{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MGILAR3GW7FCR5X2KYFSOJ6SZT","short_pith_number":"pith:MGILAR3G","schema_version":"1.0","canonical_sha256":"6190b04766b7ca28f6fa560b2727d2ccead52784ab7604301ceb1d282b3c1393","source":{"kind":"arxiv","id":"2602.02009","version":2},"attestation_state":"computed","paper":{"title":"Logic-Guided Vector Fields for Constrained Generative Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ali Baheri","submitted_at":"2026-02-02T12:09:42Z","abstract_excerpt":"Neuro-symbolic systems aim to combine the expressive structure of symbolic logic with the flexibility of neural learning; yet, generative models typically lack mechanisms to enforce declarative constraints at generation time. We propose Logic-Guided Vector Fields (LGVF), a neuro-symbolic framework that injects symbolic knowledge, specified as differentiable relaxations of logical constraints, into flow matching generative models. LGVF couples two complementary mechanisms: (1) a training-time logic loss that penalizes constraint violations along continuous flow trajectories, with weights that e"},"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":"2602.02009","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T12:09:42Z","cross_cats_sorted":[],"title_canon_sha256":"e236f079a2b3d29e957dafd33097abdf38cb04fe941dfe1afe3860c2a620b70c","abstract_canon_sha256":"bbdf93d7785ccdf5b15a5e8a1ca6509b8ff7c9b4307ee0f29cacbf090458b7ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:31.751756Z","signature_b64":"o0tTn6c2TsejWH4ieNZ+ij8mIh8EJOre4ey3vYYEs3zj/JNS9KFPRJnDaT833VV8PR1HPlpoLnZtydNcxFLuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6190b04766b7ca28f6fa560b2727d2ccead52784ab7604301ceb1d282b3c1393","last_reissued_at":"2026-05-26T01:02:31.751006Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:31.751006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Logic-Guided Vector Fields for Constrained Generative Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ali Baheri","submitted_at":"2026-02-02T12:09:42Z","abstract_excerpt":"Neuro-symbolic systems aim to combine the expressive structure of symbolic logic with the flexibility of neural learning; yet, generative models typically lack mechanisms to enforce declarative constraints at generation time. We propose Logic-Guided Vector Fields (LGVF), a neuro-symbolic framework that injects symbolic knowledge, specified as differentiable relaxations of logical constraints, into flow matching generative models. LGVF couples two complementary mechanisms: (1) a training-time logic loss that penalizes constraint violations along continuous flow trajectories, with weights that e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.02009","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/2602.02009/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":"2602.02009","created_at":"2026-05-26T01:02:31.751103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.02009v2","created_at":"2026-05-26T01:02:31.751103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02009","created_at":"2026-05-26T01:02:31.751103+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGILAR3GW7FC","created_at":"2026-05-26T01:02:31.751103+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGILAR3GW7FCR5X2","created_at":"2026-05-26T01:02:31.751103+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGILAR3G","created_at":"2026-05-26T01:02:31.751103+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.18601","citing_title":"Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MGILAR3GW7FCR5X2KYFSOJ6SZT","json":"https://pith.science/pith/MGILAR3GW7FCR5X2KYFSOJ6SZT.json","graph_json":"https://pith.science/api/pith-number/MGILAR3GW7FCR5X2KYFSOJ6SZT/graph.json","events_json":"https://pith.science/api/pith-number/MGILAR3GW7FCR5X2KYFSOJ6SZT/events.json","paper":"https://pith.science/paper/MGILAR3G"},"agent_actions":{"view_html":"https://pith.science/pith/MGILAR3GW7FCR5X2KYFSOJ6SZT","download_json":"https://pith.science/pith/MGILAR3GW7FCR5X2KYFSOJ6SZT.json","view_paper":"https://pith.science/paper/MGILAR3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.02009&json=true","fetch_graph":"https://pith.science/api/pith-number/MGILAR3GW7FCR5X2KYFSOJ6SZT/graph.json","fetch_events":"https://pith.science/api/pith-number/MGILAR3GW7FCR5X2KYFSOJ6SZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGILAR3GW7FCR5X2KYFSOJ6SZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGILAR3GW7FCR5X2KYFSOJ6SZT/action/storage_attestation","attest_author":"https://pith.science/pith/MGILAR3GW7FCR5X2KYFSOJ6SZT/action/author_attestation","sign_citation":"https://pith.science/pith/MGILAR3GW7FCR5X2KYFSOJ6SZT/action/citation_signature","submit_replication":"https://pith.science/pith/MGILAR3GW7FCR5X2KYFSOJ6SZT/action/replication_record"}},"created_at":"2026-05-26T01:02:31.751103+00:00","updated_at":"2026-05-26T01:02:31.751103+00:00"}