{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AW6ZRJ5AFNCCK63HAHTLMANDRU","short_pith_number":"pith:AW6ZRJ5A","schema_version":"1.0","canonical_sha256":"05bd98a7a02b44257b6701e6b601a38d1db0bdf0ae91234641e2684321f0cf56","source":{"kind":"arxiv","id":"2605.21381","version":1},"attestation_state":"computed","paper":{"title":"Disentangling Generation and Regression in Stochastic Interpolants for Controllable Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jia Ma, Jihong Guan, Shuigeng Zhou, Wengen Li, Yichao Zhang, Yi Liu","submitted_at":"2026-05-20T16:41:32Z","abstract_excerpt":"Recent advances in Image Restoration (IR) have been largely driven by generative methods such as Diffusion Models and Flow Matching, which excel in synthesizing realistic textures while suffering from slow multi-step inference and compromised pixel fidelity. In contrast, classical regression-based IR methods excel precisely in these aspects, offering single-step efficiency and high pixel-level reconstruction fidelity. To bridge this gap, we propose DiSI, a unified framework that Disentangles the underlying Stochastic Interpolant process into independent generation and regression components. Th"},"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":"2605.21381","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T16:41:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"22e7554c7e70e3339ee1d93ae8ac12abbafec4cf140cb7e3fd5470e52635ec5d","abstract_canon_sha256":"89d2630550d9c8d5df418eceb4c8e1cb87c86d68b39979bb888b1df678fa4144"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:31.963689Z","signature_b64":"hlm2j0nf6TEI1+jGnk1nmLmAjPhJmk/pKDOwIhrrEngsMD45wNRdTQ3p51tluCC00s6ow+kAeKiPfWWL06cZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05bd98a7a02b44257b6701e6b601a38d1db0bdf0ae91234641e2684321f0cf56","last_reissued_at":"2026-05-21T02:05:31.962885Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:31.962885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangling Generation and Regression in Stochastic Interpolants for Controllable Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jia Ma, Jihong Guan, Shuigeng Zhou, Wengen Li, Yichao Zhang, Yi Liu","submitted_at":"2026-05-20T16:41:32Z","abstract_excerpt":"Recent advances in Image Restoration (IR) have been largely driven by generative methods such as Diffusion Models and Flow Matching, which excel in synthesizing realistic textures while suffering from slow multi-step inference and compromised pixel fidelity. In contrast, classical regression-based IR methods excel precisely in these aspects, offering single-step efficiency and high pixel-level reconstruction fidelity. To bridge this gap, we propose DiSI, a unified framework that Disentangles the underlying Stochastic Interpolant process into independent generation and regression components. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21381","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/2605.21381/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":"2605.21381","created_at":"2026-05-21T02:05:31.963019+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21381v1","created_at":"2026-05-21T02:05:31.963019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21381","created_at":"2026-05-21T02:05:31.963019+00:00"},{"alias_kind":"pith_short_12","alias_value":"AW6ZRJ5AFNCC","created_at":"2026-05-21T02:05:31.963019+00:00"},{"alias_kind":"pith_short_16","alias_value":"AW6ZRJ5AFNCCK63H","created_at":"2026-05-21T02:05:31.963019+00:00"},{"alias_kind":"pith_short_8","alias_value":"AW6ZRJ5A","created_at":"2026-05-21T02:05:31.963019+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/AW6ZRJ5AFNCCK63HAHTLMANDRU","json":"https://pith.science/pith/AW6ZRJ5AFNCCK63HAHTLMANDRU.json","graph_json":"https://pith.science/api/pith-number/AW6ZRJ5AFNCCK63HAHTLMANDRU/graph.json","events_json":"https://pith.science/api/pith-number/AW6ZRJ5AFNCCK63HAHTLMANDRU/events.json","paper":"https://pith.science/paper/AW6ZRJ5A"},"agent_actions":{"view_html":"https://pith.science/pith/AW6ZRJ5AFNCCK63HAHTLMANDRU","download_json":"https://pith.science/pith/AW6ZRJ5AFNCCK63HAHTLMANDRU.json","view_paper":"https://pith.science/paper/AW6ZRJ5A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21381&json=true","fetch_graph":"https://pith.science/api/pith-number/AW6ZRJ5AFNCCK63HAHTLMANDRU/graph.json","fetch_events":"https://pith.science/api/pith-number/AW6ZRJ5AFNCCK63HAHTLMANDRU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AW6ZRJ5AFNCCK63HAHTLMANDRU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AW6ZRJ5AFNCCK63HAHTLMANDRU/action/storage_attestation","attest_author":"https://pith.science/pith/AW6ZRJ5AFNCCK63HAHTLMANDRU/action/author_attestation","sign_citation":"https://pith.science/pith/AW6ZRJ5AFNCCK63HAHTLMANDRU/action/citation_signature","submit_replication":"https://pith.science/pith/AW6ZRJ5AFNCCK63HAHTLMANDRU/action/replication_record"}},"created_at":"2026-05-21T02:05:31.963019+00:00","updated_at":"2026-05-21T02:05:31.963019+00:00"}