{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EYWWUTNVBEDFAERRGF24U7HFMS","short_pith_number":"pith:EYWWUTNV","canonical_record":{"source":{"id":"2607.26398","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T02:17:27Z","cross_cats_sorted":[],"title_canon_sha256":"9802f28df765c172f87b45b1a1add2cd0a6ebb4a8875fb06775381fa325ec305","abstract_canon_sha256":"17aa45506304e7ce0ec1429a1994945dbe8521b3078d55e317d7389e17529cd7"},"schema_version":"1.0"},"canonical_sha256":"262d6a4db509065012313175ca7ce5649e01b6ef5ae0573d5c58fc2029da86f0","source":{"kind":"arxiv","id":"2607.26398","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26398","created_at":"2026-07-30T01:18:18Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26398v1","created_at":"2026-07-30T01:18:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26398","created_at":"2026-07-30T01:18:18Z"},{"alias_kind":"pith_short_12","alias_value":"EYWWUTNVBEDF","created_at":"2026-07-30T01:18:18Z"},{"alias_kind":"pith_short_16","alias_value":"EYWWUTNVBEDFAERR","created_at":"2026-07-30T01:18:18Z"},{"alias_kind":"pith_short_8","alias_value":"EYWWUTNV","created_at":"2026-07-30T01:18:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EYWWUTNVBEDFAERRGF24U7HFMS","target":"record","payload":{"canonical_record":{"source":{"id":"2607.26398","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T02:17:27Z","cross_cats_sorted":[],"title_canon_sha256":"9802f28df765c172f87b45b1a1add2cd0a6ebb4a8875fb06775381fa325ec305","abstract_canon_sha256":"17aa45506304e7ce0ec1429a1994945dbe8521b3078d55e317d7389e17529cd7"},"schema_version":"1.0"},"canonical_sha256":"262d6a4db509065012313175ca7ce5649e01b6ef5ae0573d5c58fc2029da86f0","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"262d6a4db509065012313175ca7ce5649e01b6ef5ae0573d5c58fc2029da86f0","last_reissued_at":"2026-07-30T01:18:18.906460Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:18:18.906460Z"},"source_kind":"arxiv","source_id":"2607.26398","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":"2026-07-30T01:18:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k6gkU+9oLaKjf4JHM5G0txcdCytkXc78Dvwz7Y32Ks2BPEukicCZ3WZCIhg4whEtP4pinI0azK32ovxkziffAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T20:55:55.856376Z"},"content_sha256":"6ca75b26b7cae5f16df9d9dc1207ad7d085dc36e892d3565986db4bc6e972e55","schema_version":"1.0","event_id":"sha256:6ca75b26b7cae5f16df9d9dc1207ad7d085dc36e892d3565986db4bc6e972e55"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EYWWUTNVBEDFAERRGF24U7HFMS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Flow Map Learning via Nongradient Vector Flow","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aahlad Puli, Anshuk Uppal, Mark Goldstein, Raghav Singhal, Rajesh Ranganath","submitted_at":"2026-07-29T02:17:27Z","abstract_excerpt":"Diffusion and flow-based models benefit from simple regression losses, but inference incurs significant overhead because sampling requires integration. Consistency models address this by directly learning the flow maps along the ODE trajectory, opening a design space between one-step and many-step approaches. However, existing methods face computational challenges such as requiring model inverses or backpropagation through iterated model calls, and do not always prove that the desired ODE flow map is a solution to the loss. We introduce SGFlow, an approach for learning flow maps that bypasses "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26398","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/2607.26398/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":"2026-07-30T01:18:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KhLxRcDkNADtoTZBLjT0a5Aw9xlJYQ4j3ZKFqekWNA10hkezaa+XoLW9jS2pGxmFxDDc+9Oq/1L8kVbBg1tCCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T20:55:55.856908Z"},"content_sha256":"463956e80b69158155cb5bfe2e0791d5652041a528355ef272966cbc4a4eb853","schema_version":"1.0","event_id":"sha256:463956e80b69158155cb5bfe2e0791d5652041a528355ef272966cbc4a4eb853"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EYWWUTNVBEDFAERRGF24U7HFMS/bundle.json","state_url":"https://pith.science/pith/EYWWUTNVBEDFAERRGF24U7HFMS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EYWWUTNVBEDFAERRGF24U7HFMS/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":"2026-08-01T20:55:55Z","links":{"resolver":"https://pith.science/pith/EYWWUTNVBEDFAERRGF24U7HFMS","bundle":"https://pith.science/pith/EYWWUTNVBEDFAERRGF24U7HFMS/bundle.json","state":"https://pith.science/pith/EYWWUTNVBEDFAERRGF24U7HFMS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EYWWUTNVBEDFAERRGF24U7HFMS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EYWWUTNVBEDFAERRGF24U7HFMS","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":"17aa45506304e7ce0ec1429a1994945dbe8521b3078d55e317d7389e17529cd7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T02:17:27Z","title_canon_sha256":"9802f28df765c172f87b45b1a1add2cd0a6ebb4a8875fb06775381fa325ec305"},"schema_version":"1.0","source":{"id":"2607.26398","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26398","created_at":"2026-07-30T01:18:18Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26398v1","created_at":"2026-07-30T01:18:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26398","created_at":"2026-07-30T01:18:18Z"},{"alias_kind":"pith_short_12","alias_value":"EYWWUTNVBEDF","created_at":"2026-07-30T01:18:18Z"},{"alias_kind":"pith_short_16","alias_value":"EYWWUTNVBEDFAERR","created_at":"2026-07-30T01:18:18Z"},{"alias_kind":"pith_short_8","alias_value":"EYWWUTNV","created_at":"2026-07-30T01:18:18Z"}],"graph_snapshots":[{"event_id":"sha256:463956e80b69158155cb5bfe2e0791d5652041a528355ef272966cbc4a4eb853","target":"graph","created_at":"2026-07-30T01:18:18Z","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/2607.26398/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion and flow-based models benefit from simple regression losses, but inference incurs significant overhead because sampling requires integration. Consistency models address this by directly learning the flow maps along the ODE trajectory, opening a design space between one-step and many-step approaches. However, existing methods face computational challenges such as requiring model inverses or backpropagation through iterated model calls, and do not always prove that the desired ODE flow map is a solution to the loss. We introduce SGFlow, an approach for learning flow maps that bypasses ","authors_text":"Aahlad Puli, Anshuk Uppal, Mark Goldstein, Raghav Singhal, Rajesh Ranganath","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T02:17:27Z","title":"Flow Map Learning via Nongradient Vector Flow"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26398","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":"sha256:6ca75b26b7cae5f16df9d9dc1207ad7d085dc36e892d3565986db4bc6e972e55","target":"record","created_at":"2026-07-30T01:18:18Z","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":"17aa45506304e7ce0ec1429a1994945dbe8521b3078d55e317d7389e17529cd7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T02:17:27Z","title_canon_sha256":"9802f28df765c172f87b45b1a1add2cd0a6ebb4a8875fb06775381fa325ec305"},"schema_version":"1.0","source":{"id":"2607.26398","kind":"arxiv","version":1}},"canonical_sha256":"262d6a4db509065012313175ca7ce5649e01b6ef5ae0573d5c58fc2029da86f0","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"262d6a4db509065012313175ca7ce5649e01b6ef5ae0573d5c58fc2029da86f0","first_computed_at":"2026-07-30T01:18:18.906460Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:18:18.906460Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26398","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ca75b26b7cae5f16df9d9dc1207ad7d085dc36e892d3565986db4bc6e972e55","sha256:463956e80b69158155cb5bfe2e0791d5652041a528355ef272966cbc4a4eb853"],"state_sha256":"52971b882bbce963cc1d6c18c7cdcde64719285e3b0bec2ce1b48b92925d89d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vjPefnkMig0KEEOSLQvMGl6Dsg4xdz77KuN8JpjaA1ih924seqFztBu811EfBPnTKEclOyhvuCD2WA74lyZbCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T20:55:55.861626Z","bundle_sha256":"2d46383f2455e097bdc6e52e1725e2ed084b3b56cc7c5b87b5f2e755ef3e4453"}}