{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TIQYUFL45CYRN5OSZZ36MFU3PF","short_pith_number":"pith:TIQYUFL4","schema_version":"1.0","canonical_sha256":"9a218a157ce8b116f5d2ce77e6169b796d2162058829d86664cbea0f9503e3b9","source":{"kind":"arxiv","id":"2607.00095","version":1},"attestation_state":"computed","paper":{"title":"SNAP-FM: Sparse Nonlinear Accelerated Projection for Physics-Constrained Generative Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE"],"primary_cat":"cs.LG","authors_text":"Alaina Kolli, Alan Edelman, Christopher Vincent Rackauckas, Pengfei Cai, Rafael Gomez-Bombarelli, Theodoros Xenakis, Utkarsh Utkarsh","submitted_at":"2026-06-30T19:35:09Z","abstract_excerpt":"Generative models have emerged as scalable surrogates for physical simulation, yet they offer no guarantee that their outputs respect the conservation laws, boundary conditions, and nonlinear invariants that govern the underlying physics. Constrained sampling closes this gap, enforcing such constraints exactly at inference time without retraining, but at a computational cost: projection, correction, and trajectory-optimization steps are repeated during sampling, with these steps becoming expensive for nonlinear constraints. Standard ML frameworks exacerbate this: their dense tensor algebra and"},"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":"2607.00095","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-30T19:35:09Z","cross_cats_sorted":["cs.AI","cs.CE"],"title_canon_sha256":"352eb0c4b17e397c914872f9f05e17cbf90b9622305af6de1439cf5d0780d2a5","abstract_canon_sha256":"0110ed4549710a6e5a30b6bca4a3e271e429182820e53e28406abd28e4700a10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T00:18:34.272840Z","signature_b64":"C2b7mpzqbZ0BQ5TtO8veVCbHKGcEWIUeYV5pwnJffpgULoHcZgoYviyoclGg1IQXhMg6sQrOYmgOeCcGNRrpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a218a157ce8b116f5d2ce77e6169b796d2162058829d86664cbea0f9503e3b9","last_reissued_at":"2026-07-02T00:18:34.272368Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T00:18:34.272368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SNAP-FM: Sparse Nonlinear Accelerated Projection for Physics-Constrained Generative Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE"],"primary_cat":"cs.LG","authors_text":"Alaina Kolli, Alan Edelman, Christopher Vincent Rackauckas, Pengfei Cai, Rafael Gomez-Bombarelli, Theodoros Xenakis, Utkarsh Utkarsh","submitted_at":"2026-06-30T19:35:09Z","abstract_excerpt":"Generative models have emerged as scalable surrogates for physical simulation, yet they offer no guarantee that their outputs respect the conservation laws, boundary conditions, and nonlinear invariants that govern the underlying physics. Constrained sampling closes this gap, enforcing such constraints exactly at inference time without retraining, but at a computational cost: projection, correction, and trajectory-optimization steps are repeated during sampling, with these steps becoming expensive for nonlinear constraints. Standard ML frameworks exacerbate this: their dense tensor algebra and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00095","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/2607.00095/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":"2607.00095","created_at":"2026-07-02T00:18:34.272425+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00095v1","created_at":"2026-07-02T00:18:34.272425+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00095","created_at":"2026-07-02T00:18:34.272425+00:00"},{"alias_kind":"pith_short_12","alias_value":"TIQYUFL45CYR","created_at":"2026-07-02T00:18:34.272425+00:00"},{"alias_kind":"pith_short_16","alias_value":"TIQYUFL45CYRN5OS","created_at":"2026-07-02T00:18:34.272425+00:00"},{"alias_kind":"pith_short_8","alias_value":"TIQYUFL4","created_at":"2026-07-02T00:18:34.272425+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/TIQYUFL45CYRN5OSZZ36MFU3PF","json":"https://pith.science/pith/TIQYUFL45CYRN5OSZZ36MFU3PF.json","graph_json":"https://pith.science/api/pith-number/TIQYUFL45CYRN5OSZZ36MFU3PF/graph.json","events_json":"https://pith.science/api/pith-number/TIQYUFL45CYRN5OSZZ36MFU3PF/events.json","paper":"https://pith.science/paper/TIQYUFL4"},"agent_actions":{"view_html":"https://pith.science/pith/TIQYUFL45CYRN5OSZZ36MFU3PF","download_json":"https://pith.science/pith/TIQYUFL45CYRN5OSZZ36MFU3PF.json","view_paper":"https://pith.science/paper/TIQYUFL4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00095&json=true","fetch_graph":"https://pith.science/api/pith-number/TIQYUFL45CYRN5OSZZ36MFU3PF/graph.json","fetch_events":"https://pith.science/api/pith-number/TIQYUFL45CYRN5OSZZ36MFU3PF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TIQYUFL45CYRN5OSZZ36MFU3PF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TIQYUFL45CYRN5OSZZ36MFU3PF/action/storage_attestation","attest_author":"https://pith.science/pith/TIQYUFL45CYRN5OSZZ36MFU3PF/action/author_attestation","sign_citation":"https://pith.science/pith/TIQYUFL45CYRN5OSZZ36MFU3PF/action/citation_signature","submit_replication":"https://pith.science/pith/TIQYUFL45CYRN5OSZZ36MFU3PF/action/replication_record"}},"created_at":"2026-07-02T00:18:34.272425+00:00","updated_at":"2026-07-02T00:18:34.272425+00:00"}