{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YATNZIXEWI4UYFG25RUXC27BER","short_pith_number":"pith:YATNZIXE","schema_version":"1.0","canonical_sha256":"c026dca2e4b2394c14daec69716be1245598ba3158943ad6e1aba169a9ba0031","source":{"kind":"arxiv","id":"2504.21487","version":2},"attestation_state":"computed","paper":{"title":"DGSolver: Diffusion Generalist Solver with Universal Posterior Sampling for Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Du, Di Wang, Haonan Guo, Hebaixu Wang, Jiayi Ma, Jing Zhang","submitted_at":"2025-04-30T10:12:48Z","abstract_excerpt":"Diffusion models have achieved remarkable progress in universal image restoration. While existing methods speed up inference by reducing sampling steps, substantial step intervals often introduce cumulative errors. Moreover, they struggle to balance the commonality of degradation representations and restoration quality. To address these challenges, we introduce \\textbf{DGSolver}, a diffusion generalist solver with universal posterior sampling. We first derive the exact ordinary differential equations for generalist diffusion models and tailor high-order solvers with a queue-based accelerated s"},"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":"2504.21487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-30T10:12:48Z","cross_cats_sorted":[],"title_canon_sha256":"bedd1f699a5b77a57e9a6f6e17c084475e8d89e51de09685904fbc330df1be09","abstract_canon_sha256":"a1ccbfeb6c98a397031eb2ba8c28b3efd3d9eb3299ffa449c5c159fb11f9c341"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:07.207281Z","signature_b64":"nMGv93TpCTQFk58NN66385fWBMH5lH+yYLJAbZB/QMrsU6Dc0rces8a7ArrgRxHstxtgE+1clhpBnvWMkywlDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c026dca2e4b2394c14daec69716be1245598ba3158943ad6e1aba169a9ba0031","last_reissued_at":"2026-07-05T11:00:07.206722Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:07.206722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DGSolver: Diffusion Generalist Solver with Universal Posterior Sampling for Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Du, Di Wang, Haonan Guo, Hebaixu Wang, Jiayi Ma, Jing Zhang","submitted_at":"2025-04-30T10:12:48Z","abstract_excerpt":"Diffusion models have achieved remarkable progress in universal image restoration. While existing methods speed up inference by reducing sampling steps, substantial step intervals often introduce cumulative errors. Moreover, they struggle to balance the commonality of degradation representations and restoration quality. To address these challenges, we introduce \\textbf{DGSolver}, a diffusion generalist solver with universal posterior sampling. We first derive the exact ordinary differential equations for generalist diffusion models and tailor high-order solvers with a queue-based accelerated s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21487","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/2504.21487/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":"2504.21487","created_at":"2026-07-05T11:00:07.206788+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.21487v2","created_at":"2026-07-05T11:00:07.206788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21487","created_at":"2026-07-05T11:00:07.206788+00:00"},{"alias_kind":"pith_short_12","alias_value":"YATNZIXEWI4U","created_at":"2026-07-05T11:00:07.206788+00:00"},{"alias_kind":"pith_short_16","alias_value":"YATNZIXEWI4UYFG2","created_at":"2026-07-05T11:00:07.206788+00:00"},{"alias_kind":"pith_short_8","alias_value":"YATNZIXE","created_at":"2026-07-05T11:00:07.206788+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01048","citing_title":"Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translation","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2510.23116","citing_title":"Residual Diffusion Bridge Model for Image Restoration","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YATNZIXEWI4UYFG25RUXC27BER","json":"https://pith.science/pith/YATNZIXEWI4UYFG25RUXC27BER.json","graph_json":"https://pith.science/api/pith-number/YATNZIXEWI4UYFG25RUXC27BER/graph.json","events_json":"https://pith.science/api/pith-number/YATNZIXEWI4UYFG25RUXC27BER/events.json","paper":"https://pith.science/paper/YATNZIXE"},"agent_actions":{"view_html":"https://pith.science/pith/YATNZIXEWI4UYFG25RUXC27BER","download_json":"https://pith.science/pith/YATNZIXEWI4UYFG25RUXC27BER.json","view_paper":"https://pith.science/paper/YATNZIXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.21487&json=true","fetch_graph":"https://pith.science/api/pith-number/YATNZIXEWI4UYFG25RUXC27BER/graph.json","fetch_events":"https://pith.science/api/pith-number/YATNZIXEWI4UYFG25RUXC27BER/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YATNZIXEWI4UYFG25RUXC27BER/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YATNZIXEWI4UYFG25RUXC27BER/action/storage_attestation","attest_author":"https://pith.science/pith/YATNZIXEWI4UYFG25RUXC27BER/action/author_attestation","sign_citation":"https://pith.science/pith/YATNZIXEWI4UYFG25RUXC27BER/action/citation_signature","submit_replication":"https://pith.science/pith/YATNZIXEWI4UYFG25RUXC27BER/action/replication_record"}},"created_at":"2026-07-05T11:00:07.206788+00:00","updated_at":"2026-07-05T11:00:07.206788+00:00"}