{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R52PPIMV6PIMG4LRK6I2YMMSQE","short_pith_number":"pith:R52PPIMV","schema_version":"1.0","canonical_sha256":"8f74f7a195f3d0c371715791ac31928107e5fc61dfec63018b2cf632a0478a23","source":{"kind":"arxiv","id":"2412.07883","version":2},"attestation_state":"computed","paper":{"title":"On Faster Marginalization with Squared Circuits via Orthonormalization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Antonio Vergari, Lorenzo Loconte","submitted_at":"2024-12-10T19:37:03Z","abstract_excerpt":"Squared tensor networks (TNs) and their generalization as parameterized computational graphs -- squared circuits -- have been recently used as expressive distribution estimators in high dimensions. However, the squaring operation introduces additional complexity when marginalizing variables or computing the partition function, which hinders their usage in machine learning applications. Canonical forms of popular TNs are parameterized via unitary matrices as to simplify the computation of particular marginals, but cannot be mapped to general circuits since these might not correspond to a known "},"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":"2412.07883","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-10T19:37:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cb23eae36d7162097ea3d12cca9c7c719cfb01d6b4a4135231e93b656300dffa","abstract_canon_sha256":"25d31a37a4f9b01acf61892e84875ca7b2f235f8649bfd073d2d366ca020ac11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:55.790394Z","signature_b64":"InW3Ktv/gaLPXTfTun1BSteWMuCzcmaoIHaWhbZb9C6lJ/Plj36Aa5G4ReKjc49S1eG7o0ojeBMaN0F2Y3DFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f74f7a195f3d0c371715791ac31928107e5fc61dfec63018b2cf632a0478a23","last_reissued_at":"2026-07-05T10:02:55.790012Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:55.790012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Faster Marginalization with Squared Circuits via Orthonormalization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Antonio Vergari, Lorenzo Loconte","submitted_at":"2024-12-10T19:37:03Z","abstract_excerpt":"Squared tensor networks (TNs) and their generalization as parameterized computational graphs -- squared circuits -- have been recently used as expressive distribution estimators in high dimensions. However, the squaring operation introduces additional complexity when marginalizing variables or computing the partition function, which hinders their usage in machine learning applications. Canonical forms of popular TNs are parameterized via unitary matrices as to simplify the computation of particular marginals, but cannot be mapped to general circuits since these might not correspond to a known "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07883","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/2412.07883/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":"2412.07883","created_at":"2026-07-05T10:02:55.790068+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07883v2","created_at":"2026-07-05T10:02:55.790068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07883","created_at":"2026-07-05T10:02:55.790068+00:00"},{"alias_kind":"pith_short_12","alias_value":"R52PPIMV6PIM","created_at":"2026-07-05T10:02:55.790068+00:00"},{"alias_kind":"pith_short_16","alias_value":"R52PPIMV6PIMG4LR","created_at":"2026-07-05T10:02:55.790068+00:00"},{"alias_kind":"pith_short_8","alias_value":"R52PPIMV","created_at":"2026-07-05T10:02:55.790068+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01824","citing_title":"A Quantum Information Theoretic Approach to Tractable Probabilistic Models","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R52PPIMV6PIMG4LRK6I2YMMSQE","json":"https://pith.science/pith/R52PPIMV6PIMG4LRK6I2YMMSQE.json","graph_json":"https://pith.science/api/pith-number/R52PPIMV6PIMG4LRK6I2YMMSQE/graph.json","events_json":"https://pith.science/api/pith-number/R52PPIMV6PIMG4LRK6I2YMMSQE/events.json","paper":"https://pith.science/paper/R52PPIMV"},"agent_actions":{"view_html":"https://pith.science/pith/R52PPIMV6PIMG4LRK6I2YMMSQE","download_json":"https://pith.science/pith/R52PPIMV6PIMG4LRK6I2YMMSQE.json","view_paper":"https://pith.science/paper/R52PPIMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07883&json=true","fetch_graph":"https://pith.science/api/pith-number/R52PPIMV6PIMG4LRK6I2YMMSQE/graph.json","fetch_events":"https://pith.science/api/pith-number/R52PPIMV6PIMG4LRK6I2YMMSQE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R52PPIMV6PIMG4LRK6I2YMMSQE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R52PPIMV6PIMG4LRK6I2YMMSQE/action/storage_attestation","attest_author":"https://pith.science/pith/R52PPIMV6PIMG4LRK6I2YMMSQE/action/author_attestation","sign_citation":"https://pith.science/pith/R52PPIMV6PIMG4LRK6I2YMMSQE/action/citation_signature","submit_replication":"https://pith.science/pith/R52PPIMV6PIMG4LRK6I2YMMSQE/action/replication_record"}},"created_at":"2026-07-05T10:02:55.790068+00:00","updated_at":"2026-07-05T10:02:55.790068+00:00"}