{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:CEHR3NIVA6OGC46WO7HOTH6FXJ","short_pith_number":"pith:CEHR3NIV","schema_version":"1.0","canonical_sha256":"110f1db515079c6173d677cee99fc5ba545a8847d3c37cc9394b65f8a94941a7","source":{"kind":"arxiv","id":"1605.06523","version":2},"attestation_state":"computed","paper":{"title":"TensorLog: A Differentiable Deductive Database","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.LG"],"primary_cat":"cs.AI","authors_text":"William W. Cohen","submitted_at":"2016-05-20T20:10:46Z","abstract_excerpt":"Large knowledge bases (KBs) are useful in many tasks, but it is unclear how to integrate this sort of knowledge into \"deep\" gradient-based learning systems. To address this problem, we describe a probabilistic deductive database, called TensorLog, in which reasoning uses a differentiable process. In TensorLog, each clause in a logical theory is first converted into certain type of factor graph. Then, for each type of query to the factor graph, the message-passing steps required to perform belief propagation (BP) are \"unrolled\" into a function, which is differentiable. We show that these functi"},"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":"1605.06523","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-05-20T20:10:46Z","cross_cats_sorted":["cs.DB","cs.LG"],"title_canon_sha256":"c6e70fafd6786d5b4bb2d5c81aa798044a9c1f989863a38efa0c863435452c9c","abstract_canon_sha256":"4ba3d40d2f2455cdff2388ed374fbe5944cf49a2dc39e05c0f3ff2feecbc9839"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:10:45.529840Z","signature_b64":"DXJXmUx2jWRMnqzYkBcZPxxovHyNHI+aiy2t0fcSiO/Uk1Uh+2VrQAxLv5FaDucEDDTaZIGIaGQIBeOaDyyXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"110f1db515079c6173d677cee99fc5ba545a8847d3c37cc9394b65f8a94941a7","last_reissued_at":"2026-05-18T01:10:45.529444Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:10:45.529444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TensorLog: A Differentiable Deductive Database","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.LG"],"primary_cat":"cs.AI","authors_text":"William W. Cohen","submitted_at":"2016-05-20T20:10:46Z","abstract_excerpt":"Large knowledge bases (KBs) are useful in many tasks, but it is unclear how to integrate this sort of knowledge into \"deep\" gradient-based learning systems. To address this problem, we describe a probabilistic deductive database, called TensorLog, in which reasoning uses a differentiable process. In TensorLog, each clause in a logical theory is first converted into certain type of factor graph. Then, for each type of query to the factor graph, the message-passing steps required to perform belief propagation (BP) are \"unrolled\" into a function, which is differentiable. We show that these functi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.06523","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":""},"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":"1605.06523","created_at":"2026-05-18T01:10:45.529501+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.06523v2","created_at":"2026-05-18T01:10:45.529501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.06523","created_at":"2026-05-18T01:10:45.529501+00:00"},{"alias_kind":"pith_short_12","alias_value":"CEHR3NIVA6OG","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_16","alias_value":"CEHR3NIVA6OGC46W","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_8","alias_value":"CEHR3NIV","created_at":"2026-05-18T12:30:09.641336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.20402","citing_title":"SoftReason: A Fully Differentiable Neuro-Soft-Symbolic Deductive Reasoning Architecture over High-Dimensional Perceptual Data","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CEHR3NIVA6OGC46WO7HOTH6FXJ","json":"https://pith.science/pith/CEHR3NIVA6OGC46WO7HOTH6FXJ.json","graph_json":"https://pith.science/api/pith-number/CEHR3NIVA6OGC46WO7HOTH6FXJ/graph.json","events_json":"https://pith.science/api/pith-number/CEHR3NIVA6OGC46WO7HOTH6FXJ/events.json","paper":"https://pith.science/paper/CEHR3NIV"},"agent_actions":{"view_html":"https://pith.science/pith/CEHR3NIVA6OGC46WO7HOTH6FXJ","download_json":"https://pith.science/pith/CEHR3NIVA6OGC46WO7HOTH6FXJ.json","view_paper":"https://pith.science/paper/CEHR3NIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.06523&json=true","fetch_graph":"https://pith.science/api/pith-number/CEHR3NIVA6OGC46WO7HOTH6FXJ/graph.json","fetch_events":"https://pith.science/api/pith-number/CEHR3NIVA6OGC46WO7HOTH6FXJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CEHR3NIVA6OGC46WO7HOTH6FXJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CEHR3NIVA6OGC46WO7HOTH6FXJ/action/storage_attestation","attest_author":"https://pith.science/pith/CEHR3NIVA6OGC46WO7HOTH6FXJ/action/author_attestation","sign_citation":"https://pith.science/pith/CEHR3NIVA6OGC46WO7HOTH6FXJ/action/citation_signature","submit_replication":"https://pith.science/pith/CEHR3NIVA6OGC46WO7HOTH6FXJ/action/replication_record"}},"created_at":"2026-05-18T01:10:45.529501+00:00","updated_at":"2026-05-18T01:10:45.529501+00:00"}