{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TMEOLZISK7H7BCND3QYAWVFFW5","short_pith_number":"pith:TMEOLZIS","schema_version":"1.0","canonical_sha256":"9b08e5e51257cff089a3dc300b54a5b75faaec4952e085a3638248629202c03a","source":{"kind":"arxiv","id":"2509.21663","version":2},"attestation_state":"computed","paper":{"title":"Logic of Hypotheses: from Zero to Full Knowledge in Neurosymbolic Integration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LO"],"primary_cat":"cs.LG","authors_text":"Alessandro Daniele, Davide Bizzaro","submitted_at":"2025-09-25T22:31:43Z","abstract_excerpt":"Neurosymbolic integration (NeSy) blends neural-network learning with symbolic reasoning. The field can be split between methods injecting hand-crafted rules into neural models, and methods inducing symbolic rules from data. We introduce Logic of Hypotheses (LoH), a novel language that unifies these strands, enabling the flexible integration of data-driven rule learning with symbolic priors and expert knowledge. LoH extends propositional logic syntax with a choice operator, which has learnable parameters and selects a subformula from a pool of options. Using fuzzy logic, formulas in LoH 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":"2509.21663","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-25T22:31:43Z","cross_cats_sorted":["cs.AI","cs.LO"],"title_canon_sha256":"5b0340a23021db974ce86bbbef8be73c3226a554490fc41de7346dd556e5514c","abstract_canon_sha256":"5e0eac6e2b4fee72c85093ce5d8d91ef69f7cd918bcbc7e1431615fbf673f1f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:35.631006Z","signature_b64":"iMlj0UotZYVIIf1iXl1tqH4Jm7U3yaK18gV0/gyNBBEqIEFlrDW2lQYKIYkolVGnBZynRvAb6snPVVLCi71hBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b08e5e51257cff089a3dc300b54a5b75faaec4952e085a3638248629202c03a","last_reissued_at":"2026-05-20T00:01:35.630194Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:35.630194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Logic of Hypotheses: from Zero to Full Knowledge in Neurosymbolic Integration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LO"],"primary_cat":"cs.LG","authors_text":"Alessandro Daniele, Davide Bizzaro","submitted_at":"2025-09-25T22:31:43Z","abstract_excerpt":"Neurosymbolic integration (NeSy) blends neural-network learning with symbolic reasoning. The field can be split between methods injecting hand-crafted rules into neural models, and methods inducing symbolic rules from data. We introduce Logic of Hypotheses (LoH), a novel language that unifies these strands, enabling the flexible integration of data-driven rule learning with symbolic priors and expert knowledge. LoH extends propositional logic syntax with a choice operator, which has learnable parameters and selects a subformula from a pool of options. Using fuzzy logic, formulas in LoH can be "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.21663","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/2509.21663/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":"2509.21663","created_at":"2026-05-20T00:01:35.630325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.21663v2","created_at":"2026-05-20T00:01:35.630325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.21663","created_at":"2026-05-20T00:01:35.630325+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMEOLZISK7H7","created_at":"2026-05-20T00:01:35.630325+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMEOLZISK7H7BCND","created_at":"2026-05-20T00:01:35.630325+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMEOLZIS","created_at":"2026-05-20T00:01:35.630325+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/TMEOLZISK7H7BCND3QYAWVFFW5","json":"https://pith.science/pith/TMEOLZISK7H7BCND3QYAWVFFW5.json","graph_json":"https://pith.science/api/pith-number/TMEOLZISK7H7BCND3QYAWVFFW5/graph.json","events_json":"https://pith.science/api/pith-number/TMEOLZISK7H7BCND3QYAWVFFW5/events.json","paper":"https://pith.science/paper/TMEOLZIS"},"agent_actions":{"view_html":"https://pith.science/pith/TMEOLZISK7H7BCND3QYAWVFFW5","download_json":"https://pith.science/pith/TMEOLZISK7H7BCND3QYAWVFFW5.json","view_paper":"https://pith.science/paper/TMEOLZIS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.21663&json=true","fetch_graph":"https://pith.science/api/pith-number/TMEOLZISK7H7BCND3QYAWVFFW5/graph.json","fetch_events":"https://pith.science/api/pith-number/TMEOLZISK7H7BCND3QYAWVFFW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMEOLZISK7H7BCND3QYAWVFFW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMEOLZISK7H7BCND3QYAWVFFW5/action/storage_attestation","attest_author":"https://pith.science/pith/TMEOLZISK7H7BCND3QYAWVFFW5/action/author_attestation","sign_citation":"https://pith.science/pith/TMEOLZISK7H7BCND3QYAWVFFW5/action/citation_signature","submit_replication":"https://pith.science/pith/TMEOLZISK7H7BCND3QYAWVFFW5/action/replication_record"}},"created_at":"2026-05-20T00:01:35.630325+00:00","updated_at":"2026-05-20T00:01:35.630325+00:00"}