate_roleplay_stepaudio2_multigpu.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"682d5ae8f0b77646","mcp_get_code":{"code_sha256":"682d5ae8f0b77646"}},{"arxiv_id":"2510.13212","paper":"/paper/arxiv-2510-13212","title":"Towards Understanding Valuable Preference Data for Large Language Model Alignment","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"tmlr-group/TIF_LossDiff-IRM","path":"winrate_eval/single_score_local.py","file_url":"https://github.com/tmlr-group/TIF_LossDiff-IRM/blob/HEAD/winrate_eval/single_score_local.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8e680b35d845de28","mcp_get_code":{"code_sha256":"8e680b35d845de28"}},{"arxiv_id":"2506.01262","paper":"/paper/exploring-the-potential-of-llms-as","title":"Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis","date":"2025-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"12kimih/HiCUPID","path":"src/train_dpo.py","file_url":"https://github.com/12kimih/HiCUPID/blob/HEAD/src/train_dpo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a8cb09c73a473dbb","mcp_get_code":{"code_sha256":"a8cb09c73a473dbb"}},{"arxiv_id":"2506.01262","paper":"/paper/exploring-the-potential-of-llms-as","title":"Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis","date":"2025-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"12kimih/HiCUPID","path":"src/train_sft.py","file_url":"https://github.com/12kimih/HiCUPID/blob/HEAD/src/train_sft.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5f8f8198f02dec22","mcp_get_code":{"code_sha256":"5f8f8198f02dec22"}}]}