{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7NYTRQJ7FSB7NFX4LN5H2S34II","short_pith_number":"pith:7NYTRQJ7","schema_version":"1.0","canonical_sha256":"fb7138c13f2c83f696fc5b7a7d4b7c4230f30ca59c1087bf4db4cc841e649f94","source":{"kind":"arxiv","id":"2506.19839","version":1},"attestation_state":"computed","paper":{"title":"Improving Progressive Generation with Decomposable Flow Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Arpit Sahni, Ivan Skorokhodov, Moayed Haji-Ali, Sergey Tulyakov, Vicente Ordonez, Willi Menapace","submitted_at":"2025-06-24T17:58:02Z","abstract_excerpt":"Generating high-dimensional visual modalities is a computationally intensive task. A common solution is progressive generation, where the outputs are synthesized in a coarse-to-fine spectral autoregressive manner. While diffusion models benefit from the coarse-to-fine nature of denoising, explicit multi-stage architectures are rarely adopted. These architectures have increased the complexity of the overall approach, introducing the need for a custom diffusion formulation, decomposition-dependent stage transitions, add-hoc samplers, or a model cascade. Our contribution, Decomposable Flow Matchi"},"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":"2506.19839","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T17:58:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"94f585e7d0f17e4647bf558e0744fe85bc07413cc07b1ec39892d0257b76ac86","abstract_canon_sha256":"f4b8168819298d5faee8cbe9259ca63dbda737c11cd43f4ad2668006f58bb026"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:39.288290Z","signature_b64":"5KOq8FAUcwMTxexlJ2pOKCALUO1lbLwAh+zF3ocIMlRiZxrq7mfMb2/yeEqPIu5TXEPrdHk0WmZwiQmpEmm0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb7138c13f2c83f696fc5b7a7d4b7c4230f30ca59c1087bf4db4cc841e649f94","last_reissued_at":"2026-07-05T11:26:39.287815Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:39.287815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Progressive Generation with Decomposable Flow Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Arpit Sahni, Ivan Skorokhodov, Moayed Haji-Ali, Sergey Tulyakov, Vicente Ordonez, Willi Menapace","submitted_at":"2025-06-24T17:58:02Z","abstract_excerpt":"Generating high-dimensional visual modalities is a computationally intensive task. A common solution is progressive generation, where the outputs are synthesized in a coarse-to-fine spectral autoregressive manner. While diffusion models benefit from the coarse-to-fine nature of denoising, explicit multi-stage architectures are rarely adopted. These architectures have increased the complexity of the overall approach, introducing the need for a custom diffusion formulation, decomposition-dependent stage transitions, add-hoc samplers, or a model cascade. Our contribution, Decomposable Flow Matchi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19839","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/2506.19839/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":"2506.19839","created_at":"2026-07-05T11:26:39.287869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19839v1","created_at":"2026-07-05T11:26:39.287869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19839","created_at":"2026-07-05T11:26:39.287869+00:00"},{"alias_kind":"pith_short_12","alias_value":"7NYTRQJ7FSB7","created_at":"2026-07-05T11:26:39.287869+00:00"},{"alias_kind":"pith_short_16","alias_value":"7NYTRQJ7FSB7NFX4","created_at":"2026-07-05T11:26:39.287869+00:00"},{"alias_kind":"pith_short_8","alias_value":"7NYTRQJ7","created_at":"2026-07-05T11:26:39.287869+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22668","citing_title":"SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7NYTRQJ7FSB7NFX4LN5H2S34II","json":"https://pith.science/pith/7NYTRQJ7FSB7NFX4LN5H2S34II.json","graph_json":"https://pith.science/api/pith-number/7NYTRQJ7FSB7NFX4LN5H2S34II/graph.json","events_json":"https://pith.science/api/pith-number/7NYTRQJ7FSB7NFX4LN5H2S34II/events.json","paper":"https://pith.science/paper/7NYTRQJ7"},"agent_actions":{"view_html":"https://pith.science/pith/7NYTRQJ7FSB7NFX4LN5H2S34II","download_json":"https://pith.science/pith/7NYTRQJ7FSB7NFX4LN5H2S34II.json","view_paper":"https://pith.science/paper/7NYTRQJ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19839&json=true","fetch_graph":"https://pith.science/api/pith-number/7NYTRQJ7FSB7NFX4LN5H2S34II/graph.json","fetch_events":"https://pith.science/api/pith-number/7NYTRQJ7FSB7NFX4LN5H2S34II/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7NYTRQJ7FSB7NFX4LN5H2S34II/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7NYTRQJ7FSB7NFX4LN5H2S34II/action/storage_attestation","attest_author":"https://pith.science/pith/7NYTRQJ7FSB7NFX4LN5H2S34II/action/author_attestation","sign_citation":"https://pith.science/pith/7NYTRQJ7FSB7NFX4LN5H2S34II/action/citation_signature","submit_replication":"https://pith.science/pith/7NYTRQJ7FSB7NFX4LN5H2S34II/action/replication_record"}},"created_at":"2026-07-05T11:26:39.287869+00:00","updated_at":"2026-07-05T11:26:39.287869+00:00"}