{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BPZB3OHIKGIYXMJGHX7QFBAFMV","short_pith_number":"pith:BPZB3OHI","canonical_record":{"source":{"id":"2601.21892","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-29T15:49:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c45fbbc391060580efa72447877bc0a05d7db1f3dd9dfd57f8b10877e43ac96c","abstract_canon_sha256":"5dbdb68d2c990ee0c961abb609095cfbceee3d44e1890a34583508fb81552a57"},"schema_version":"1.0"},"canonical_sha256":"0bf21db8e851918bb1263dff0284056554661e20552fa154f622207d8516802a","source":{"kind":"arxiv","id":"2601.21892","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21892","created_at":"2026-05-18T03:09:24Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21892v2","created_at":"2026-05-18T03:09:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21892","created_at":"2026-05-18T03:09:24Z"},{"alias_kind":"pith_short_12","alias_value":"BPZB3OHIKGIY","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"BPZB3OHIKGIYXMJG","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"BPZB3OHI","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BPZB3OHIKGIYXMJGHX7QFBAFMV","target":"record","payload":{"canonical_record":{"source":{"id":"2601.21892","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-29T15:49:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c45fbbc391060580efa72447877bc0a05d7db1f3dd9dfd57f8b10877e43ac96c","abstract_canon_sha256":"5dbdb68d2c990ee0c961abb609095cfbceee3d44e1890a34583508fb81552a57"},"schema_version":"1.0"},"canonical_sha256":"0bf21db8e851918bb1263dff0284056554661e20552fa154f622207d8516802a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:24.099959Z","signature_b64":"7Sa5o1a9puJAsbI653LKMH5JohmT8oU0tjhlfHLn8FvXzGqv4dbbh+Mn2wZnfBk0azeYg3MxTBidqgtJhb4+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bf21db8e851918bb1263dff0284056554661e20552fa154f622207d8516802a","last_reissued_at":"2026-05-18T03:09:24.099324Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:24.099324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.21892","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/6/NQOA5Qr/FZ2VsQmgAlD0haiMhANxp4juG2LOUF6yVoGpt06mF/ZYuKWcbRumELp9kx3oG0YVNFsn+qWlABg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T13:00:11.637028Z"},"content_sha256":"0b60a43300b3ea47cea34402c23d12ccdf8203cc1f60c0a953e4dd4cda832102","schema_version":"1.0","event_id":"sha256:0b60a43300b3ea47cea34402c23d12ccdf8203cc1f60c0a953e4dd4cda832102"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BPZB3OHIKGIYXMJGHX7QFBAFMV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Classifier-Free Guidance of Flow Matching via Manifold Projection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Reformulating classifier-free guidance in flow matching as manifold-constrained homotopy optimization reduces sensitivity to guidance scales.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chao Wang, Haixia Liu, Jian-Feng Cai, Zhengyi Su","submitted_at":"2026-01-29T15:49:31Z","abstract_excerpt":"Classifier-free guidance (CFG) is a widely used technique for controllable generation in diffusion and flow-based models. Despite its empirical success, CFG relies on a heuristic linear extrapolation that is often sensitive to the guidance scale. In this work, we provide a principled interpretation of CFG through the lens of optimization. We demonstrate that the velocity field in flow matching corresponds to the gradient of a sequence of smoothed distance functions, which guides latent variables toward the scaled target image set. This perspective reveals that the standard CFG formulation is a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We reformulate the CFG sampling as a homotopy optimization with a manifold constraint. This formulation necessitates a manifold projection step, which we implement via an incremental gradient descent scheme during sampling.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the velocity field in flow matching exactly corresponds to the gradient of a sequence of smoothed distance functions guiding latent variables toward the scaled target image set, making standard CFG merely an approximation whose gap controls sensitivity.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Reformulates CFG sampling in flow matching as homotopy optimization with manifold projection via incremental gradient descent and Anderson acceleration, yielding better fidelity and robustness without retraining.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Reformulating classifier-free guidance in flow matching as manifold-constrained homotopy optimization reduces sensitivity to guidance scales.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"218ada2be6aab54ce68536ae4ac14a9b30af0864b9230229b25bb89e9c662cde"},"source":{"id":"2601.21892","kind":"arxiv","version":2},"verdict":{"id":"2ec256b3-fd97-4606-9ddb-05647fedb311","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T09:40:42.595531Z","strongest_claim":"We reformulate the CFG sampling as a homotopy optimization with a manifold constraint. This formulation necessitates a manifold projection step, which we implement via an incremental gradient descent scheme during sampling.","one_line_summary":"Reformulates CFG sampling in flow matching as homotopy optimization with manifold projection via incremental gradient descent and Anderson acceleration, yielding better fidelity and robustness without retraining.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the velocity field in flow matching exactly corresponds to the gradient of a sequence of smoothed distance functions guiding latent variables toward the scaled target image set, making standard CFG merely an approximation whose gap controls sensitivity.","pith_extraction_headline":"Reformulating classifier-free guidance in flow matching as manifold-constrained homotopy optimization reduces sensitivity to guidance scales."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b7b7a2ff27ae5244c865e08bb4baf6e4acb4c71758fd46b10c733d768075f22b"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"2ec256b3-fd97-4606-9ddb-05647fedb311"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e0fbzwZfWyFbWB0ks123zktFZjCdwdWgKoK/yDhvodLjBm8IEdawNkPgtKMlXl3TZKZqlS4+87SlkN7Jmc2VCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T13:00:11.637980Z"},"content_sha256":"8eb6b0572313dcc2e4970d6a139b0260ce4a2395afeb96402b2de9ddb06ff888","schema_version":"1.0","event_id":"sha256:8eb6b0572313dcc2e4970d6a139b0260ce4a2395afeb96402b2de9ddb06ff888"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BPZB3OHIKGIYXMJGHX7QFBAFMV/bundle.json","state_url":"https://pith.science/pith/BPZB3OHIKGIYXMJGHX7QFBAFMV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BPZB3OHIKGIYXMJGHX7QFBAFMV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T13:00:11Z","links":{"resolver":"https://pith.science/pith/BPZB3OHIKGIYXMJGHX7QFBAFMV","bundle":"https://pith.science/pith/BPZB3OHIKGIYXMJGHX7QFBAFMV/bundle.json","state":"https://pith.science/pith/BPZB3OHIKGIYXMJGHX7QFBAFMV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BPZB3OHIKGIYXMJGHX7QFBAFMV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BPZB3OHIKGIYXMJGHX7QFBAFMV","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":"5dbdb68d2c990ee0c961abb609095cfbceee3d44e1890a34583508fb81552a57","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-29T15:49:31Z","title_canon_sha256":"c45fbbc391060580efa72447877bc0a05d7db1f3dd9dfd57f8b10877e43ac96c"},"schema_version":"1.0","source":{"id":"2601.21892","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21892","created_at":"2026-05-18T03:09:24Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21892v2","created_at":"2026-05-18T03:09:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21892","created_at":"2026-05-18T03:09:24Z"},{"alias_kind":"pith_short_12","alias_value":"BPZB3OHIKGIY","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"BPZB3OHIKGIYXMJG","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"BPZB3OHI","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:8eb6b0572313dcc2e4970d6a139b0260ce4a2395afeb96402b2de9ddb06ff888","target":"graph","created_at":"2026-05-18T03:09:24Z","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":"We reformulate the CFG sampling as a homotopy optimization with a manifold constraint. This formulation necessitates a manifold projection step, which we implement via an incremental gradient descent scheme during sampling."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the velocity field in flow matching exactly corresponds to the gradient of a sequence of smoothed distance functions guiding latent variables toward the scaled target image set, making standard CFG merely an approximation whose gap controls sensitivity."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Reformulates CFG sampling in flow matching as homotopy optimization with manifold projection via incremental gradient descent and Anderson acceleration, yielding better fidelity and robustness without retraining."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Reformulating classifier-free guidance in flow matching as manifold-constrained homotopy optimization reduces sensitivity to guidance scales."}],"snapshot_sha256":"218ada2be6aab54ce68536ae4ac14a9b30af0864b9230229b25bb89e9c662cde"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b7b7a2ff27ae5244c865e08bb4baf6e4acb4c71758fd46b10c733d768075f22b"},"paper":{"abstract_excerpt":"Classifier-free guidance (CFG) is a widely used technique for controllable generation in diffusion and flow-based models. Despite its empirical success, CFG relies on a heuristic linear extrapolation that is often sensitive to the guidance scale. In this work, we provide a principled interpretation of CFG through the lens of optimization. We demonstrate that the velocity field in flow matching corresponds to the gradient of a sequence of smoothed distance functions, which guides latent variables toward the scaled target image set. This perspective reveals that the standard CFG formulation is a","authors_text":"Chao Wang, Haixia Liu, Jian-Feng Cai, Zhengyi Su","cross_cats":["cs.AI"],"headline":"Reformulating classifier-free guidance in flow matching as manifold-constrained homotopy optimization reduces sensitivity to guidance scales.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-29T15:49:31Z","title":"Improving Classifier-Free Guidance of Flow Matching via Manifold Projection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21892","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T09:40:42.595531Z","id":"2ec256b3-fd97-4606-9ddb-05647fedb311","model_set":{"reader":"grok-4.3"},"one_line_summary":"Reformulates CFG sampling in flow matching as homotopy optimization with manifold projection via incremental gradient descent and Anderson acceleration, yielding better fidelity and robustness without retraining.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Reformulating classifier-free guidance in flow matching as manifold-constrained homotopy optimization reduces sensitivity to guidance scales.","strongest_claim":"We reformulate the CFG sampling as a homotopy optimization with a manifold constraint. This formulation necessitates a manifold projection step, which we implement via an incremental gradient descent scheme during sampling.","weakest_assumption":"That the velocity field in flow matching exactly corresponds to the gradient of a sequence of smoothed distance functions guiding latent variables toward the scaled target image set, making standard CFG merely an approximation whose gap controls sensitivity."}},"verdict_id":"2ec256b3-fd97-4606-9ddb-05647fedb311"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0b60a43300b3ea47cea34402c23d12ccdf8203cc1f60c0a953e4dd4cda832102","target":"record","created_at":"2026-05-18T03:09:24Z","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":"5dbdb68d2c990ee0c961abb609095cfbceee3d44e1890a34583508fb81552a57","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-29T15:49:31Z","title_canon_sha256":"c45fbbc391060580efa72447877bc0a05d7db1f3dd9dfd57f8b10877e43ac96c"},"schema_version":"1.0","source":{"id":"2601.21892","kind":"arxiv","version":2}},"canonical_sha256":"0bf21db8e851918bb1263dff0284056554661e20552fa154f622207d8516802a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bf21db8e851918bb1263dff0284056554661e20552fa154f622207d8516802a","first_computed_at":"2026-05-18T03:09:24.099324Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:24.099324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7Sa5o1a9puJAsbI653LKMH5JohmT8oU0tjhlfHLn8FvXzGqv4dbbh+Mn2wZnfBk0azeYg3MxTBidqgtJhb4+BA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:24.099959Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.21892","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b60a43300b3ea47cea34402c23d12ccdf8203cc1f60c0a953e4dd4cda832102","sha256:8eb6b0572313dcc2e4970d6a139b0260ce4a2395afeb96402b2de9ddb06ff888"],"state_sha256":"1a7d3dbd93ac956c180a5d0dbfe1adc7a39895aa31500052fbfb859bc48d6eb2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UDjJDuVPKFni4x6gAPpK/rnGGZ8MfMMEd+NHdtaTX9po9Ul4Cto2o5utlsRC1NdHQgmhbJK/fW5GDNopJmC9Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T13:00:11.642834Z","bundle_sha256":"914084bc08e24903da55578e2644423e652b3e7c1388e9215016d1f95d9eb937"}}