{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RMC646UYLLESYX5BBVTBXEXCW4","short_pith_number":"pith:RMC646UY","schema_version":"1.0","canonical_sha256":"8b05ee7a985ac92c5fa10d661b92e2b7376d8b411cb42f51a34b1c70c91fd4c8","source":{"kind":"arxiv","id":"2410.07273","version":1},"attestation_state":"computed","paper":{"title":"BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chao Zhang, Chen Li, Fangyikang Wang, Hanbin Zhao, Hubery Yin, Hui Qian, Huminhao Zhu, Yuejiang Dong","submitted_at":"2024-10-09T06:32:26Z","abstract_excerpt":"The inversion of diffusion model sampling, which aims to find the corresponding initial noise of a sample, plays a critical role in various tasks. Recently, several heuristic exact inversion samplers have been proposed to address the inexact inversion issue in a training-free manner. However, the theoretical properties of these heuristic samplers remain unknown and they often exhibit mediocre sampling quality. In this paper, we introduce a generic formulation, \\emph{Bidirectional Explicit Linear Multi-step} (BELM) samplers, of the exact inversion samplers, which includes all previously propose"},"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":"2410.07273","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T06:32:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"548f082134a67c2305b644b4bd2716f2b84e27442d15da2b41a7fbaa1a48234c","abstract_canon_sha256":"f954e2244ee9615af2d5dcec17493cabc545eb8b91ce6dfaff2430bbbf8bd73c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:33.870197Z","signature_b64":"fKO+RCU9lQsISlVbaWMkBzKUOE5Ws0CbLf/3vODWJrQ4w9NHLugb5zjs0vX+R//vOOmlIL3v0Kyt+trKMogxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b05ee7a985ac92c5fa10d661b92e2b7376d8b411cb42f51a34b1c70c91fd4c8","last_reissued_at":"2026-07-05T09:18:33.869708Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:33.869708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chao Zhang, Chen Li, Fangyikang Wang, Hanbin Zhao, Hubery Yin, Hui Qian, Huminhao Zhu, Yuejiang Dong","submitted_at":"2024-10-09T06:32:26Z","abstract_excerpt":"The inversion of diffusion model sampling, which aims to find the corresponding initial noise of a sample, plays a critical role in various tasks. Recently, several heuristic exact inversion samplers have been proposed to address the inexact inversion issue in a training-free manner. However, the theoretical properties of these heuristic samplers remain unknown and they often exhibit mediocre sampling quality. In this paper, we introduce a generic formulation, \\emph{Bidirectional Explicit Linear Multi-step} (BELM) samplers, of the exact inversion samplers, which includes all previously propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07273","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/2410.07273/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":"2410.07273","created_at":"2026-07-05T09:18:33.869769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07273v1","created_at":"2026-07-05T09:18:33.869769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07273","created_at":"2026-07-05T09:18:33.869769+00:00"},{"alias_kind":"pith_short_12","alias_value":"RMC646UYLLES","created_at":"2026-07-05T09:18:33.869769+00:00"},{"alias_kind":"pith_short_16","alias_value":"RMC646UYLLESYX5B","created_at":"2026-07-05T09:18:33.869769+00:00"},{"alias_kind":"pith_short_8","alias_value":"RMC646UY","created_at":"2026-07-05T09:18:33.869769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24222","citing_title":"Unleashing High-Quality Image Generation in Diffusion Sampling Using Second-Order Levenberg-Marquardt-Langevin","ref_index":82,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RMC646UYLLESYX5BBVTBXEXCW4","json":"https://pith.science/pith/RMC646UYLLESYX5BBVTBXEXCW4.json","graph_json":"https://pith.science/api/pith-number/RMC646UYLLESYX5BBVTBXEXCW4/graph.json","events_json":"https://pith.science/api/pith-number/RMC646UYLLESYX5BBVTBXEXCW4/events.json","paper":"https://pith.science/paper/RMC646UY"},"agent_actions":{"view_html":"https://pith.science/pith/RMC646UYLLESYX5BBVTBXEXCW4","download_json":"https://pith.science/pith/RMC646UYLLESYX5BBVTBXEXCW4.json","view_paper":"https://pith.science/paper/RMC646UY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07273&json=true","fetch_graph":"https://pith.science/api/pith-number/RMC646UYLLESYX5BBVTBXEXCW4/graph.json","fetch_events":"https://pith.science/api/pith-number/RMC646UYLLESYX5BBVTBXEXCW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RMC646UYLLESYX5BBVTBXEXCW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RMC646UYLLESYX5BBVTBXEXCW4/action/storage_attestation","attest_author":"https://pith.science/pith/RMC646UYLLESYX5BBVTBXEXCW4/action/author_attestation","sign_citation":"https://pith.science/pith/RMC646UYLLESYX5BBVTBXEXCW4/action/citation_signature","submit_replication":"https://pith.science/pith/RMC646UYLLESYX5BBVTBXEXCW4/action/replication_record"}},"created_at":"2026-07-05T09:18:33.869769+00:00","updated_at":"2026-07-05T09:18:33.869769+00:00"}