{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GYGLVKWJOBWMCGKCT77Z4UKVAW","short_pith_number":"pith:GYGLVKWJ","schema_version":"1.0","canonical_sha256":"360cbaaac9706cc119429fff9e51550599ce8b391a8624bfd9bb836bc9ef1f34","source":{"kind":"arxiv","id":"2507.04385","version":2},"attestation_state":"computed","paper":{"title":"Tractable Representation Learning with Probabilistic Circuits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Antonio Vergari, Kristian Kersting, Martin Mundt, Sahil Sidheekh, Sriraam Natarajan, Steven Braun","submitted_at":"2025-07-06T13:17:16Z","abstract_excerpt":"Probabilistic circuits (PCs) are powerful probabilistic models that enable exact and tractable inference, making them highly suitable for probabilistic reasoning and inference tasks. While dominant in neural networks, representation learning with PCs remains underexplored, with prior approaches relying on external neural embeddings or activation-based encodings. To address this gap, we introduce autoencoding probabilistic circuits (APCs), a novel framework leveraging the tractability of PCs to model probabilistic embeddings explicitly. APCs extend PCs by jointly modeling data and embeddings, o"},"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":"2507.04385","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-06T13:17:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8ed0bfbe3542b089435b7f96a4f76aaba6a4304d7e03fe23922b1160d3b19dcc","abstract_canon_sha256":"2675e29b2cddd8806803b0e1c27640ddba98c19fbd6ee8969c96cd642e99e381"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:33.271714Z","signature_b64":"g4OzU/jzYm0WAw/BVlk6B3NueYzy/GmHkGGn8K4mY7RNU81SWyHEowKB46Nbl6wZwtItUDhfqDdTNV5Cs6QACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"360cbaaac9706cc119429fff9e51550599ce8b391a8624bfd9bb836bc9ef1f34","last_reissued_at":"2026-07-05T11:43:33.271260Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:33.271260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tractable Representation Learning with Probabilistic Circuits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Antonio Vergari, Kristian Kersting, Martin Mundt, Sahil Sidheekh, Sriraam Natarajan, Steven Braun","submitted_at":"2025-07-06T13:17:16Z","abstract_excerpt":"Probabilistic circuits (PCs) are powerful probabilistic models that enable exact and tractable inference, making them highly suitable for probabilistic reasoning and inference tasks. While dominant in neural networks, representation learning with PCs remains underexplored, with prior approaches relying on external neural embeddings or activation-based encodings. To address this gap, we introduce autoencoding probabilistic circuits (APCs), a novel framework leveraging the tractability of PCs to model probabilistic embeddings explicitly. APCs extend PCs by jointly modeling data and embeddings, o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04385","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/2507.04385/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":"2507.04385","created_at":"2026-07-05T11:43:33.271335+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04385v2","created_at":"2026-07-05T11:43:33.271335+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04385","created_at":"2026-07-05T11:43:33.271335+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYGLVKWJOBWM","created_at":"2026-07-05T11:43:33.271335+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYGLVKWJOBWMCGKC","created_at":"2026-07-05T11:43:33.271335+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYGLVKWJ","created_at":"2026-07-05T11:43:33.271335+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/GYGLVKWJOBWMCGKCT77Z4UKVAW","json":"https://pith.science/pith/GYGLVKWJOBWMCGKCT77Z4UKVAW.json","graph_json":"https://pith.science/api/pith-number/GYGLVKWJOBWMCGKCT77Z4UKVAW/graph.json","events_json":"https://pith.science/api/pith-number/GYGLVKWJOBWMCGKCT77Z4UKVAW/events.json","paper":"https://pith.science/paper/GYGLVKWJ"},"agent_actions":{"view_html":"https://pith.science/pith/GYGLVKWJOBWMCGKCT77Z4UKVAW","download_json":"https://pith.science/pith/GYGLVKWJOBWMCGKCT77Z4UKVAW.json","view_paper":"https://pith.science/paper/GYGLVKWJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04385&json=true","fetch_graph":"https://pith.science/api/pith-number/GYGLVKWJOBWMCGKCT77Z4UKVAW/graph.json","fetch_events":"https://pith.science/api/pith-number/GYGLVKWJOBWMCGKCT77Z4UKVAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYGLVKWJOBWMCGKCT77Z4UKVAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYGLVKWJOBWMCGKCT77Z4UKVAW/action/storage_attestation","attest_author":"https://pith.science/pith/GYGLVKWJOBWMCGKCT77Z4UKVAW/action/author_attestation","sign_citation":"https://pith.science/pith/GYGLVKWJOBWMCGKCT77Z4UKVAW/action/citation_signature","submit_replication":"https://pith.science/pith/GYGLVKWJOBWMCGKCT77Z4UKVAW/action/replication_record"}},"created_at":"2026-07-05T11:43:33.271335+00:00","updated_at":"2026-07-05T11:43:33.271335+00:00"}