{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4DIWYDSK6YAJGNN6DAV4ZMVSIJ","short_pith_number":"pith:4DIWYDSK","schema_version":"1.0","canonical_sha256":"e0d16c0e4af6009335be182bccb2b242653832f1d2b6cc4d4c5548e805230b3b","source":{"kind":"arxiv","id":"2605.16902","version":1},"attestation_state":"computed","paper":{"title":"ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"An artifact graph of models and datasets lets graph methods rank untested performance links to find new SOTA results.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bodhisattwa Prasad Majumder, Haofei Yu, Jiaxuan You, Kyle Richardson, Peter Clark","submitted_at":"2026-05-16T09:26:08Z","abstract_excerpt":"Scientific artifacts such as models and datasets are foundations for research. With the rapid growth of platforms like HuggingFace, researchers now have access to a large number of artifacts. Yet, a key challenge remains: how can we automatically discover the state-of-the-art (SOTA) model for a given dataset by fully leveraging existing artifacts? We formalize this task as automatic SOTA discovery by modeling HuggingFace as an artifact graph, where nodes are models/datasets and edges represent evaluations. We propose ArtifactLinker, a two-stage framework: (1) ranking promising unobserved model"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.16902","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-16T09:26:08Z","cross_cats_sorted":[],"title_canon_sha256":"18e178aebd2eb24b1aaf006e5257aaa7f3012abe9aa34295c4b62962e2838a42","abstract_canon_sha256":"3b2cf161f50e35f44f18d75e90e44eed41644681a655ce111c5ccf1380cb45ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:29.235157Z","signature_b64":"SNRu/CeVFxusnwxS6QvfTcaiXrnKiOa39Tw2pugqDrOTvrGGp4xENgcA9if8bpR7djWJW3QZastVnLgBBwgmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0d16c0e4af6009335be182bccb2b242653832f1d2b6cc4d4c5548e805230b3b","last_reissued_at":"2026-05-20T00:03:29.234232Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:29.234232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"An artifact graph of models and datasets lets graph methods rank untested performance links to find new SOTA results.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bodhisattwa Prasad Majumder, Haofei Yu, Jiaxuan You, Kyle Richardson, Peter Clark","submitted_at":"2026-05-16T09:26:08Z","abstract_excerpt":"Scientific artifacts such as models and datasets are foundations for research. With the rapid growth of platforms like HuggingFace, researchers now have access to a large number of artifacts. Yet, a key challenge remains: how can we automatically discover the state-of-the-art (SOTA) model for a given dataset by fully leveraging existing artifacts? We formalize this task as automatic SOTA discovery by modeling HuggingFace as an artifact graph, where nodes are models/datasets and edges represent evaluations. We propose ArtifactLinker, a two-stage framework: (1) ranking promising unobserved model"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Graph structures between existing artifacts are effective for missing link prediction; end-to-end ranking and verification with ArtifactLinker help discover potential SOTA results and research insights.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Existing published evaluations form a sufficiently connected and informative graph that unobserved model-dataset performance links can be ranked accurately from graph structure alone.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ArtifactLinker frames SOTA discovery as missing-link prediction on an artifact graph of models and datasets, with a two-stage ranking-plus-verification pipeline and a new benchmark of 14k artifacts.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An artifact graph of models and datasets lets graph methods rank untested performance links to find new SOTA results.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5f0405dc064889e85e5f026b7a98883dfdcdd6131d6c6d9f1d83c2d97dee0037"},"source":{"id":"2605.16902","kind":"arxiv","version":1},"verdict":{"id":"13589376-5b49-4df8-ace7-526e676a77bd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T20:25:21.390548Z","strongest_claim":"Graph structures between existing artifacts are effective for missing link prediction; end-to-end ranking and verification with ArtifactLinker help discover potential SOTA results and research insights.","one_line_summary":"ArtifactLinker frames SOTA discovery as missing-link prediction on an artifact graph of models and datasets, with a two-stage ranking-plus-verification pipeline and a new benchmark of 14k artifacts.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Existing published evaluations form a sufficiently connected and informative graph that unobserved model-dataset performance links can be ranked accurately from graph structure alone.","pith_extraction_headline":"An artifact graph of models and datasets lets graph methods rank untested performance links to find new SOTA results."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16902/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"cited_work_retraction","ran_at":"2026-05-19T20:52:23.353004Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T20:31:40.485435Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T20:31:19.107673Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.275794Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.354878Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"77d515ec8e0789caefe000bb2cc5d267b28aef9eda42632b6d60f958dfc53000"},"references":{"count":33,"sample":[{"doi":"","year":null,"title":"On the suitability of hug- ging face hub for empirical studies.ArXiv, abs/2307.14841,","work_id":"2107051f-40e9-47ec-bad4-f1ff041d5889","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Evaluating sakana's AI scientist: Bold claims, mixed results","work_id":"39f280b4-8df6-4383-811e-2241b7141020","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"A large annotated corpus for learning natural language inference","work_id":"612282f5-76dd-459e-817d-c47c0485d1ff","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Analyzing the evolution and maintenance of ml models on hugging face.2024 IEEE/ACM 21st International Conference on Mining Software Repositories (MSR), pp","work_id":"62ebf373-d5b9-45ac-949d-cedf5b0946d8","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Joel Castaño, Rafael Cabañas, Antonio Salmer’on, David Lo, and Silverio Mart’inez- Fern’andez","work_id":"a5ee127c-226e-4e62-b6cf-62edd4528dd9","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":33,"snapshot_sha256":"edca1a8fa8f6647435b47144f8da7c7d0142ca19a0a845056b5597fd88ba404c","internal_anchors":5},"formal_canon":{"evidence_count":2,"snapshot_sha256":"71a84f7aad4957e709a56b79971f8a06c7edb256aeecd160d863a9c18f332cb4"},"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":"2605.16902","created_at":"2026-05-20T00:03:29.234404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16902v1","created_at":"2026-05-20T00:03:29.234404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16902","created_at":"2026-05-20T00:03:29.234404+00:00"},{"alias_kind":"pith_short_12","alias_value":"4DIWYDSK6YAJ","created_at":"2026-05-20T00:03:29.234404+00:00"},{"alias_kind":"pith_short_16","alias_value":"4DIWYDSK6YAJGNN6","created_at":"2026-05-20T00:03:29.234404+00:00"},{"alias_kind":"pith_short_8","alias_value":"4DIWYDSK","created_at":"2026-05-20T00:03:29.234404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4DIWYDSK6YAJGNN6DAV4ZMVSIJ","json":"https://pith.science/pith/4DIWYDSK6YAJGNN6DAV4ZMVSIJ.json","graph_json":"https://pith.science/api/pith-number/4DIWYDSK6YAJGNN6DAV4ZMVSIJ/graph.json","events_json":"https://pith.science/api/pith-number/4DIWYDSK6YAJGNN6DAV4ZMVSIJ/events.json","paper":"https://pith.science/paper/4DIWYDSK"},"agent_actions":{"view_html":"https://pith.science/pith/4DIWYDSK6YAJGNN6DAV4ZMVSIJ","download_json":"https://pith.science/pith/4DIWYDSK6YAJGNN6DAV4ZMVSIJ.json","view_paper":"https://pith.science/paper/4DIWYDSK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16902&json=true","fetch_graph":"https://pith.science/api/pith-number/4DIWYDSK6YAJGNN6DAV4ZMVSIJ/graph.json","fetch_events":"https://pith.science/api/pith-number/4DIWYDSK6YAJGNN6DAV4ZMVSIJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4DIWYDSK6YAJGNN6DAV4ZMVSIJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4DIWYDSK6YAJGNN6DAV4ZMVSIJ/action/storage_attestation","attest_author":"https://pith.science/pith/4DIWYDSK6YAJGNN6DAV4ZMVSIJ/action/author_attestation","sign_citation":"https://pith.science/pith/4DIWYDSK6YAJGNN6DAV4ZMVSIJ/action/citation_signature","submit_replication":"https://pith.science/pith/4DIWYDSK6YAJGNN6DAV4ZMVSIJ/action/replication_record"}},"created_at":"2026-05-20T00:03:29.234404+00:00","updated_at":"2026-05-20T00:03:29.234404+00:00"}