{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5YGHGWJLF5J274EZKONLMAL2YD","short_pith_number":"pith:5YGHGWJL","schema_version":"1.0","canonical_sha256":"ee0c73592b2f53aff099539ab6017ac0f183c31594e4a2f8970d19180c9ff4bd","source":{"kind":"arxiv","id":"2602.09303","version":2},"attestation_state":"computed","paper":{"title":"Stabilizing Physics-Informed Consistency Models via Structure-Preserving Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Che-Chia Chang, Chen-Yang Dai, Chieh-Hsin Lai, Ming-Chih Lai, Te-Sheng Lin","submitted_at":"2026-02-10T00:40:19Z","abstract_excerpt":"We propose a physics-informed consistency modeling framework for solving partial differential equations (PDEs) via fast, few-step generative inference. We identify a key stability challenge in physics-constrained consistency training, where PDE residuals can drive the model toward trivial or degenerate solutions, degrading the learned data distribution. To address this, we introduce a structure-preserving two-stage training strategy that decouples distribution learning from physics enforcement by freezing the coefficient decoder during physics-informed fine-tuning. We further propose a two-ste"},"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":"2602.09303","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-10T00:40:19Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"12fb8b23c0231f0ea701fa603f529c90f92532f40ada7323c8d1adbff29f609c","abstract_canon_sha256":"06d4079eceea3a892f3867b94dca9089c85a8a4e7ad6a06d09887a00c2321714"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:25.831136Z","signature_b64":"PwlS9HaD2NA3gLc0phg3RVV7bzmbwgsOpRkHxMZiFoj599UpxcXcVFv6HWvEJN0+4sgwsSr1iHJVEe4d4dk3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee0c73592b2f53aff099539ab6017ac0f183c31594e4a2f8970d19180c9ff4bd","last_reissued_at":"2026-06-24T01:14:25.830673Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:25.830673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stabilizing Physics-Informed Consistency Models via Structure-Preserving Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Che-Chia Chang, Chen-Yang Dai, Chieh-Hsin Lai, Ming-Chih Lai, Te-Sheng Lin","submitted_at":"2026-02-10T00:40:19Z","abstract_excerpt":"We propose a physics-informed consistency modeling framework for solving partial differential equations (PDEs) via fast, few-step generative inference. We identify a key stability challenge in physics-constrained consistency training, where PDE residuals can drive the model toward trivial or degenerate solutions, degrading the learned data distribution. To address this, we introduce a structure-preserving two-stage training strategy that decouples distribution learning from physics enforcement by freezing the coefficient decoder during physics-informed fine-tuning. We further propose a two-ste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.09303","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/2602.09303/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":"2602.09303","created_at":"2026-06-24T01:14:25.830736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.09303v2","created_at":"2026-06-24T01:14:25.830736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.09303","created_at":"2026-06-24T01:14:25.830736+00:00"},{"alias_kind":"pith_short_12","alias_value":"5YGHGWJLF5J2","created_at":"2026-06-24T01:14:25.830736+00:00"},{"alias_kind":"pith_short_16","alias_value":"5YGHGWJLF5J274EZ","created_at":"2026-06-24T01:14:25.830736+00:00"},{"alias_kind":"pith_short_8","alias_value":"5YGHGWJL","created_at":"2026-06-24T01:14:25.830736+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/5YGHGWJLF5J274EZKONLMAL2YD","json":"https://pith.science/pith/5YGHGWJLF5J274EZKONLMAL2YD.json","graph_json":"https://pith.science/api/pith-number/5YGHGWJLF5J274EZKONLMAL2YD/graph.json","events_json":"https://pith.science/api/pith-number/5YGHGWJLF5J274EZKONLMAL2YD/events.json","paper":"https://pith.science/paper/5YGHGWJL"},"agent_actions":{"view_html":"https://pith.science/pith/5YGHGWJLF5J274EZKONLMAL2YD","download_json":"https://pith.science/pith/5YGHGWJLF5J274EZKONLMAL2YD.json","view_paper":"https://pith.science/paper/5YGHGWJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.09303&json=true","fetch_graph":"https://pith.science/api/pith-number/5YGHGWJLF5J274EZKONLMAL2YD/graph.json","fetch_events":"https://pith.science/api/pith-number/5YGHGWJLF5J274EZKONLMAL2YD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5YGHGWJLF5J274EZKONLMAL2YD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5YGHGWJLF5J274EZKONLMAL2YD/action/storage_attestation","attest_author":"https://pith.science/pith/5YGHGWJLF5J274EZKONLMAL2YD/action/author_attestation","sign_citation":"https://pith.science/pith/5YGHGWJLF5J274EZKONLMAL2YD/action/citation_signature","submit_replication":"https://pith.science/pith/5YGHGWJLF5J274EZKONLMAL2YD/action/replication_record"}},"created_at":"2026-06-24T01:14:25.830736+00:00","updated_at":"2026-06-24T01:14:25.830736+00:00"}