{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7U4RVTLL3ULA52B4DDE72F54DH","short_pith_number":"pith:7U4RVTLL","schema_version":"1.0","canonical_sha256":"fd391acd6bdd160ee83c18c9fd17bc19f4d0aacd95041eb9d67c2356c459648b","source":{"kind":"arxiv","id":"2502.07636","version":1},"attestation_state":"computed","paper":{"title":"Consistency Training with Physical Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Che-Chia Chang, Chen-Yang Dai, Chieh-Hsin Lai, Ming-Chih Lai, Te-Sheng Lin","submitted_at":"2025-02-11T15:23:14Z","abstract_excerpt":"We propose a physics-aware Consistency Training (CT) method that accelerates sampling in Diffusion Models with physical constraints. Our approach leverages a two-stage strategy: (1) learning the noise-to-data mapping via CT, and (2) incorporating physics constraints as a regularizer. Experiments on toy examples show that our method generates samples in a single step while adhering to the imposed constraints. This approach has the potential to efficiently solve partial differential equations (PDEs) using deep generative modeling."},"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":"2502.07636","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T15:23:14Z","cross_cats_sorted":[],"title_canon_sha256":"5293cf376e0d67925db48f4a1cd2f4af85e8b7fcd262c0083d122e00fce754ba","abstract_canon_sha256":"384eedb1633499aed63e48352e9d98acf6bf48b76d567390c39f63cbb6db0671"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:40.327000Z","signature_b64":"TJ62tCdWiEs7n0gEtgvGtNPW5iv5rycWOdXPxk2MNu2rCoDRKHk/Z7LM/3qHgI58xKKafyZLCIbygDgB01wGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd391acd6bdd160ee83c18c9fd17bc19f4d0aacd95041eb9d67c2356c459648b","last_reissued_at":"2026-07-05T10:12:40.326504Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:40.326504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Consistency Training with Physical Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Che-Chia Chang, Chen-Yang Dai, Chieh-Hsin Lai, Ming-Chih Lai, Te-Sheng Lin","submitted_at":"2025-02-11T15:23:14Z","abstract_excerpt":"We propose a physics-aware Consistency Training (CT) method that accelerates sampling in Diffusion Models with physical constraints. Our approach leverages a two-stage strategy: (1) learning the noise-to-data mapping via CT, and (2) incorporating physics constraints as a regularizer. Experiments on toy examples show that our method generates samples in a single step while adhering to the imposed constraints. This approach has the potential to efficiently solve partial differential equations (PDEs) using deep generative modeling."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07636","kind":"arxiv","version":1},"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/2502.07636/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":"2502.07636","created_at":"2026-07-05T10:12:40.326564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.07636v1","created_at":"2026-07-05T10:12:40.326564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07636","created_at":"2026-07-05T10:12:40.326564+00:00"},{"alias_kind":"pith_short_12","alias_value":"7U4RVTLL3ULA","created_at":"2026-07-05T10:12:40.326564+00:00"},{"alias_kind":"pith_short_16","alias_value":"7U4RVTLL3ULA52B4","created_at":"2026-07-05T10:12:40.326564+00:00"},{"alias_kind":"pith_short_8","alias_value":"7U4RVTLL","created_at":"2026-07-05T10:12:40.326564+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/7U4RVTLL3ULA52B4DDE72F54DH","json":"https://pith.science/pith/7U4RVTLL3ULA52B4DDE72F54DH.json","graph_json":"https://pith.science/api/pith-number/7U4RVTLL3ULA52B4DDE72F54DH/graph.json","events_json":"https://pith.science/api/pith-number/7U4RVTLL3ULA52B4DDE72F54DH/events.json","paper":"https://pith.science/paper/7U4RVTLL"},"agent_actions":{"view_html":"https://pith.science/pith/7U4RVTLL3ULA52B4DDE72F54DH","download_json":"https://pith.science/pith/7U4RVTLL3ULA52B4DDE72F54DH.json","view_paper":"https://pith.science/paper/7U4RVTLL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.07636&json=true","fetch_graph":"https://pith.science/api/pith-number/7U4RVTLL3ULA52B4DDE72F54DH/graph.json","fetch_events":"https://pith.science/api/pith-number/7U4RVTLL3ULA52B4DDE72F54DH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7U4RVTLL3ULA52B4DDE72F54DH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7U4RVTLL3ULA52B4DDE72F54DH/action/storage_attestation","attest_author":"https://pith.science/pith/7U4RVTLL3ULA52B4DDE72F54DH/action/author_attestation","sign_citation":"https://pith.science/pith/7U4RVTLL3ULA52B4DDE72F54DH/action/citation_signature","submit_replication":"https://pith.science/pith/7U4RVTLL3ULA52B4DDE72F54DH/action/replication_record"}},"created_at":"2026-07-05T10:12:40.326564+00:00","updated_at":"2026-07-05T10:12:40.326564+00:00"}