{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:I3ZJJDSVAL6TKRKXO4IYJAYME5","short_pith_number":"pith:I3ZJJDSV","canonical_record":{"source":{"id":"2205.13624","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-26T20:52:18Z","cross_cats_sorted":["math.OC","physics.comp-ph"],"title_canon_sha256":"2541a596937e17fd042e7dc92a84adb4f03fe4e01cb20feec57e8e69607cfe71","abstract_canon_sha256":"721d3ce584693ce639ae6f52b1f08a422cb18ab666984cc4ea1aaef180d6d466"},"schema_version":"1.0"},"canonical_sha256":"46f2948e5502fd354557771184830c275268c831808c5f3a3045114d2a20add4","source":{"kind":"arxiv","id":"2205.13624","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.13624","created_at":"2026-07-05T04:26:50Z"},{"alias_kind":"arxiv_version","alias_value":"2205.13624v1","created_at":"2026-07-05T04:26:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13624","created_at":"2026-07-05T04:26:50Z"},{"alias_kind":"pith_short_12","alias_value":"I3ZJJDSVAL6T","created_at":"2026-07-05T04:26:50Z"},{"alias_kind":"pith_short_16","alias_value":"I3ZJJDSVAL6TKRKX","created_at":"2026-07-05T04:26:50Z"},{"alias_kind":"pith_short_8","alias_value":"I3ZJJDSV","created_at":"2026-07-05T04:26:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:I3ZJJDSVAL6TKRKXO4IYJAYME5","target":"record","payload":{"canonical_record":{"source":{"id":"2205.13624","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-26T20:52:18Z","cross_cats_sorted":["math.OC","physics.comp-ph"],"title_canon_sha256":"2541a596937e17fd042e7dc92a84adb4f03fe4e01cb20feec57e8e69607cfe71","abstract_canon_sha256":"721d3ce584693ce639ae6f52b1f08a422cb18ab666984cc4ea1aaef180d6d466"},"schema_version":"1.0"},"canonical_sha256":"46f2948e5502fd354557771184830c275268c831808c5f3a3045114d2a20add4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:50.267309Z","signature_b64":"qIT22vF51QkwYrcEzD682Y3+mmWikMbmfIsi9shHLrU/Jaxhh0z5OXMnm24VDgrA3rv2B4GlFJ9ZH6GMsa8bBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46f2948e5502fd354557771184830c275268c831808c5f3a3045114d2a20add4","last_reissued_at":"2026-07-05T04:26:50.266902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:50.266902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.13624","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":"2026-07-05T04:26:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rWHDwzwiCVuPS4A3lc8umbGonSK+j7N7tqTfgbVm8B0DO9e565SGNMm+Q17VaPvjlMg76mSxqHFB1zfUwMp6BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T10:10:55.542004Z"},"content_sha256":"9b9a9e5d35f9b285225111d50bd654a965e1b8a97619ce77d50b1eacf61890e5","schema_version":"1.0","event_id":"sha256:9b9a9e5d35f9b285225111d50bd654a965e1b8a97619ce77d50b1eacf61890e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:I3ZJJDSVAL6TKRKXO4IYJAYME5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Faster Optimization on Sparse Graphs via Neural Reparametrization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Csaba Both, Jianzhi Long, Nima Dehmamy, Rose Yu","submitted_at":"2022-05-26T20:52:18Z","abstract_excerpt":"In mathematical optimization, second-order Newton's methods generally converge faster than first-order methods, but they require the inverse of the Hessian, hence are computationally expensive. However, we discover that on sparse graphs, graph neural networks (GNN) can implement an efficient Quasi-Newton method that can speed up optimization by a factor of 10-100x. Our method, neural reparametrization, modifies the optimization parameters as the output of a GNN to reshape the optimization landscape. Using a precomputed Hessian as the propagation rule, the GNN can effectively utilize the second"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13624","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/2205.13624/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":"2026-07-05T04:26:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HQRpE7DdgwpXVenadj0wJqBg7sAv4Y7VJbNx2yzjcaEV07R0MXl8lfH0kVVUuq7VT1j72nu4bxIQhM6ZvNcIAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T10:10:55.542517Z"},"content_sha256":"a1790b64a42cce9833d57a9426a8ee40bc43e3e914e09ae10148cf59d5053f47","schema_version":"1.0","event_id":"sha256:a1790b64a42cce9833d57a9426a8ee40bc43e3e914e09ae10148cf59d5053f47"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I3ZJJDSVAL6TKRKXO4IYJAYME5/bundle.json","state_url":"https://pith.science/pith/I3ZJJDSVAL6TKRKXO4IYJAYME5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I3ZJJDSVAL6TKRKXO4IYJAYME5/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":"2026-08-19T10:10:55Z","links":{"resolver":"https://pith.science/pith/I3ZJJDSVAL6TKRKXO4IYJAYME5","bundle":"https://pith.science/pith/I3ZJJDSVAL6TKRKXO4IYJAYME5/bundle.json","state":"https://pith.science/pith/I3ZJJDSVAL6TKRKXO4IYJAYME5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I3ZJJDSVAL6TKRKXO4IYJAYME5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:I3ZJJDSVAL6TKRKXO4IYJAYME5","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":"721d3ce584693ce639ae6f52b1f08a422cb18ab666984cc4ea1aaef180d6d466","cross_cats_sorted":["math.OC","physics.comp-ph"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-26T20:52:18Z","title_canon_sha256":"2541a596937e17fd042e7dc92a84adb4f03fe4e01cb20feec57e8e69607cfe71"},"schema_version":"1.0","source":{"id":"2205.13624","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.13624","created_at":"2026-07-05T04:26:50Z"},{"alias_kind":"arxiv_version","alias_value":"2205.13624v1","created_at":"2026-07-05T04:26:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13624","created_at":"2026-07-05T04:26:50Z"},{"alias_kind":"pith_short_12","alias_value":"I3ZJJDSVAL6T","created_at":"2026-07-05T04:26:50Z"},{"alias_kind":"pith_short_16","alias_value":"I3ZJJDSVAL6TKRKX","created_at":"2026-07-05T04:26:50Z"},{"alias_kind":"pith_short_8","alias_value":"I3ZJJDSV","created_at":"2026-07-05T04:26:50Z"}],"graph_snapshots":[{"event_id":"sha256:a1790b64a42cce9833d57a9426a8ee40bc43e3e914e09ae10148cf59d5053f47","target":"graph","created_at":"2026-07-05T04:26:50Z","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/2205.13624/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In mathematical optimization, second-order Newton's methods generally converge faster than first-order methods, but they require the inverse of the Hessian, hence are computationally expensive. However, we discover that on sparse graphs, graph neural networks (GNN) can implement an efficient Quasi-Newton method that can speed up optimization by a factor of 10-100x. Our method, neural reparametrization, modifies the optimization parameters as the output of a GNN to reshape the optimization landscape. Using a precomputed Hessian as the propagation rule, the GNN can effectively utilize the second","authors_text":"Csaba Both, Jianzhi Long, Nima Dehmamy, Rose Yu","cross_cats":["math.OC","physics.comp-ph"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-26T20:52:18Z","title":"Faster Optimization on Sparse Graphs via Neural Reparametrization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13624","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":"sha256:9b9a9e5d35f9b285225111d50bd654a965e1b8a97619ce77d50b1eacf61890e5","target":"record","created_at":"2026-07-05T04:26:50Z","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":"721d3ce584693ce639ae6f52b1f08a422cb18ab666984cc4ea1aaef180d6d466","cross_cats_sorted":["math.OC","physics.comp-ph"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-26T20:52:18Z","title_canon_sha256":"2541a596937e17fd042e7dc92a84adb4f03fe4e01cb20feec57e8e69607cfe71"},"schema_version":"1.0","source":{"id":"2205.13624","kind":"arxiv","version":1}},"canonical_sha256":"46f2948e5502fd354557771184830c275268c831808c5f3a3045114d2a20add4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46f2948e5502fd354557771184830c275268c831808c5f3a3045114d2a20add4","first_computed_at":"2026-07-05T04:26:50.266902Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:26:50.266902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qIT22vF51QkwYrcEzD682Y3+mmWikMbmfIsi9shHLrU/Jaxhh0z5OXMnm24VDgrA3rv2B4GlFJ9ZH6GMsa8bBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:26:50.267309Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.13624","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b9a9e5d35f9b285225111d50bd654a965e1b8a97619ce77d50b1eacf61890e5","sha256:a1790b64a42cce9833d57a9426a8ee40bc43e3e914e09ae10148cf59d5053f47"],"state_sha256":"dff9e396a40778345bace6920e2bbeadb1be8f9496608ea5a2f6576a7056a83e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8yrjXnwlLAQU63UDcYYt4iVTWc8RNvrZKBgatNSb/TTSHvaY1cRYhieVgqdmzOPPvlJWW9EJiTCiZS8c+qICBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T10:10:55.549334Z","bundle_sha256":"c5286309e70bf8c4e4989d0775de8a9539547186fedbb7932c5ae6f25f99890f"}}