{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TUCWOVSSDMMSPICSMI6TVCLOTD","short_pith_number":"pith:TUCWOVSS","schema_version":"1.0","canonical_sha256":"9d056756521b1927a052623d3a896e98d620cdd016da8cd71fb68e2d29262d4c","source":{"kind":"arxiv","id":"2605.17373","version":1},"attestation_state":"computed","paper":{"title":"FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anirudh Goyal, Chang Liu, Dianbo Liu, Hou Hei Lam, Qiran Zou, Samson Yu, Srinivas Anumasa, Tianyi Zhang, Tingting Chen, Wenhao Zhao, Yiming Tang, Yingtao Zhu, Zhengyao Jiang, Zufeng Zhang","submitted_at":"2026-05-17T10:30:38Z","abstract_excerpt":"AI research agents accelerate ML research by automating hypothesis generation, experimentation, and empirical refinement. Existing agent strategies range from greedy hill-climbing to tree search and evolutionary optimization, yet which strategy choices drive performance remains unclear. Answering this question requires a benchmark that separates agent strategy (e.g., search topology) from execution infrastructure (e.g., code editor), so that performance differences are attributable to strategy rather than infrastructure, and that provides process-level metrics beyond final scores to analyze ex"},"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":"2605.17373","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T10:30:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"80c37f64a51eaba714afe02bb215a8f5a1726f1cee408a25154134636183e61f","abstract_canon_sha256":"40ba6f2783394bd6fa4f36e91ad60f75f9c20ce1792688c67ce9e3780c86ba38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:55.293920Z","signature_b64":"5cxoHK2yErjI3OxkpaUR8N++3C3EnMiAmph+hyUF5TjHm+/JUyjI7fxvqT/DmT5o/ZwTvMNTAcEwcYFyoZglDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d056756521b1927a052623d3a896e98d620cdd016da8cd71fb68e2d29262d4c","last_reissued_at":"2026-05-20T00:03:55.293034Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:55.293034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anirudh Goyal, Chang Liu, Dianbo Liu, Hou Hei Lam, Qiran Zou, Samson Yu, Srinivas Anumasa, Tianyi Zhang, Tingting Chen, Wenhao Zhao, Yiming Tang, Yingtao Zhu, Zhengyao Jiang, Zufeng Zhang","submitted_at":"2026-05-17T10:30:38Z","abstract_excerpt":"AI research agents accelerate ML research by automating hypothesis generation, experimentation, and empirical refinement. Existing agent strategies range from greedy hill-climbing to tree search and evolutionary optimization, yet which strategy choices drive performance remains unclear. Answering this question requires a benchmark that separates agent strategy (e.g., search topology) from execution infrastructure (e.g., code editor), so that performance differences are attributable to strategy rather than infrastructure, and that provides process-level metrics beyond final scores to analyze ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17373","kind":"arxiv","version":1},"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/2605.17373/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T21:41:57.776122Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.713019Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"e87fbe9044cc55026dda214436c7ef0093c7bdf73ed632e67868cb191d5fa8bf"},"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":"2605.17373","created_at":"2026-05-20T00:03:55.293168+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17373v1","created_at":"2026-05-20T00:03:55.293168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17373","created_at":"2026-05-20T00:03:55.293168+00:00"},{"alias_kind":"pith_short_12","alias_value":"TUCWOVSSDMMS","created_at":"2026-05-20T00:03:55.293168+00:00"},{"alias_kind":"pith_short_16","alias_value":"TUCWOVSSDMMSPICS","created_at":"2026-05-20T00:03:55.293168+00:00"},{"alias_kind":"pith_short_8","alias_value":"TUCWOVSS","created_at":"2026-05-20T00:03:55.293168+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TUCWOVSSDMMSPICSMI6TVCLOTD","json":"https://pith.science/pith/TUCWOVSSDMMSPICSMI6TVCLOTD.json","graph_json":"https://pith.science/api/pith-number/TUCWOVSSDMMSPICSMI6TVCLOTD/graph.json","events_json":"https://pith.science/api/pith-number/TUCWOVSSDMMSPICSMI6TVCLOTD/events.json","paper":"https://pith.science/paper/TUCWOVSS"},"agent_actions":{"view_html":"https://pith.science/pith/TUCWOVSSDMMSPICSMI6TVCLOTD","download_json":"https://pith.science/pith/TUCWOVSSDMMSPICSMI6TVCLOTD.json","view_paper":"https://pith.science/paper/TUCWOVSS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17373&json=true","fetch_graph":"https://pith.science/api/pith-number/TUCWOVSSDMMSPICSMI6TVCLOTD/graph.json","fetch_events":"https://pith.science/api/pith-number/TUCWOVSSDMMSPICSMI6TVCLOTD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TUCWOVSSDMMSPICSMI6TVCLOTD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TUCWOVSSDMMSPICSMI6TVCLOTD/action/storage_attestation","attest_author":"https://pith.science/pith/TUCWOVSSDMMSPICSMI6TVCLOTD/action/author_attestation","sign_citation":"https://pith.science/pith/TUCWOVSSDMMSPICSMI6TVCLOTD/action/citation_signature","submit_replication":"https://pith.science/pith/TUCWOVSSDMMSPICSMI6TVCLOTD/action/replication_record"}},"created_at":"2026-05-20T00:03:55.293168+00:00","updated_at":"2026-05-20T00:03:55.293168+00:00"}