{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:E57JTNLKTRN4UJNBDMDDICPDVZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9429f75217f0e1f02b867eafb02978cae37e8d6aa3f57e33dc6dde5c17069459","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T01:16:18Z","title_canon_sha256":"cb00c5fed0056a7efb9a04f7377bcdee459016a714c41e6a7f4672c0ebc5b724"},"schema_version":"1.0","source":{"id":"2605.16736","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16736","created_at":"2026-05-20T00:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16736v1","created_at":"2026-05-20T00:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16736","created_at":"2026-05-20T00:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"E57JTNLKTRN4","created_at":"2026-05-20T00:02:39Z"},{"alias_kind":"pith_short_16","alias_value":"E57JTNLKTRN4UJNB","created_at":"2026-05-20T00:02:39Z"},{"alias_kind":"pith_short_8","alias_value":"E57JTNLK","created_at":"2026-05-20T00:02:39Z"}],"graph_snapshots":[{"event_id":"sha256:2a1e4aac45fca0656627e556021947bbaa32c2a2301ac2d09edb1cc301889ccd","target":"graph","created_at":"2026-05-20T00:02:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The resulting method is simple, has the same algorithmic form across model classes, and has at least third-order local truncation error and second-order global error. Experiments on pretrained flow and diffusion models show that CAB improves quality-NFE trade-offs in the low-step regime of 6-20 NFEs."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the rectification step transforms the sampling dynamics of both flow and diffusion models into a common coordinate system where the multistep Adams-Bashforth predictor with correction term can be applied uniformly without introducing instability or order reduction."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CAB accelerates flow and diffusion sampling via rectification to a shared coordinate system followed by a corrected Adams-Bashforth predictor that achieves third-order local truncation error while using no additional NFEs."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CAB unifies flow and diffusion sampling by rectifying dynamics to one coordinate system then applying a corrected multistep predictor that needs no extra model calls."}],"snapshot_sha256":"6d8bd74048c47b4db90fffda380e73883ab3e4b4afd05746608a894dbe6e3dea"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"24031508b6e909224025959dd11d9307c5c91310884a106f30647897613f40d7"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T22:01:19.904601Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T21:51:05.203058Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.338124Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.466479Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16736/integrity.json","findings":[],"snapshot_sha256":"632004d6041db3e6ee0b96ac3ba02e2b26aa2d0fc836d84a53033d0a2fbd4a96","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Flow and diffusion models achieve high-fidelity, high-resolution image synthesis, but often require many function evaluations (NFEs) at sampling time. Existing acceleration methods either require additional training through distillation or rely on training-free high-order solvers, and both can degrade sample quality at low NFE budgets. We propose CAB (Corrected Adams-Bashforth), a training-free sampler that accelerates both flow and diffusion models. CAB first transforms the sampling dynamics to a common rectified coordinate system, and then applies a multistep Adams-Bashforth predictor augmen","authors_text":"Anuska Roy, Pravin Nair","cross_cats":[],"headline":"CAB unifies flow and diffusion sampling by rectifying dynamics to one coordinate system then applying a corrected multistep predictor that needs no extra model calls.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T01:16:18Z","title":"CAB: Accelerating Flow and Diffusion Sampling via Rectification and Corrected Adams-Bashforth"},"references":{"count":82,"internal_anchors":2,"resolved_work":82,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Denoising diffusion probabilistic models , author=. Proc. Advances in neural information processing systems , volume=","work_id":"cbe3c85b-ddc7-450c-88f8-57357a7c4155","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Flow Matching for Generative Modeling , author=. Proc. International Conference on Learning Representations , year=","work_id":"63bd3ecc-3129-45b5-a88e-c5cc5b739a8c","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Video Diffusion Models , author =. Proc. Advances in neural information processing systems , volume=","work_id":"7ec8f3f0-529a-463b-9053-e25f568c7d76","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"IEEE Transactions on Pattern Analysis and Machine Intelligence , volume=","work_id":"5adfb806-8536-4b3f-8b12-95855a5e540d","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications , year =","work_id":"b67969d6-7ae4-4413-8926-c33d2327a0b2","year":2021}],"snapshot_sha256":"e27428deec63559f1c981e2ba18a81869832d2372413302dfaeb7712b0257790"},"source":{"id":"2605.16736","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T21:37:34.430104Z","id":"399aedcf-40e9-4489-8a91-ef9cc5f427d7","model_set":{"reader":"grok-4.3"},"one_line_summary":"CAB accelerates flow and diffusion sampling via rectification to a shared coordinate system followed by a corrected Adams-Bashforth predictor that achieves third-order local truncation error while using no additional NFEs.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"CAB unifies flow and diffusion sampling by rectifying dynamics to one coordinate system then applying a corrected multistep predictor that needs no extra model calls.","strongest_claim":"The resulting method is simple, has the same algorithmic form across model classes, and has at least third-order local truncation error and second-order global error. Experiments on pretrained flow and diffusion models show that CAB improves quality-NFE trade-offs in the low-step regime of 6-20 NFEs.","weakest_assumption":"That the rectification step transforms the sampling dynamics of both flow and diffusion models into a common coordinate system where the multistep Adams-Bashforth predictor with correction term can be applied uniformly without introducing instability or order reduction."}},"verdict_id":"399aedcf-40e9-4489-8a91-ef9cc5f427d7"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bba9a089fc4414284a6cfa78a9975cf9808043c0bf790d06ec4d71fcc2d98c45","target":"record","created_at":"2026-05-20T00:02:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9429f75217f0e1f02b867eafb02978cae37e8d6aa3f57e33dc6dde5c17069459","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T01:16:18Z","title_canon_sha256":"cb00c5fed0056a7efb9a04f7377bcdee459016a714c41e6a7f4672c0ebc5b724"},"schema_version":"1.0","source":{"id":"2605.16736","kind":"arxiv","version":1}},"canonical_sha256":"277e99b56a9c5bca25a11b063409e3ae543f9f24e901c2141e4da52969289c36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"277e99b56a9c5bca25a11b063409e3ae543f9f24e901c2141e4da52969289c36","first_computed_at":"2026-05-20T00:02:39.065073Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:39.065073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xphjz9daEoxdWSmTZdO9CxyawE1O8I4NoPEvWxMhec1Ukisp5uQi8rqL51VSthp/uVHq9PESNQdpHKuZnCDDBw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:39.065927Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16736","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bba9a089fc4414284a6cfa78a9975cf9808043c0bf790d06ec4d71fcc2d98c45","sha256:2a1e4aac45fca0656627e556021947bbaa32c2a2301ac2d09edb1cc301889ccd"],"state_sha256":"b282188b29e9c652389dbdc24953d48c9f7e13d389990825919b0f521ac87774"}