{"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/load-records","entry":"load_records","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":10,"n_papers_ran":5,"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":10,"n_samples_ran":5,"n_samples_fingerprinted":0,"n_places":10,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":4,"unverified":5},"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":"2609.04166","paper":"/paper/arxiv-2609-04166","title":"From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Deception Research","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"yshk-mxim/deceptive-mechanism","path":"replication_package/experiment1/analysis/src/deceit_analysis/tier1.py","file_url":"https://github.com/yshk-mxim/deceptive-mechanism/blob/HEAD/replication_package/experiment1/analysis/src/deceit_analysis/tier1.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cee362d3a9ff71a6","mcp_get_code":{"code_sha256":"cee362d3a9ff71a6"}},{"arxiv_id":"2609.03109","paper":"/paper/arxiv-2609-03109","title":"SLIDEFORGE: An LLM Agent for Controllable Editing of Slides as Structured Artifacts","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"UIUC-MONET/SLIDEFORGE","path":"decomposition/usage_report.py","file_url":"https://github.com/UIUC-MONET/SLIDEFORGE/blob/HEAD/decomposition/usage_report.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"06e5847ca19a164f","mcp_get_code":{"code_sha256":"06e5847ca19a164f"}},{"arxiv_id":"2608.10042","paper":"/paper/arxiv-2608-10042","title":"UserToolBench: A User-Profile-Hidden Benchmark for Personalized Decision Making in Tool-Use LLMs","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"xxy212/UserToolBench","path":"utb/generation/visualize_model_calls.py","file_url":"https://github.com/xxy212/UserToolBench/blob/HEAD/utb/generation/visualize_model_calls.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0d3e73d11282bfc3","mcp_get_code":{"code_sha256":"0d3e73d11282bfc3"}},{"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/postprocess_generation.py","file_url":"https://github.com/krystalgong/Persuasion_Index_Code/blob/HEAD/lexicons/LLM_expansion/postprocess_generation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"671ab98d80ff3d16","mcp_get_code":{"code_sha256":"671ab98d80ff3d16"}},{"arxiv_id":"2606.00160","paper":"/paper/arxiv-2606-00160","title":"DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"ZJunBo/DataShield","path":"datashield/compute_projections.py","file_url":"https://github.com/ZJunBo/DataShield/blob/HEAD/datashield/compute_projections.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"27b6012e992f0750","mcp_get_code":{"code_sha256":"27b6012e992f0750"}},{"arxiv_id":"2605.25816","paper":"/paper/arxiv-2605-25816","title":"Fine-Tuning Over Architectural Complexity: Broad-Coverage PII Detection on PIIBench with DeBERTa","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"pritesh-2711/pii-bench","path":"run_existing_models_benchmark.py","file_url":"https://github.com/pritesh-2711/pii-bench/blob/HEAD/run_existing_models_benchmark.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"77586c3078962791","mcp_get_code":{"code_sha256":"77586c3078962791"}},{"arxiv_id":"2605.07510","paper":"/paper/arxiv-2605-07510","title":"InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"hbhalpha/InterLV-Search-Bench","path":"agentic_search/gpt_judge.py","file_url":"https://github.com/hbhalpha/InterLV-Search-Bench/blob/HEAD/agentic_search/gpt_judge.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ae76f55ef9721fbd","mcp_get_code":{"code_sha256":"ae76f55ef9721fbd"}},{"arxiv_id":"2604.04323","paper":"/paper/arxiv-2604-04323","title":"How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"UCSB-NLP-Chang/Skill-Usage","path":"search_server/index_builder.py","file_url":"https://github.com/UCSB-NLP-Chang/Skill-Usage/blob/HEAD/search_server/index_builder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8815dd447edad001","mcp_get_code":{"code_sha256":"8815dd447edad001"}},{"arxiv_id":"2602.08826","paper":"/paper/arxiv-2602-08826","title":"Affective Flow Language Model for Emotional Support Conversation","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"chz2025/AffectiveFlow","path":"analyze/count_trees.py","file_url":"https://github.com/chz2025/AffectiveFlow/blob/HEAD/analyze/count_trees.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fa4a5a7ac3c6e2a8","mcp_get_code":{"code_sha256":"fa4a5a7ac3c6e2a8"}},{"arxiv_id":"2601.14046","paper":"/paper/arxiv-2601-14046","title":"PRiSM: Benchmarking Phone Realization in Speech Models","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"changelinglab/prism","path":"src/metrics/naive_baseline.py","file_url":"https://github.com/changelinglab/prism/blob/HEAD/src/metrics/naive_baseline.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a716978cfdd5450d","mcp_get_code":{"code_sha256":"a716978cfdd5450d"}}]}