{"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-and-prepare-data","entry":"load_and_prepare_data","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":7,"n_papers_ran":4,"n_papers_ran_no_instrument_failure":3,"n_papers_ran_instrument_only":1,"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":12,"n_samples_ran":7,"n_samples_constructed":0,"n_samples_ran_checked":4,"n_samples_instrument":3,"n_samples_unverified":5,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":2,"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":3,"ran_fixture":0,"ran":4,"unverified":5},"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":"2602.04075","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-04075","title":"Thermodynamic assessment of machine learning models for solid-state synthesis prediction","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"BAMeScience/SynCoTrainMP","path":"syncotrainmp/data_selection.py","file_url":"https://github.com/BAMeScience/SynCoTrainMP/blob/HEAD/syncotrainmp/data_selection.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":"c4dade724c0cfd73","code_sha256_prefix":"c4dade724c0cfd73","mcp_get_code":{"code_sha256":"c4dade724c0cfd73"}},{"arxiv_id":"2601.21112","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-21112","title":"How does information access affect LLM monitors' ability to detect sabotage?","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Aether-AIS/cotrh-blue-team","path":"src/paper_plots.py","file_url":"https://github.com/Aether-AIS/cotrh-blue-team/blob/HEAD/src/paper_plots.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":"035cf90bdebce5b1","code_sha256_prefix":"035cf90bdebce5b1","mcp_get_code":{"code_sha256":"035cf90bdebce5b1"}},{"arxiv_id":"2601.21112","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-21112","title":"How does information access affect LLM monitors' ability to detect sabotage?","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Aether-AIS/cotrh-blue-team","path":"src/paper_plots_by_awareness_app.py","file_url":"https://github.com/Aether-AIS/cotrh-blue-team/blob/HEAD/src/paper_plots_by_awareness_app.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":"bdac748f046af4e3","code_sha256_prefix":"bdac748f046af4e3","mcp_get_code":{"code_sha256":"bdac748f046af4e3"}},{"arxiv_id":"2601.21112","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-21112","title":"How does information access affect LLM monitors' ability to detect sabotage?","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Aether-AIS/cotrh-blue-team","path":"src/paper_plots_by_awareness_main.py","file_url":"https://github.com/Aether-AIS/cotrh-blue-team/blob/HEAD/src/paper_plots_by_awareness_main.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":"39a14ade9ca51cbd","code_sha256_prefix":"39a14ade9ca51cbd","mcp_get_code":{"code_sha256":"39a14ade9ca51cbd"}},{"arxiv_id":"2601.21112","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-21112","title":"How does information access affect LLM monitors' ability to detect sabotage?","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Aether-AIS/cotrh-blue-team","path":"src/cot_red_handed/final_plots_combined.py","file_url":"https://github.com/Aether-AIS/cotrh-blue-team/blob/HEAD/src/cot_red_handed/final_plots_combined.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":"e0e7d608faab6b0a","code_sha256_prefix":"e0e7d608faab6b0a","mcp_get_code":{"code_sha256":"e0e7d608faab6b0a"}},{"arxiv_id":"2601.21112","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-21112","title":"How does information access affect LLM monitors' ability to detect sabotage?","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Aether-AIS/cotrh-blue-team","path":"src/cot_red_handed/final_plots.py","file_url":"https://github.com/Aether-AIS/cotrh-blue-team/blob/HEAD/src/cot_red_handed/final_plots.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":"3f0b4e1d36fc2faf","code_sha256_prefix":"3f0b4e1d36fc2faf","mcp_get_code":{"code_sha256":"3f0b4e1d36fc2faf"}},{"arxiv_id":"2601.21112","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-21112","title":"How does information access affect LLM monitors' ability to detect sabotage?","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Aether-AIS/cotrh-blue-team","path":"src/cot_red_handed/final_plots_hierarchical.py","file_url":"https://github.com/Aether-AIS/cotrh-blue-team/blob/HEAD/src/cot_red_handed/final_plots_hierarchical.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":"8a9246d7895245bf","code_sha256_prefix":"8a9246d7895245bf","mcp_get_code":{"code_sha256":"8a9246d7895245bf"}},{"arxiv_id":"2505.21785","arxiv_id_is_arxiv":true,"paper":"/paper/born-a-transformer-always-a-transformer","title":"Born a Transformer -- Always a Transformer?","date":"2025-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lacoco-lab/always_a_transformer","path":"finetuning/flipflop/finetune_flipflop.py","file_url":"https://github.com/lacoco-lab/always_a_transformer/blob/HEAD/finetuning/flipflop/finetune_flipflop.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":"d2f2fdec627fb1b5","code_sha256_prefix":"d2f2fdec627fb1b5","mcp_get_code":{"code_sha256":"d2f2fdec627fb1b5"}},{"arxiv_id":"2502.07272","arxiv_id_is_arxiv":true,"paper":"/paper/generator-a-long-context-generative-genomic","title":"GENERator: A Long-Context Generative Genomic Foundation Model","date":"2025-02-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"generteam/generator","path":"src/tasks/downstream/variant_effect_prediction.py","file_url":"https://github.com/generteam/generator/blob/HEAD/src/tasks/downstream/variant_effect_prediction.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":"5a3497d4b2c9e9af","code_sha256_prefix":"5a3497d4b2c9e9af","mcp_get_code":{"code_sha256":"5a3497d4b2c9e9af"}},{"arxiv_id":"2409.11353","arxiv_id_is_arxiv":true,"paper":"/paper/thames-an-end-to-end-tool-for-hallucination","title":"THaMES: An End-to-End Tool for Hallucination Mitigation and Evaluation in Large Language Models","date":"2024-09-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"holistic-ai/THaMES","path":"src/finetune.py","file_url":"https://github.com/holistic-ai/THaMES/blob/HEAD/src/finetune.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, holistic-ai/THaMES when it was checked","code_sha256":"c96f67232998b5cf","code_sha256_prefix":"c96f67232998b5cf","mcp_get_code":{"code_sha256":"c96f67232998b5cf"}},{"arxiv_id":"2407.10106","arxiv_id_is_arxiv":true,"paper":"/paper/distillseq-a-framework-for-safety-alignment","title":"DistillSeq: A Framework for Safety Alignment Testing in Large Language Models using Knowledge Distillation","date":null,"month_inferred_from_arxiv_id":"2024-07","title_source":"archive","repo":"DistillSeq/DistillSeq","path":"train_model.py","file_url":"https://github.com/DistillSeq/DistillSeq/blob/HEAD/train_model.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, DistillSeq/DistillSeq when it was checked","code_sha256":"ac470a8a61464260","code_sha256_prefix":"ac470a8a61464260","mcp_get_code":{"code_sha256":"ac470a8a61464260"}},{"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/CoT_bootstrap.py","file_url":"https://github.com/xiongsiheng/tg-llm/blob/HEAD/src/CoT_bootstrap.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":"d9e464347efd6ebe","code_sha256_prefix":"d9e464347efd6ebe","mcp_get_code":{"code_sha256":"d9e464347efd6ebe"}}],"record_sha256":"f8e2d4eef98baa78f37110db6e2f8590fe948d60c1373ecc7ee480678ccb8b62","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}