{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B4MVK7JM5KC7NOU3YXC3C4HJIG","short_pith_number":"pith:B4MVK7JM","schema_version":"1.0","canonical_sha256":"0f19557d2cea85f6ba9bc5c5b170e94187447891de5155d780e679912b1b4c62","source":{"kind":"arxiv","id":"2602.23526","version":3},"attestation_state":"computed","paper":{"title":"Training with Hard Constraints: Learning Neural Certificates and Controllers for SDEs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Chun-Wei Kong, Ibon Gracia, Jay McMahon, Morteza Lahijanian, Sebastian Escobar","submitted_at":"2026-02-26T22:11:07Z","abstract_excerpt":"Due to their expressive power, neural networks (NNs) are promising templates for functional optimization problems, particularly for reach-avoid certificate generation for systems governed by stochastic differential equations (SDEs). However, ensuring hard-constraint satisfaction remains a major challenge. In this work, we propose two constraint-driven training frameworks with guarantees for supermartingale-based neural certificate construction and controller synthesis for SDEs. The first approach enforces certificate inequalities via domain discretization and a bound-based loss, guaranteeing g"},"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":"2602.23526","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2026-02-26T22:11:07Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"26e37ab2b7789f2d552a005986e2c98dab878d766372ba9acc13f019bdcbfb4b","abstract_canon_sha256":"2a4dc34799012f91b3c49a9e9d5115e75569f7a3b33317e87940f8341fad9d4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:46.452243Z","signature_b64":"p2aUxXDCwJZxejUm/mDdABpL5PlwwnaEYCRbXIDdxoyL7A4Vj+hSVPiidYc65XGaoKzwpOV/+RJ4xFeiweZ6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f19557d2cea85f6ba9bc5c5b170e94187447891de5155d780e679912b1b4c62","last_reissued_at":"2026-06-04T01:08:46.451728Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:46.451728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training with Hard Constraints: Learning Neural Certificates and Controllers for SDEs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Chun-Wei Kong, Ibon Gracia, Jay McMahon, Morteza Lahijanian, Sebastian Escobar","submitted_at":"2026-02-26T22:11:07Z","abstract_excerpt":"Due to their expressive power, neural networks (NNs) are promising templates for functional optimization problems, particularly for reach-avoid certificate generation for systems governed by stochastic differential equations (SDEs). However, ensuring hard-constraint satisfaction remains a major challenge. In this work, we propose two constraint-driven training frameworks with guarantees for supermartingale-based neural certificate construction and controller synthesis for SDEs. The first approach enforces certificate inequalities via domain discretization and a bound-based loss, guaranteeing g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.23526","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/2602.23526/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":"2602.23526","created_at":"2026-06-04T01:08:46.451792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.23526v3","created_at":"2026-06-04T01:08:46.451792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.23526","created_at":"2026-06-04T01:08:46.451792+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4MVK7JM5KC7","created_at":"2026-06-04T01:08:46.451792+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4MVK7JM5KC7NOU3","created_at":"2026-06-04T01:08:46.451792+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4MVK7JM","created_at":"2026-06-04T01:08:46.451792+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.20208","citing_title":"Stochastic Barrier Certificates in the Presence of Dynamic Obstacles","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4MVK7JM5KC7NOU3YXC3C4HJIG","json":"https://pith.science/pith/B4MVK7JM5KC7NOU3YXC3C4HJIG.json","graph_json":"https://pith.science/api/pith-number/B4MVK7JM5KC7NOU3YXC3C4HJIG/graph.json","events_json":"https://pith.science/api/pith-number/B4MVK7JM5KC7NOU3YXC3C4HJIG/events.json","paper":"https://pith.science/paper/B4MVK7JM"},"agent_actions":{"view_html":"https://pith.science/pith/B4MVK7JM5KC7NOU3YXC3C4HJIG","download_json":"https://pith.science/pith/B4MVK7JM5KC7NOU3YXC3C4HJIG.json","view_paper":"https://pith.science/paper/B4MVK7JM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.23526&json=true","fetch_graph":"https://pith.science/api/pith-number/B4MVK7JM5KC7NOU3YXC3C4HJIG/graph.json","fetch_events":"https://pith.science/api/pith-number/B4MVK7JM5KC7NOU3YXC3C4HJIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4MVK7JM5KC7NOU3YXC3C4HJIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4MVK7JM5KC7NOU3YXC3C4HJIG/action/storage_attestation","attest_author":"https://pith.science/pith/B4MVK7JM5KC7NOU3YXC3C4HJIG/action/author_attestation","sign_citation":"https://pith.science/pith/B4MVK7JM5KC7NOU3YXC3C4HJIG/action/citation_signature","submit_replication":"https://pith.science/pith/B4MVK7JM5KC7NOU3YXC3C4HJIG/action/replication_record"}},"created_at":"2026-06-04T01:08:46.451792+00:00","updated_at":"2026-06-04T01:08:46.451792+00:00"}