{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WRCBW2R3CAS7NDG2HEOLBFA7EG","short_pith_number":"pith:WRCBW2R3","schema_version":"1.0","canonical_sha256":"b4441b6a3b1025f68cda391cb0941f21a24f0f0b0ed9c9c12285a0ec0ac55390","source":{"kind":"arxiv","id":"2403.18035","version":4},"attestation_state":"computed","paper":{"title":"Bidirectional Consistency Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jiajun He, Liangchen Li","submitted_at":"2024-03-26T18:40:36Z","abstract_excerpt":"Diffusion models (DMs) are capable of generating remarkably high-quality samples by iteratively denoising a random vector, a process that corresponds to moving along the probability flow ordinary differential equation (PF ODE). Interestingly, DMs can also invert an input image to noise by moving backward along the PF ODE, a key operation for downstream tasks such as interpolation and image editing. However, the iterative nature of this process restricts its speed, hindering its broader application. Recently, Consistency Models (CMs) have emerged to address this challenge by approximating the i"},"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":"2403.18035","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-26T18:40:36Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4dba303d4f2d574c22a849d03b23fa5bf6fbed8f2539edf1959b01c116bfc8af","abstract_canon_sha256":"6dd6bf0d5e424bd9863da882ffcfd77ca52a6573f47dad7633d99cd5754143df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:58.320939Z","signature_b64":"4lhPJKrsUeJLfOAdWM1ZNUHFe1njRrxNs0kQ0hxTJbwjGe+KVo3/Jtatl0d4jPEcsPBp1Xca7yMBl5DkHSF5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4441b6a3b1025f68cda391cb0941f21a24f0f0b0ed9c9c12285a0ec0ac55390","last_reissued_at":"2026-07-05T10:21:58.320432Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:58.320432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bidirectional Consistency Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jiajun He, Liangchen Li","submitted_at":"2024-03-26T18:40:36Z","abstract_excerpt":"Diffusion models (DMs) are capable of generating remarkably high-quality samples by iteratively denoising a random vector, a process that corresponds to moving along the probability flow ordinary differential equation (PF ODE). Interestingly, DMs can also invert an input image to noise by moving backward along the PF ODE, a key operation for downstream tasks such as interpolation and image editing. However, the iterative nature of this process restricts its speed, hindering its broader application. Recently, Consistency Models (CMs) have emerged to address this challenge by approximating the i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18035","kind":"arxiv","version":4},"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/2403.18035/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":"2403.18035","created_at":"2026-07-05T10:21:58.320498+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.18035v4","created_at":"2026-07-05T10:21:58.320498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18035","created_at":"2026-07-05T10:21:58.320498+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRCBW2R3CAS7","created_at":"2026-07-05T10:21:58.320498+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRCBW2R3CAS7NDG2","created_at":"2026-07-05T10:21:58.320498+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRCBW2R3","created_at":"2026-07-05T10:21:58.320498+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27147","citing_title":"How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27147","citing_title":"How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27147","citing_title":"How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WRCBW2R3CAS7NDG2HEOLBFA7EG","json":"https://pith.science/pith/WRCBW2R3CAS7NDG2HEOLBFA7EG.json","graph_json":"https://pith.science/api/pith-number/WRCBW2R3CAS7NDG2HEOLBFA7EG/graph.json","events_json":"https://pith.science/api/pith-number/WRCBW2R3CAS7NDG2HEOLBFA7EG/events.json","paper":"https://pith.science/paper/WRCBW2R3"},"agent_actions":{"view_html":"https://pith.science/pith/WRCBW2R3CAS7NDG2HEOLBFA7EG","download_json":"https://pith.science/pith/WRCBW2R3CAS7NDG2HEOLBFA7EG.json","view_paper":"https://pith.science/paper/WRCBW2R3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.18035&json=true","fetch_graph":"https://pith.science/api/pith-number/WRCBW2R3CAS7NDG2HEOLBFA7EG/graph.json","fetch_events":"https://pith.science/api/pith-number/WRCBW2R3CAS7NDG2HEOLBFA7EG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRCBW2R3CAS7NDG2HEOLBFA7EG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRCBW2R3CAS7NDG2HEOLBFA7EG/action/storage_attestation","attest_author":"https://pith.science/pith/WRCBW2R3CAS7NDG2HEOLBFA7EG/action/author_attestation","sign_citation":"https://pith.science/pith/WRCBW2R3CAS7NDG2HEOLBFA7EG/action/citation_signature","submit_replication":"https://pith.science/pith/WRCBW2R3CAS7NDG2HEOLBFA7EG/action/replication_record"}},"created_at":"2026-07-05T10:21:58.320498+00:00","updated_at":"2026-07-05T10:21:58.320498+00:00"}