{"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/get-examples","entry":"get_examples","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":15,"n_papers_ran":9,"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":15,"n_samples_ran":9,"n_samples_fingerprinted":2,"n_places":15,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":6,"unverified":6},"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":"2505.18384","paper":"/paper/dynamic-risk-assessments-for-offensive","title":"Dynamic Risk Assessments for Offensive Cybersecurity Agents","date":"2025-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"boyiwei/dynamic-risk-assessment","path":"run_evaluation.py","file_url":"https://github.com/boyiwei/dynamic-risk-assessment/blob/HEAD/run_evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"07105a13d005394c","mcp_get_code":{"code_sha256":"07105a13d005394c"}},{"arxiv_id":"2412.19513","paper":"/paper/confidence-v-s-critique-a-decomposition-of","title":"Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs","date":"2024-12-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Zhe-Young/SelfCorrectDecompose","path":"eval_logits.py","file_url":"https://github.com/Zhe-Young/SelfCorrectDecompose/blob/HEAD/eval_logits.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":"fbe652c7fa7abfbc","mcp_get_code":{"code_sha256":"fbe652c7fa7abfbc"}},{"arxiv_id":"2412.14093","paper":"/paper/alignment-faking-in-large-language-models","title":"Alignment faking in large language models","date":"2024-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"redwoodresearch/alignment_faking_public","path":"model_organism/analyse_paraphrases.py","file_url":"https://github.com/redwoodresearch/alignment_faking_public/blob/HEAD/model_organism/analyse_paraphrases.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"11be8a6d8c172ea7","mcp_get_code":{"code_sha256":"11be8a6d8c172ea7"}},{"arxiv_id":"2409.07429","paper":"/paper/agent-workflow-memory","title":"Agent Workflow Memory","date":"2024-09-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zorazrw/agent-workflow-memory","path":"mind2web/workflow/retrieve.py","file_url":"https://github.com/zorazrw/agent-workflow-memory/blob/HEAD/mind2web/workflow/retrieve.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":"a1075bc76f348b17","mcp_get_code":{"code_sha256":"a1075bc76f348b17"}},{"arxiv_id":"2402.02834","paper":"/paper/shortened-llama-a-simple-depth-pruning-for","title":"Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nota-netspresso/shortened-llm","path":"src/dataset.py","file_url":"https://github.com/nota-netspresso/shortened-llm/blob/HEAD/src/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dda7f6122e4d1904","mcp_get_code":{"code_sha256":"dda7f6122e4d1904"}},{"arxiv_id":"2401.06766","paper":"/paper/mind-your-format-towards-consistent","title":"Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements","date":"2024-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yandex-research/mind-your-format","path":"examples.py","file_url":"https://github.com/yandex-research/mind-your-format/blob/HEAD/examples.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":"39c1250cde8fa4e6","mcp_get_code":{"code_sha256":"39c1250cde8fa4e6"}},{"arxiv_id":"2312.12832","paper":"/paper/turning-dust-into-gold-distilling-complex","title":"Turning Dust into Gold: Distilling Complex Reasoning Capabilities from LLMs by Leveraging Negative Data","date":"2023-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yiwei98/TDG","path":"code/dataset.py","file_url":"https://github.com/Yiwei98/TDG/blob/HEAD/code/dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b45ecd8e25d563f0","mcp_get_code":{"code_sha256":"b45ecd8e25d563f0"}},{"arxiv_id":"2310.17140","paper":"/paper/symbolic-planning-and-code-generation-for","title":"Symbolic Planning and Code Generation for Grounded Dialogue","date":"2023-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"justinchiu/onecommon-gpt","path":"oc/ocdata.py","file_url":"https://github.com/justinchiu/onecommon-gpt/blob/HEAD/oc/ocdata.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8cabae34903b7511","mcp_get_code":{"code_sha256":"8cabae34903b7511"}},{"arxiv_id":"2310.07177","paper":"/paper/online-speculative-decoding","title":"Online Speculative Decoding","date":"2023-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liuxiaoxuanpku/osd","path":"distill/data.py","file_url":"https://github.com/liuxiaoxuanpku/osd/blob/HEAD/distill/data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cfda031d44778d32","mcp_get_code":{"code_sha256":"cfda031d44778d32"}},{"arxiv_id":"2308.15419","paper":"/paper/characterizing-learning-curves-during","title":"Characterizing Learning Curves During Language Model Pre-Training: Learning, Forgetting, and Stability","date":"2023-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tylerachang/lm-learning-curves","path":"utils/data_utils.py","file_url":"https://github.com/tylerachang/lm-learning-curves/blob/HEAD/utils/data_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"71ab3c3ebeb19aed","mcp_get_code":{"code_sha256":"71ab3c3ebeb19aed"}},{"arxiv_id":"2303.09092","paper":"/paper/investigating-failures-to-generalize-for","title":"Challenges to Evaluating the Generalization of Coreference Resolution Models: A Measurement Modeling Perspective","date":"2023-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ianporada/coref-data","path":"dataset_creation/manual/ezcoref_raw/push_to_hub.py","file_url":"https://github.com/ianporada/coref-data/blob/HEAD/dataset_creation/manual/ezcoref_raw/push_to_hub.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":"1eb237786c327189","mcp_get_code":{"code_sha256":"1eb237786c327189"}},{"arxiv_id":"2302.06868","paper":"/paper/switchprompt-learning-domain-specific-gated","title":"SwitchPrompt: Learning Domain-Specific Gated Soft Prompts for Classification in Low-Resource Domains","date":"2023-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"boschresearch/switchprompt","path":"databuilding_script.py","file_url":"https://github.com/boschresearch/switchprompt/blob/HEAD/databuilding_script.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"0926ffb7817e4ac6","mcp_get_code":{"code_sha256":"0926ffb7817e4ac6"}},{"arxiv_id":"2110.13880","paper":"/paper/understanding-interlocking-dynamics-of","title":"Understanding Interlocking Dynamics of Cooperative Rationalization","date":"2021-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gorov/understanding_interlocking","path":"beer_data_utils_neurips21.py","file_url":"https://github.com/gorov/understanding_interlocking/blob/HEAD/beer_data_utils_neurips21.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e3d9a7174e604bf2","mcp_get_code":{"code_sha256":"e3d9a7174e604bf2"}},{"arxiv_id":"2110.04400","paper":"/paper/hydrasum-disentangling-stylistic-features-in-1","title":"HydraSum: Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models","date":"2021-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/hydra-sum","path":"modelling/train_seq2seq_utils.py","file_url":"https://github.com/salesforce/hydra-sum/blob/HEAD/modelling/train_seq2seq_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"1b2cef5d2e4a09bb","mcp_get_code":{"code_sha256":"1b2cef5d2e4a09bb"}},{"arxiv_id":"2003.09772","paper":"/paper/invariant-rationalization","title":"Invariant Rationalization","date":"2020-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"code-terminator/invariant_rationalization","path":"imdb.py","file_url":"https://github.com/code-terminator/invariant_rationalization/blob/HEAD/imdb.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c7fb71ec3b394233","mcp_get_code":{"code_sha256":"c7fb71ec3b394233"}}]}