{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KNP5IE72OPGYACT6RLJD6D7IRV","short_pith_number":"pith:KNP5IE72","schema_version":"1.0","canonical_sha256":"535fd413fa73cd800a7e8ad23f0fe88d66547eb74abce24374c3e034ff14561b","source":{"kind":"arxiv","id":"2504.00255","version":2},"attestation_state":"computed","paper":{"title":"SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA","cs.SE"],"primary_cat":"cs.CL","authors_text":"Hanqi Yan, Lin Gui, Shuyin Ouyang, Yanzheng Xiang, Yulan He","submitted_at":"2025-03-31T22:02:24Z","abstract_excerpt":"This study evaluates large language models (LLMs) in generating code from algorithm descriptions in recent NLP papers. The task requires two key competencies: (1) algorithm comprehension: synthesizing information from papers and academic literature to understand implementation logic, and (2) coding expertise: identifying dependencies and correctly implementing necessary APIs. To facilitate rigorous evaluation, we introduce SciReplicate-Bench, a benchmark of 100 tasks from 36 NLP papers published in 2024, featuring detailed annotations and comprehensive test cases. Building on SciReplicate-Benc"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.00255","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T22:02:24Z","cross_cats_sorted":["cs.AI","cs.MA","cs.SE"],"title_canon_sha256":"f3f32f00907a8d70ec33a30a718c51c97b04903a80e765c0bc70a2d20041d492","abstract_canon_sha256":"97120aef70c0a65a24fced3c7b1227914dd7ead8547700899504c702a07d9578"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:52.660156Z","signature_b64":"SqGQx435oF6xlb9AafRuphJ2TxJdvnHXoYQcRDjSniwTYrL2gfFSR2VugYtKL3UFBj+5D3sk0HitxLALp/UEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"535fd413fa73cd800a7e8ad23f0fe88d66547eb74abce24374c3e034ff14561b","last_reissued_at":"2026-07-05T11:49:52.659676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:52.659676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA","cs.SE"],"primary_cat":"cs.CL","authors_text":"Hanqi Yan, Lin Gui, Shuyin Ouyang, Yanzheng Xiang, Yulan He","submitted_at":"2025-03-31T22:02:24Z","abstract_excerpt":"This study evaluates large language models (LLMs) in generating code from algorithm descriptions in recent NLP papers. The task requires two key competencies: (1) algorithm comprehension: synthesizing information from papers and academic literature to understand implementation logic, and (2) coding expertise: identifying dependencies and correctly implementing necessary APIs. To facilitate rigorous evaluation, we introduce SciReplicate-Bench, a benchmark of 100 tasks from 36 NLP papers published in 2024, featuring detailed annotations and comprehensive test cases. Building on SciReplicate-Benc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00255","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.00255/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.00255","created_at":"2026-07-05T11:49:52.659734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.00255v2","created_at":"2026-07-05T11:49:52.659734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00255","created_at":"2026-07-05T11:49:52.659734+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNP5IE72OPGY","created_at":"2026-07-05T11:49:52.659734+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNP5IE72OPGYACT6","created_at":"2026-07-05T11:49:52.659734+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNP5IE72","created_at":"2026-07-05T11:49:52.659734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02134","citing_title":"Coding-agents can replicate scientific machine learning papers","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28371","citing_title":"From paper to benchmark: agentic, framework-based reproduction of under-specified methods in machine health intelligence","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23204","citing_title":"AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16616","citing_title":"MLReplicate: Benchmarking Autonomous Research Systems for Machine Learning Reproducibility","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18661","citing_title":"AI for Auto-Research: Roadmap & User Guide","ref_index":225,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16902","citing_title":"ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2506.22598","citing_title":"RExBench: Can coding agents autonomously implement AI research extensions?","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11354","citing_title":"ReplicatorBench: Benchmarking LLM Agents for Replicability in Social and Behavioral Sciences","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05550","citing_title":"AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KNP5IE72OPGYACT6RLJD6D7IRV","json":"https://pith.science/pith/KNP5IE72OPGYACT6RLJD6D7IRV.json","graph_json":"https://pith.science/api/pith-number/KNP5IE72OPGYACT6RLJD6D7IRV/graph.json","events_json":"https://pith.science/api/pith-number/KNP5IE72OPGYACT6RLJD6D7IRV/events.json","paper":"https://pith.science/paper/KNP5IE72"},"agent_actions":{"view_html":"https://pith.science/pith/KNP5IE72OPGYACT6RLJD6D7IRV","download_json":"https://pith.science/pith/KNP5IE72OPGYACT6RLJD6D7IRV.json","view_paper":"https://pith.science/paper/KNP5IE72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.00255&json=true","fetch_graph":"https://pith.science/api/pith-number/KNP5IE72OPGYACT6RLJD6D7IRV/graph.json","fetch_events":"https://pith.science/api/pith-number/KNP5IE72OPGYACT6RLJD6D7IRV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNP5IE72OPGYACT6RLJD6D7IRV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNP5IE72OPGYACT6RLJD6D7IRV/action/storage_attestation","attest_author":"https://pith.science/pith/KNP5IE72OPGYACT6RLJD6D7IRV/action/author_attestation","sign_citation":"https://pith.science/pith/KNP5IE72OPGYACT6RLJD6D7IRV/action/citation_signature","submit_replication":"https://pith.science/pith/KNP5IE72OPGYACT6RLJD6D7IRV/action/replication_record"}},"created_at":"2026-07-05T11:49:52.659734+00:00","updated_at":"2026-07-05T11:49:52.659734+00:00"}