{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2UDX2LKAEVUTBJDC2BJVLAMX22","short_pith_number":"pith:2UDX2LKA","schema_version":"1.0","canonical_sha256":"d5077d2d40256930a462d053558197d6b62277336f7c7e5af586626c9342a9cf","source":{"kind":"arxiv","id":"2507.10726","version":1},"attestation_state":"computed","paper":{"title":"Extracting Document Relations from Search Corpus by Marginalizing over User Queries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Kaoru Tsunoda, Ken Kaneiwa, Yuki Iwamoto","submitted_at":"2025-07-14T18:47:13Z","abstract_excerpt":"Understanding relationships between documents in large-scale corpora is essential for knowledge discovery and information organization. However, existing approaches rely heavily on manual annotation or predefined relationship taxonomies. We propose EDR-MQ (Extracting Document Relations by Marginalizing over User Queries), a novel framework that discovers document relationships through query marginalization. EDR-MQ is based on the insight that strongly related documents often co-occur in results across diverse user queries, enabling us to estimate joint probabilities between document pairs by m"},"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":"2507.10726","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-14T18:47:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"860f360d724d0be2b92de09301ea73694636c4988c8c969318b36ed5a5ed6be8","abstract_canon_sha256":"e817e3ef34df3d0e25dd3560947f4f0892b6d7f828a674a31edb826a2ca03753"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:59.014880Z","signature_b64":"jn7EuT5CLtYGnYiP3Ui+kFcMsq6bPzQyu4FaZ0SSjBCu6Qtft7o/QLq40qfiJ3obxaxodzFIeUZcAIde5uGmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5077d2d40256930a462d053558197d6b62277336f7c7e5af586626c9342a9cf","last_reissued_at":"2026-07-05T11:36:59.014496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:59.014496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extracting Document Relations from Search Corpus by Marginalizing over User Queries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Kaoru Tsunoda, Ken Kaneiwa, Yuki Iwamoto","submitted_at":"2025-07-14T18:47:13Z","abstract_excerpt":"Understanding relationships between documents in large-scale corpora is essential for knowledge discovery and information organization. However, existing approaches rely heavily on manual annotation or predefined relationship taxonomies. We propose EDR-MQ (Extracting Document Relations by Marginalizing over User Queries), a novel framework that discovers document relationships through query marginalization. EDR-MQ is based on the insight that strongly related documents often co-occur in results across diverse user queries, enabling us to estimate joint probabilities between document pairs by m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10726","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/2507.10726/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":"2507.10726","created_at":"2026-07-05T11:36:59.014551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.10726v1","created_at":"2026-07-05T11:36:59.014551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10726","created_at":"2026-07-05T11:36:59.014551+00:00"},{"alias_kind":"pith_short_12","alias_value":"2UDX2LKAEVUT","created_at":"2026-07-05T11:36:59.014551+00:00"},{"alias_kind":"pith_short_16","alias_value":"2UDX2LKAEVUTBJDC","created_at":"2026-07-05T11:36:59.014551+00:00"},{"alias_kind":"pith_short_8","alias_value":"2UDX2LKA","created_at":"2026-07-05T11:36:59.014551+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/2UDX2LKAEVUTBJDC2BJVLAMX22","json":"https://pith.science/pith/2UDX2LKAEVUTBJDC2BJVLAMX22.json","graph_json":"https://pith.science/api/pith-number/2UDX2LKAEVUTBJDC2BJVLAMX22/graph.json","events_json":"https://pith.science/api/pith-number/2UDX2LKAEVUTBJDC2BJVLAMX22/events.json","paper":"https://pith.science/paper/2UDX2LKA"},"agent_actions":{"view_html":"https://pith.science/pith/2UDX2LKAEVUTBJDC2BJVLAMX22","download_json":"https://pith.science/pith/2UDX2LKAEVUTBJDC2BJVLAMX22.json","view_paper":"https://pith.science/paper/2UDX2LKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.10726&json=true","fetch_graph":"https://pith.science/api/pith-number/2UDX2LKAEVUTBJDC2BJVLAMX22/graph.json","fetch_events":"https://pith.science/api/pith-number/2UDX2LKAEVUTBJDC2BJVLAMX22/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2UDX2LKAEVUTBJDC2BJVLAMX22/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2UDX2LKAEVUTBJDC2BJVLAMX22/action/storage_attestation","attest_author":"https://pith.science/pith/2UDX2LKAEVUTBJDC2BJVLAMX22/action/author_attestation","sign_citation":"https://pith.science/pith/2UDX2LKAEVUTBJDC2BJVLAMX22/action/citation_signature","submit_replication":"https://pith.science/pith/2UDX2LKAEVUTBJDC2BJVLAMX22/action/replication_record"}},"created_at":"2026-07-05T11:36:59.014551+00:00","updated_at":"2026-07-05T11:36:59.014551+00:00"}