{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NOGDTPALKAUBE3ZOCHHL3D5HS3","short_pith_number":"pith:NOGDTPAL","schema_version":"1.0","canonical_sha256":"6b8c39bc0b5028126f2e11cebd8fa796f5e0fde9c569b9c7a78335d68e89066f","source":{"kind":"arxiv","id":"2109.06587","version":1},"attestation_state":"computed","paper":{"title":"Sum-Product-Attention Networks: Leveraging Self-Attention in Probabilistic Circuits","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Devendra Singh Dhami, Kristian Kersting, Zhongjie Yu","submitted_at":"2021-09-14T11:20:54Z","abstract_excerpt":"Probabilistic circuits (PCs) have become the de-facto standard for learning and inference in probabilistic modeling. We introduce Sum-Product-Attention Networks (SPAN), a new generative model that integrates probabilistic circuits with Transformers. SPAN uses self-attention to select the most relevant parts of a probabilistic circuit, here sum-product networks, to improve the modeling capability of the underlying sum-product network. We show that while modeling, SPAN focuses on a specific set of independent assumptions in every product layer of the sum-product network. Our empirical evaluation"},"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":"2109.06587","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-14T11:20:54Z","cross_cats_sorted":[],"title_canon_sha256":"0b36edeabb666e259f8e3de941abdd693457d31ccb2672a227e5635c5f934cdf","abstract_canon_sha256":"472130b3ee1f73dc51afb070ff329ffc2b1440858e940882ac46a2c03db5769e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:14:28.323606Z","signature_b64":"sTy/lem18VvBnoRCbHbpJ9XodBQ+wNeGbWG0Xb99Q1rFp+lVhCfkXCwAJlTS4tRET9K/DDLbmLzvjAYz0HTuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b8c39bc0b5028126f2e11cebd8fa796f5e0fde9c569b9c7a78335d68e89066f","last_reissued_at":"2026-07-05T03:14:28.323169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:14:28.323169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sum-Product-Attention Networks: Leveraging Self-Attention in Probabilistic Circuits","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Devendra Singh Dhami, Kristian Kersting, Zhongjie Yu","submitted_at":"2021-09-14T11:20:54Z","abstract_excerpt":"Probabilistic circuits (PCs) have become the de-facto standard for learning and inference in probabilistic modeling. We introduce Sum-Product-Attention Networks (SPAN), a new generative model that integrates probabilistic circuits with Transformers. SPAN uses self-attention to select the most relevant parts of a probabilistic circuit, here sum-product networks, to improve the modeling capability of the underlying sum-product network. We show that while modeling, SPAN focuses on a specific set of independent assumptions in every product layer of the sum-product network. Our empirical evaluation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06587","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/2109.06587/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":"2109.06587","created_at":"2026-07-05T03:14:28.323244+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.06587v1","created_at":"2026-07-05T03:14:28.323244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06587","created_at":"2026-07-05T03:14:28.323244+00:00"},{"alias_kind":"pith_short_12","alias_value":"NOGDTPALKAUB","created_at":"2026-07-05T03:14:28.323244+00:00"},{"alias_kind":"pith_short_16","alias_value":"NOGDTPALKAUBE3ZO","created_at":"2026-07-05T03:14:28.323244+00:00"},{"alias_kind":"pith_short_8","alias_value":"NOGDTPAL","created_at":"2026-07-05T03:14:28.323244+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/NOGDTPALKAUBE3ZOCHHL3D5HS3","json":"https://pith.science/pith/NOGDTPALKAUBE3ZOCHHL3D5HS3.json","graph_json":"https://pith.science/api/pith-number/NOGDTPALKAUBE3ZOCHHL3D5HS3/graph.json","events_json":"https://pith.science/api/pith-number/NOGDTPALKAUBE3ZOCHHL3D5HS3/events.json","paper":"https://pith.science/paper/NOGDTPAL"},"agent_actions":{"view_html":"https://pith.science/pith/NOGDTPALKAUBE3ZOCHHL3D5HS3","download_json":"https://pith.science/pith/NOGDTPALKAUBE3ZOCHHL3D5HS3.json","view_paper":"https://pith.science/paper/NOGDTPAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.06587&json=true","fetch_graph":"https://pith.science/api/pith-number/NOGDTPALKAUBE3ZOCHHL3D5HS3/graph.json","fetch_events":"https://pith.science/api/pith-number/NOGDTPALKAUBE3ZOCHHL3D5HS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NOGDTPALKAUBE3ZOCHHL3D5HS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NOGDTPALKAUBE3ZOCHHL3D5HS3/action/storage_attestation","attest_author":"https://pith.science/pith/NOGDTPALKAUBE3ZOCHHL3D5HS3/action/author_attestation","sign_citation":"https://pith.science/pith/NOGDTPALKAUBE3ZOCHHL3D5HS3/action/citation_signature","submit_replication":"https://pith.science/pith/NOGDTPALKAUBE3ZOCHHL3D5HS3/action/replication_record"}},"created_at":"2026-07-05T03:14:28.323244+00:00","updated_at":"2026-07-05T03:14:28.323244+00:00"}