{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CCPG7GIG3XIXCCSCFNH2WYYFFO","short_pith_number":"pith:CCPG7GIG","canonical_record":{"source":{"id":"2505.23346","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T11:10:41Z","cross_cats_sorted":[],"title_canon_sha256":"86e04309be96ac05ae89b20aabc5189ff4150e1a9cdc8e1cef038833554614ae","abstract_canon_sha256":"db24781b1c5fc8b4ebfaa1abe7a6bcb7e7b4b46a018ae17bc2c273449c2b8e89"},"schema_version":"1.0"},"canonical_sha256":"109e6f9906ddd1710a422b4fab63052b96fc88cc4a79b1bdd25f9c2f14f4a0d4","source":{"kind":"arxiv","id":"2505.23346","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23346","created_at":"2026-07-05T11:11:59Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23346v1","created_at":"2026-07-05T11:11:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23346","created_at":"2026-07-05T11:11:59Z"},{"alias_kind":"pith_short_12","alias_value":"CCPG7GIG3XIX","created_at":"2026-07-05T11:11:59Z"},{"alias_kind":"pith_short_16","alias_value":"CCPG7GIG3XIXCCSC","created_at":"2026-07-05T11:11:59Z"},{"alias_kind":"pith_short_8","alias_value":"CCPG7GIG","created_at":"2026-07-05T11:11:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CCPG7GIG3XIXCCSCFNH2WYYFFO","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23346","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T11:10:41Z","cross_cats_sorted":[],"title_canon_sha256":"86e04309be96ac05ae89b20aabc5189ff4150e1a9cdc8e1cef038833554614ae","abstract_canon_sha256":"db24781b1c5fc8b4ebfaa1abe7a6bcb7e7b4b46a018ae17bc2c273449c2b8e89"},"schema_version":"1.0"},"canonical_sha256":"109e6f9906ddd1710a422b4fab63052b96fc88cc4a79b1bdd25f9c2f14f4a0d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:59.978009Z","signature_b64":"QwyESu0ttBXtXHMeccMvmHPIGaQ3yoIvkR8G1QUVbTMuQSTBpWZrJ9iVGuh+KBdQc1yKmxWEbCxUS/FKPt6ODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"109e6f9906ddd1710a422b4fab63052b96fc88cc4a79b1bdd25f9c2f14f4a0d4","last_reissued_at":"2026-07-05T11:11:59.977480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:59.977480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23346","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:11:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IfJZxudB0fd9oSVcuwM2aZ3UiSEzk0Ow/Qjg+zVtLn7gwTBrkRf7uFtqBVkqhg9vme+f0xGuNlRb71W3qzkaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:48:19.095959Z"},"content_sha256":"6bdd87532cfe9a0c935543fe98dcbc21fe9696b704ad6316a0dfe68881a9b7eb","schema_version":"1.0","event_id":"sha256:6bdd87532cfe9a0c935543fe98dcbc21fe9696b704ad6316a0dfe68881a9b7eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CCPG7GIG3XIXCCSCFNH2WYYFFO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Optimal Transport: Model-Aligned Coupling for Flow Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Tongliang Liu, Yexiong Lin, Yu Yao","submitted_at":"2025-05-29T11:10:41Z","abstract_excerpt":"Flow Matching (FM) is an effective framework for training a model to learn a vector field that transports samples from a source distribution to a target distribution. To train the model, early FM methods use random couplings, which often result in crossing paths and lead the model to learn non-straight trajectories that require many integration steps to generate high-quality samples. To address this, recent methods adopt Optimal Transport (OT) to construct couplings by minimizing geometric distances, which helps reduce path crossings. However, we observe that such geometry-based couplings do n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23346","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/2505.23346/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:11:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uY/yU+Ag4xd5b7D9b/JCJmulIvAMJXzgeY0jNLQRmL1w1SUlgwIMAX5Ie9oGywYL9z9JJxE0ZodPgLnSCl0fCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:48:19.096871Z"},"content_sha256":"2c3d1b45eff41db9b3f2c19c34e0fd01ea2242d3167e499ec31d43cdff608286","schema_version":"1.0","event_id":"sha256:2c3d1b45eff41db9b3f2c19c34e0fd01ea2242d3167e499ec31d43cdff608286"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CCPG7GIG3XIXCCSCFNH2WYYFFO/bundle.json","state_url":"https://pith.science/pith/CCPG7GIG3XIXCCSCFNH2WYYFFO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CCPG7GIG3XIXCCSCFNH2WYYFFO/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":"2026-08-04T20:48:19Z","links":{"resolver":"https://pith.science/pith/CCPG7GIG3XIXCCSCFNH2WYYFFO","bundle":"https://pith.science/pith/CCPG7GIG3XIXCCSCFNH2WYYFFO/bundle.json","state":"https://pith.science/pith/CCPG7GIG3XIXCCSCFNH2WYYFFO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CCPG7GIG3XIXCCSCFNH2WYYFFO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CCPG7GIG3XIXCCSCFNH2WYYFFO","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":"db24781b1c5fc8b4ebfaa1abe7a6bcb7e7b4b46a018ae17bc2c273449c2b8e89","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T11:10:41Z","title_canon_sha256":"86e04309be96ac05ae89b20aabc5189ff4150e1a9cdc8e1cef038833554614ae"},"schema_version":"1.0","source":{"id":"2505.23346","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23346","created_at":"2026-07-05T11:11:59Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23346v1","created_at":"2026-07-05T11:11:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23346","created_at":"2026-07-05T11:11:59Z"},{"alias_kind":"pith_short_12","alias_value":"CCPG7GIG3XIX","created_at":"2026-07-05T11:11:59Z"},{"alias_kind":"pith_short_16","alias_value":"CCPG7GIG3XIXCCSC","created_at":"2026-07-05T11:11:59Z"},{"alias_kind":"pith_short_8","alias_value":"CCPG7GIG","created_at":"2026-07-05T11:11:59Z"}],"graph_snapshots":[{"event_id":"sha256:2c3d1b45eff41db9b3f2c19c34e0fd01ea2242d3167e499ec31d43cdff608286","target":"graph","created_at":"2026-07-05T11:11:59Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.23346/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Flow Matching (FM) is an effective framework for training a model to learn a vector field that transports samples from a source distribution to a target distribution. To train the model, early FM methods use random couplings, which often result in crossing paths and lead the model to learn non-straight trajectories that require many integration steps to generate high-quality samples. To address this, recent methods adopt Optimal Transport (OT) to construct couplings by minimizing geometric distances, which helps reduce path crossings. However, we observe that such geometry-based couplings do n","authors_text":"Tongliang Liu, Yexiong Lin, Yu Yao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T11:10:41Z","title":"Beyond Optimal Transport: Model-Aligned Coupling for Flow Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23346","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6bdd87532cfe9a0c935543fe98dcbc21fe9696b704ad6316a0dfe68881a9b7eb","target":"record","created_at":"2026-07-05T11:11:59Z","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":"db24781b1c5fc8b4ebfaa1abe7a6bcb7e7b4b46a018ae17bc2c273449c2b8e89","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T11:10:41Z","title_canon_sha256":"86e04309be96ac05ae89b20aabc5189ff4150e1a9cdc8e1cef038833554614ae"},"schema_version":"1.0","source":{"id":"2505.23346","kind":"arxiv","version":1}},"canonical_sha256":"109e6f9906ddd1710a422b4fab63052b96fc88cc4a79b1bdd25f9c2f14f4a0d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"109e6f9906ddd1710a422b4fab63052b96fc88cc4a79b1bdd25f9c2f14f4a0d4","first_computed_at":"2026-07-05T11:11:59.977480Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:59.977480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QwyESu0ttBXtXHMeccMvmHPIGaQ3yoIvkR8G1QUVbTMuQSTBpWZrJ9iVGuh+KBdQc1yKmxWEbCxUS/FKPt6ODQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:59.978009Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23346","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bdd87532cfe9a0c935543fe98dcbc21fe9696b704ad6316a0dfe68881a9b7eb","sha256:2c3d1b45eff41db9b3f2c19c34e0fd01ea2242d3167e499ec31d43cdff608286"],"state_sha256":"63d417be24864a3c288ca6c0207ac83895760d2ddca68627ba8421d2f5083822"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0S/cU2wBtCPwu2uHT7+AcUwUhq3TDetmmf75C8yHMjI8NYm37iC6l4OX4JgynLbAOUZ7ibaNr8Ul4HHR/RY7DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:48:19.111918Z","bundle_sha256":"9ecabcfcfdc0021c8e9da6cb5314cde528d6ea9517e4efae19343dbbf3151ce2"}}