{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3W6N32GA4LBTWGP662WAH64DH7","short_pith_number":"pith:3W6N32GA","schema_version":"1.0","canonical_sha256":"ddbcdde8c0e2c33b19fef6ac03fb833ff6eff53673284d3808e54888a1099744","source":{"kind":"arxiv","id":"2410.11415","version":3},"attestation_state":"computed","paper":{"title":"KLay: Accelerating Arithmetic Circuits for Neurosymbolic AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jaron Maene, Pedro Zuidberg Dos Martires, Vincent Derkinderen","submitted_at":"2024-10-15T09:02:55Z","abstract_excerpt":"A popular approach to neurosymbolic AI involves mapping logic formulas to arithmetic circuits (computation graphs consisting of sums and products) and passing the outputs of a neural network through these circuits. This approach enforces symbolic constraints onto a neural network in a principled and end-to-end differentiable way. Unfortunately, arithmetic circuits are challenging to run on modern AI accelerators as they exhibit a high degree of irregular sparsity. To address this limitation, we introduce knowledge layers (KLay), a new data structure to represent arithmetic circuits that can be"},"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":"2410.11415","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T09:02:55Z","cross_cats_sorted":[],"title_canon_sha256":"a9baf9986603be074e19f346a69d756e7704f9cf1c72fd893d78272f0ac6edb8","abstract_canon_sha256":"579af7ed3797db96a73c91ba108abf7e6f566fb3289c8aa41f596aede766a75e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:35.237516Z","signature_b64":"XpPWOEkbfGcdxL8TTiSKDqpraw1EaXPfKEUqWZDhkQsBekfOVacEtVEheqDhv/LlXfzC3nV2ZYNebrW7z5V5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddbcdde8c0e2c33b19fef6ac03fb833ff6eff53673284d3808e54888a1099744","last_reissued_at":"2026-07-05T10:17:35.237000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:35.237000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KLay: Accelerating Arithmetic Circuits for Neurosymbolic AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jaron Maene, Pedro Zuidberg Dos Martires, Vincent Derkinderen","submitted_at":"2024-10-15T09:02:55Z","abstract_excerpt":"A popular approach to neurosymbolic AI involves mapping logic formulas to arithmetic circuits (computation graphs consisting of sums and products) and passing the outputs of a neural network through these circuits. This approach enforces symbolic constraints onto a neural network in a principled and end-to-end differentiable way. Unfortunately, arithmetic circuits are challenging to run on modern AI accelerators as they exhibit a high degree of irregular sparsity. To address this limitation, we introduce knowledge layers (KLay), a new data structure to represent arithmetic circuits that can be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11415","kind":"arxiv","version":3},"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/2410.11415/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":"2410.11415","created_at":"2026-07-05T10:17:35.237062+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11415v3","created_at":"2026-07-05T10:17:35.237062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11415","created_at":"2026-07-05T10:17:35.237062+00:00"},{"alias_kind":"pith_short_12","alias_value":"3W6N32GA4LBT","created_at":"2026-07-05T10:17:35.237062+00:00"},{"alias_kind":"pith_short_16","alias_value":"3W6N32GA4LBTWGP6","created_at":"2026-07-05T10:17:35.237062+00:00"},{"alias_kind":"pith_short_8","alias_value":"3W6N32GA","created_at":"2026-07-05T10:17:35.237062+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12383","citing_title":"Scaling Probabilistic Circuits via Monarch Matrices","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3W6N32GA4LBTWGP662WAH64DH7","json":"https://pith.science/pith/3W6N32GA4LBTWGP662WAH64DH7.json","graph_json":"https://pith.science/api/pith-number/3W6N32GA4LBTWGP662WAH64DH7/graph.json","events_json":"https://pith.science/api/pith-number/3W6N32GA4LBTWGP662WAH64DH7/events.json","paper":"https://pith.science/paper/3W6N32GA"},"agent_actions":{"view_html":"https://pith.science/pith/3W6N32GA4LBTWGP662WAH64DH7","download_json":"https://pith.science/pith/3W6N32GA4LBTWGP662WAH64DH7.json","view_paper":"https://pith.science/paper/3W6N32GA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11415&json=true","fetch_graph":"https://pith.science/api/pith-number/3W6N32GA4LBTWGP662WAH64DH7/graph.json","fetch_events":"https://pith.science/api/pith-number/3W6N32GA4LBTWGP662WAH64DH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3W6N32GA4LBTWGP662WAH64DH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3W6N32GA4LBTWGP662WAH64DH7/action/storage_attestation","attest_author":"https://pith.science/pith/3W6N32GA4LBTWGP662WAH64DH7/action/author_attestation","sign_citation":"https://pith.science/pith/3W6N32GA4LBTWGP662WAH64DH7/action/citation_signature","submit_replication":"https://pith.science/pith/3W6N32GA4LBTWGP662WAH64DH7/action/replication_record"}},"created_at":"2026-07-05T10:17:35.237062+00:00","updated_at":"2026-07-05T10:17:35.237062+00:00"}