{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GFIPRDCOFLW3BWUHLXT4JPN23L","short_pith_number":"pith:GFIPRDCO","canonical_record":{"source":{"id":"2505.20221","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T17:03:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b58ec89c2786388a0ec1d3a4f8093a0d4600e8248eccfdb52947e02373d32a01","abstract_canon_sha256":"45ad67ed22f65696ab102d619083111756834e64101052d7713a780775486dfe"},"schema_version":"1.0"},"canonical_sha256":"3150f88c4e2aedb0da875de7c4bdbadae5ca6c6834492c219284185b5e98071e","source":{"kind":"arxiv","id":"2505.20221","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20221","created_at":"2026-07-05T11:09:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20221v1","created_at":"2026-07-05T11:09:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20221","created_at":"2026-07-05T11:09:54Z"},{"alias_kind":"pith_short_12","alias_value":"GFIPRDCOFLW3","created_at":"2026-07-05T11:09:54Z"},{"alias_kind":"pith_short_16","alias_value":"GFIPRDCOFLW3BWUH","created_at":"2026-07-05T11:09:54Z"},{"alias_kind":"pith_short_8","alias_value":"GFIPRDCO","created_at":"2026-07-05T11:09:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GFIPRDCOFLW3BWUHLXT4JPN23L","target":"record","payload":{"canonical_record":{"source":{"id":"2505.20221","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T17:03:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b58ec89c2786388a0ec1d3a4f8093a0d4600e8248eccfdb52947e02373d32a01","abstract_canon_sha256":"45ad67ed22f65696ab102d619083111756834e64101052d7713a780775486dfe"},"schema_version":"1.0"},"canonical_sha256":"3150f88c4e2aedb0da875de7c4bdbadae5ca6c6834492c219284185b5e98071e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:54.419241Z","signature_b64":"eTI+FuGPfNGlJMbDVgs1E0s2+NV7H6Hkx1i51pCnqrKh6jcyPOkRRkGpba42L+3uC7Lkq7ybRenwP+C6tvWUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3150f88c4e2aedb0da875de7c4bdbadae5ca6c6834492c219284185b5e98071e","last_reissued_at":"2026-07-05T11:09:54.418716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:54.418716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.20221","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":"2026-07-05T11:09:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6sMQZC5El1eOmVhnBwtAM8aOkW3Xl7I9LOjoUAw67dalVMgwRZ3eytqh3j5oiV4qe0vImZ4NXRdz844qJA4HBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:53:14.660506Z"},"content_sha256":"8d1d072ec54f88d2b2868f7b5672e4bccd3e11790ccd66cc81a34db873e2be96","schema_version":"1.0","event_id":"sha256:8d1d072ec54f88d2b2868f7b5672e4bccd3e11790ccd66cc81a34db873e2be96"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GFIPRDCOFLW3BWUHLXT4JPN23L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gradient Flow Matching for Learning Update Dynamics in Neural Network Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jianxi Gao, Xiao Shou, Yanna Ding","submitted_at":"2025-05-26T17:03:22Z","abstract_excerpt":"Training deep neural networks remains computationally intensive due to the itera2 tive nature of gradient-based optimization. We propose Gradient Flow Matching (GFM), a continuous-time modeling framework that treats neural network training as a dynamical system governed by learned optimizer-aware vector fields. By leveraging conditional flow matching, GFM captures the underlying update rules of optimizers such as SGD, Adam, and RMSprop, enabling smooth extrapolation of weight trajectories toward convergence. Unlike black-box sequence models, GFM incorporates structural knowledge of gradient-ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20221","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/2505.20221/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":"2026-07-05T11:09:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9bDTCxuLpAjWD+ibAwDpgyUOZZhaw+Q5Vl4/bTjlFwo56sTSeW5IqRv7sfc0Lcejtb+Vu2yHXlCcbLj89KlWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:53:14.661034Z"},"content_sha256":"655da625fc79f0f1c6d8f5f363952ff425ac0c573e3751efbb4b360d7f76d52e","schema_version":"1.0","event_id":"sha256:655da625fc79f0f1c6d8f5f363952ff425ac0c573e3751efbb4b360d7f76d52e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GFIPRDCOFLW3BWUHLXT4JPN23L/bundle.json","state_url":"https://pith.science/pith/GFIPRDCOFLW3BWUHLXT4JPN23L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GFIPRDCOFLW3BWUHLXT4JPN23L/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":"2026-08-08T12:53:14Z","links":{"resolver":"https://pith.science/pith/GFIPRDCOFLW3BWUHLXT4JPN23L","bundle":"https://pith.science/pith/GFIPRDCOFLW3BWUHLXT4JPN23L/bundle.json","state":"https://pith.science/pith/GFIPRDCOFLW3BWUHLXT4JPN23L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GFIPRDCOFLW3BWUHLXT4JPN23L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GFIPRDCOFLW3BWUHLXT4JPN23L","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":"45ad67ed22f65696ab102d619083111756834e64101052d7713a780775486dfe","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T17:03:22Z","title_canon_sha256":"b58ec89c2786388a0ec1d3a4f8093a0d4600e8248eccfdb52947e02373d32a01"},"schema_version":"1.0","source":{"id":"2505.20221","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20221","created_at":"2026-07-05T11:09:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20221v1","created_at":"2026-07-05T11:09:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20221","created_at":"2026-07-05T11:09:54Z"},{"alias_kind":"pith_short_12","alias_value":"GFIPRDCOFLW3","created_at":"2026-07-05T11:09:54Z"},{"alias_kind":"pith_short_16","alias_value":"GFIPRDCOFLW3BWUH","created_at":"2026-07-05T11:09:54Z"},{"alias_kind":"pith_short_8","alias_value":"GFIPRDCO","created_at":"2026-07-05T11:09:54Z"}],"graph_snapshots":[{"event_id":"sha256:655da625fc79f0f1c6d8f5f363952ff425ac0c573e3751efbb4b360d7f76d52e","target":"graph","created_at":"2026-07-05T11:09:54Z","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/2505.20221/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training deep neural networks remains computationally intensive due to the itera2 tive nature of gradient-based optimization. We propose Gradient Flow Matching (GFM), a continuous-time modeling framework that treats neural network training as a dynamical system governed by learned optimizer-aware vector fields. By leveraging conditional flow matching, GFM captures the underlying update rules of optimizers such as SGD, Adam, and RMSprop, enabling smooth extrapolation of weight trajectories toward convergence. Unlike black-box sequence models, GFM incorporates structural knowledge of gradient-ba","authors_text":"Jianxi Gao, Xiao Shou, Yanna Ding","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T17:03:22Z","title":"Gradient Flow Matching for Learning Update Dynamics in Neural Network Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20221","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":"sha256:8d1d072ec54f88d2b2868f7b5672e4bccd3e11790ccd66cc81a34db873e2be96","target":"record","created_at":"2026-07-05T11:09:54Z","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":"45ad67ed22f65696ab102d619083111756834e64101052d7713a780775486dfe","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T17:03:22Z","title_canon_sha256":"b58ec89c2786388a0ec1d3a4f8093a0d4600e8248eccfdb52947e02373d32a01"},"schema_version":"1.0","source":{"id":"2505.20221","kind":"arxiv","version":1}},"canonical_sha256":"3150f88c4e2aedb0da875de7c4bdbadae5ca6c6834492c219284185b5e98071e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3150f88c4e2aedb0da875de7c4bdbadae5ca6c6834492c219284185b5e98071e","first_computed_at":"2026-07-05T11:09:54.418716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:54.418716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eTI+FuGPfNGlJMbDVgs1E0s2+NV7H6Hkx1i51pCnqrKh6jcyPOkRRkGpba42L+3uC7Lkq7ybRenwP+C6tvWUAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:54.419241Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20221","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d1d072ec54f88d2b2868f7b5672e4bccd3e11790ccd66cc81a34db873e2be96","sha256:655da625fc79f0f1c6d8f5f363952ff425ac0c573e3751efbb4b360d7f76d52e"],"state_sha256":"348b1955eb97f4804c21e1d647f56cd710b2ea31c18e1e7d18c00c379a76a94e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a0spB0T0rcoVQPkmRYV5MFA9p+Gzn5DjFmWRsH/od0PQLj6johYN924zKP0c7vwG4Me43CoXB5/xJjuW5UDMDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:53:14.664332Z","bundle_sha256":"bd792ce1f242b51c687669ada126e8b78cbc52a7e44381a040f40aeb299d2017"}}