{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:R7BTFYCSV67M5TMMCSBU34QRZB","short_pith_number":"pith:R7BTFYCS","schema_version":"1.0","canonical_sha256":"8fc332e052afbececd8c14834df211c85f1af835cde5eba1df9d7984f9b56433","source":{"kind":"arxiv","id":"2505.13534","version":2},"attestation_state":"computed","paper":{"title":"InterFeat: A Pipeline for Finding Interesting Scientific Features","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"q-bio.QM","authors_text":"Dafna Shahaf, Dan Ofer, Michal Linial","submitted_at":"2025-05-18T13:13:51Z","abstract_excerpt":"Finding interesting phenomena is the core of scientific discovery, but it is a manual, ill-defined concept. We present an integrative pipeline for automating the discovery of interesting simple hypotheses (feature-target relations with effect direction and a potential underlying mechanism) in structured biomedical data. The pipeline combines machine learning, knowledge graphs, literature search and Large Language Models. We formalize \"interestingness\" as a combination of novelty, utility and plausibility. On 8 major diseases from the UK Biobank, our pipeline consistently recovers risk factors "},"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":"2505.13534","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-05-18T13:13:51Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"title_canon_sha256":"9d942302ad629cbcf8f33e6976fa46b23fa81037ddee929c3d4abbeb432a9ed5","abstract_canon_sha256":"fe87ba622cbe82a72b314893e673ad04dbcc42beced4ecadc59e316fe966c840"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:12.609086Z","signature_b64":"bPevyudiZy4ZFbUC/u0m9Dg96mXt6BJ+mY4+xIKmMFC3ovo5g5ZXVSXZ/rgCRS5IHZ3Lr1NW52FqAG1nJ1MkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fc332e052afbececd8c14834df211c85f1af835cde5eba1df9d7984f9b56433","last_reissued_at":"2026-07-05T12:06:12.608595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:12.608595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InterFeat: A Pipeline for Finding Interesting Scientific Features","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"q-bio.QM","authors_text":"Dafna Shahaf, Dan Ofer, Michal Linial","submitted_at":"2025-05-18T13:13:51Z","abstract_excerpt":"Finding interesting phenomena is the core of scientific discovery, but it is a manual, ill-defined concept. We present an integrative pipeline for automating the discovery of interesting simple hypotheses (feature-target relations with effect direction and a potential underlying mechanism) in structured biomedical data. The pipeline combines machine learning, knowledge graphs, literature search and Large Language Models. We formalize \"interestingness\" as a combination of novelty, utility and plausibility. On 8 major diseases from the UK Biobank, our pipeline consistently recovers risk factors "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13534","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/2505.13534/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":"2505.13534","created_at":"2026-07-05T12:06:12.608649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13534v2","created_at":"2026-07-05T12:06:12.608649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13534","created_at":"2026-07-05T12:06:12.608649+00:00"},{"alias_kind":"pith_short_12","alias_value":"R7BTFYCSV67M","created_at":"2026-07-05T12:06:12.608649+00:00"},{"alias_kind":"pith_short_16","alias_value":"R7BTFYCSV67M5TMM","created_at":"2026-07-05T12:06:12.608649+00:00"},{"alias_kind":"pith_short_8","alias_value":"R7BTFYCS","created_at":"2026-07-05T12:06:12.608649+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.12944","citing_title":"Unsupervised risk factor identification across cancer types and data modalities via explainable artificial intelligence","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R7BTFYCSV67M5TMMCSBU34QRZB","json":"https://pith.science/pith/R7BTFYCSV67M5TMMCSBU34QRZB.json","graph_json":"https://pith.science/api/pith-number/R7BTFYCSV67M5TMMCSBU34QRZB/graph.json","events_json":"https://pith.science/api/pith-number/R7BTFYCSV67M5TMMCSBU34QRZB/events.json","paper":"https://pith.science/paper/R7BTFYCS"},"agent_actions":{"view_html":"https://pith.science/pith/R7BTFYCSV67M5TMMCSBU34QRZB","download_json":"https://pith.science/pith/R7BTFYCSV67M5TMMCSBU34QRZB.json","view_paper":"https://pith.science/paper/R7BTFYCS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13534&json=true","fetch_graph":"https://pith.science/api/pith-number/R7BTFYCSV67M5TMMCSBU34QRZB/graph.json","fetch_events":"https://pith.science/api/pith-number/R7BTFYCSV67M5TMMCSBU34QRZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R7BTFYCSV67M5TMMCSBU34QRZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R7BTFYCSV67M5TMMCSBU34QRZB/action/storage_attestation","attest_author":"https://pith.science/pith/R7BTFYCSV67M5TMMCSBU34QRZB/action/author_attestation","sign_citation":"https://pith.science/pith/R7BTFYCSV67M5TMMCSBU34QRZB/action/citation_signature","submit_replication":"https://pith.science/pith/R7BTFYCSV67M5TMMCSBU34QRZB/action/replication_record"}},"created_at":"2026-07-05T12:06:12.608649+00:00","updated_at":"2026-07-05T12:06:12.608649+00:00"}