{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3HGWSRP7VGCTANG5U5OWFB6FIK","short_pith_number":"pith:3HGWSRP7","schema_version":"1.0","canonical_sha256":"d9cd6945ffa9853034dda75d6287c5428dac7c475ab065aede8bda032b28a4fe","source":{"kind":"arxiv","id":"2607.26346","version":1},"attestation_state":"computed","paper":{"title":"Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI","stat.ME","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Jifan Zhang, Miklos Racz, Suqi Liu","submitted_at":"2026-07-28T23:40:49Z","abstract_excerpt":"Knowledge graph learning provides a powerful framework for representing and inferring structured knowledge, with broad practical applications. However, the scarcity of relation-specific labeled triples per entity hinders the training of expressive models, and the ad hoc design of scoring functions limits generalizability and lacks theoretical grounding. We address both issues with a theoretically grounded, end-to-end training framework that extends and subsumes existing methods. Our framework is a two-stage procedure: unsupervised pretraining over heterogeneous corpora followed by supervised l"},"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":"2607.26346","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2026-07-28T23:40:49Z","cross_cats_sorted":["cs.SI","stat.ME","stat.ML","stat.TH"],"title_canon_sha256":"e9be5f039e3baa9d1f0be807fa39f524201e8be1302053975911b52245c38c43","abstract_canon_sha256":"898df72a405cafb37f0d8f18aa8b26949f7ecc6c659081fca04d54db8ecabadb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9cd6945ffa9853034dda75d6287c5428dac7c475ab065aede8bda032b28a4fe","last_reissued_at":"2026-07-30T01:18:07.614806Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:18:07.614806Z"},"graph_snapshot":{"paper":{"title":"Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI","stat.ME","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Jifan Zhang, Miklos Racz, Suqi Liu","submitted_at":"2026-07-28T23:40:49Z","abstract_excerpt":"Knowledge graph learning provides a powerful framework for representing and inferring structured knowledge, with broad practical applications. However, the scarcity of relation-specific labeled triples per entity hinders the training of expressive models, and the ad hoc design of scoring functions limits generalizability and lacks theoretical grounding. We address both issues with a theoretically grounded, end-to-end training framework that extends and subsumes existing methods. Our framework is a two-stage procedure: unsupervised pretraining over heterogeneous corpora followed by supervised l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26346","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/2607.26346/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":"2607.26346","created_at":"2026-07-30T01:18:07.620319+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.26346v1","created_at":"2026-07-30T01:18:07.620319+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26346","created_at":"2026-07-30T01:18:07.620319+00:00"},{"alias_kind":"pith_short_12","alias_value":"3HGWSRP7VGCT","created_at":"2026-07-30T01:18:07.620319+00:00"},{"alias_kind":"pith_short_16","alias_value":"3HGWSRP7VGCTANG5","created_at":"2026-07-30T01:18:07.620319+00:00"},{"alias_kind":"pith_short_8","alias_value":"3HGWSRP7","created_at":"2026-07-30T01:18:07.620319+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/3HGWSRP7VGCTANG5U5OWFB6FIK","json":"https://pith.science/pith/3HGWSRP7VGCTANG5U5OWFB6FIK.json","graph_json":"https://pith.science/api/pith-number/3HGWSRP7VGCTANG5U5OWFB6FIK/graph.json","events_json":"https://pith.science/api/pith-number/3HGWSRP7VGCTANG5U5OWFB6FIK/events.json","paper":"https://pith.science/paper/3HGWSRP7"},"agent_actions":{"view_html":"https://pith.science/pith/3HGWSRP7VGCTANG5U5OWFB6FIK","download_json":"https://pith.science/pith/3HGWSRP7VGCTANG5U5OWFB6FIK.json","view_paper":"https://pith.science/paper/3HGWSRP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.26346&json=true","fetch_graph":"https://pith.science/api/pith-number/3HGWSRP7VGCTANG5U5OWFB6FIK/graph.json","fetch_events":"https://pith.science/api/pith-number/3HGWSRP7VGCTANG5U5OWFB6FIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3HGWSRP7VGCTANG5U5OWFB6FIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3HGWSRP7VGCTANG5U5OWFB6FIK/action/storage_attestation","attest_author":"https://pith.science/pith/3HGWSRP7VGCTANG5U5OWFB6FIK/action/author_attestation","sign_citation":"https://pith.science/pith/3HGWSRP7VGCTANG5U5OWFB6FIK/action/citation_signature","submit_replication":"https://pith.science/pith/3HGWSRP7VGCTANG5U5OWFB6FIK/action/replication_record"}},"created_at":"2026-07-30T01:18:07.620319+00:00","updated_at":"2026-07-30T01:18:07.620319+00:00"}