{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RPN7ULVOSSGDM6Z5SY3X7C3VMC","short_pith_number":"pith:RPN7ULVO","schema_version":"1.0","canonical_sha256":"8bdbfa2eae948c367b3d96377f8b75609ad3022cf4872ca5062ab79599e4a5d1","source":{"kind":"arxiv","id":"2607.14398","version":1},"attestation_state":"computed","paper":{"title":"Integration Matters: Rollout-Based Training for Constrained Diffusion Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Berend Zwartsenberg, Frank Wood, Saeid Naderiparizi, Xiaoxuan Liang","submitted_at":"2026-07-15T22:25:59Z","abstract_excerpt":"Constrained generative models aim to produce samples that satisfy complex feasibility constraints while remaining faithful to the data distribution. Existing constrained generation methods typically enforce constraints either through training-time optimization or sampling-time correction. Training-time optimization approaches optimize on states induced by the training distribution, which can differ substantially from those encountered during sampling. Sampling-time correction methods instead modify the sampling process at inference, introducing distribution shift and requiring expensive tuning"},"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":"2607.14398","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-15T22:25:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a90677a0d6330587105761b6e85819584ae2b6c2cb9ec2a492816d08ac66dd7e","abstract_canon_sha256":"6664a1aaaf92e1bee88c7e4daf0dc94bd05dab5a09da298b58b7fac4735eeb8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T00:21:10.695142Z","signature_b64":"oJeIHd9qB2Bl8e5IMSSo48ny7his/Pu2l8eZKNLSFOo7MmtQQdgrbyB+a0qvMXiRCEvnkSlfxybMaWEA9fezAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bdbfa2eae948c367b3d96377f8b75609ad3022cf4872ca5062ab79599e4a5d1","last_reissued_at":"2026-07-17T00:21:10.694324Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T00:21:10.694324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Integration Matters: Rollout-Based Training for Constrained Diffusion Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Berend Zwartsenberg, Frank Wood, Saeid Naderiparizi, Xiaoxuan Liang","submitted_at":"2026-07-15T22:25:59Z","abstract_excerpt":"Constrained generative models aim to produce samples that satisfy complex feasibility constraints while remaining faithful to the data distribution. Existing constrained generation methods typically enforce constraints either through training-time optimization or sampling-time correction. Training-time optimization approaches optimize on states induced by the training distribution, which can differ substantially from those encountered during sampling. Sampling-time correction methods instead modify the sampling process at inference, introducing distribution shift and requiring expensive tuning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14398","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/2607.14398/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":"2607.14398","created_at":"2026-07-17T00:21:10.694744+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14398v1","created_at":"2026-07-17T00:21:10.694744+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14398","created_at":"2026-07-17T00:21:10.694744+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPN7ULVOSSGD","created_at":"2026-07-17T00:21:10.694744+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPN7ULVOSSGDM6Z5","created_at":"2026-07-17T00:21:10.694744+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPN7ULVO","created_at":"2026-07-17T00:21:10.694744+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/RPN7ULVOSSGDM6Z5SY3X7C3VMC","json":"https://pith.science/pith/RPN7ULVOSSGDM6Z5SY3X7C3VMC.json","graph_json":"https://pith.science/api/pith-number/RPN7ULVOSSGDM6Z5SY3X7C3VMC/graph.json","events_json":"https://pith.science/api/pith-number/RPN7ULVOSSGDM6Z5SY3X7C3VMC/events.json","paper":"https://pith.science/paper/RPN7ULVO"},"agent_actions":{"view_html":"https://pith.science/pith/RPN7ULVOSSGDM6Z5SY3X7C3VMC","download_json":"https://pith.science/pith/RPN7ULVOSSGDM6Z5SY3X7C3VMC.json","view_paper":"https://pith.science/paper/RPN7ULVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14398&json=true","fetch_graph":"https://pith.science/api/pith-number/RPN7ULVOSSGDM6Z5SY3X7C3VMC/graph.json","fetch_events":"https://pith.science/api/pith-number/RPN7ULVOSSGDM6Z5SY3X7C3VMC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPN7ULVOSSGDM6Z5SY3X7C3VMC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPN7ULVOSSGDM6Z5SY3X7C3VMC/action/storage_attestation","attest_author":"https://pith.science/pith/RPN7ULVOSSGDM6Z5SY3X7C3VMC/action/author_attestation","sign_citation":"https://pith.science/pith/RPN7ULVOSSGDM6Z5SY3X7C3VMC/action/citation_signature","submit_replication":"https://pith.science/pith/RPN7ULVOSSGDM6Z5SY3X7C3VMC/action/replication_record"}},"created_at":"2026-07-17T00:21:10.694744+00:00","updated_at":"2026-07-17T00:21:10.694744+00:00"}