{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DF3WPDWZHZNMR5PPY74HOQK55H","short_pith_number":"pith:DF3WPDWZ","canonical_record":{"source":{"id":"2408.05560","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-10T13:52:40Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"c0a18256919068ef1eb0d99f03dcf1b06233a5122f10e93459ba81de844e52b1","abstract_canon_sha256":"c4e9f16b899e55a1bd9f55ef03aae5571e91326c25ed116a5f2f0a96e5e0731c"},"schema_version":"1.0"},"canonical_sha256":"1977678ed93e5ac8f5efc7f877415de9f5705a5f58294d44757fa4ada01b3da5","source":{"kind":"arxiv","id":"2408.05560","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.05560","created_at":"2026-05-27T02:06:12Z"},{"alias_kind":"arxiv_version","alias_value":"2408.05560v2","created_at":"2026-05-27T02:06:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05560","created_at":"2026-05-27T02:06:12Z"},{"alias_kind":"pith_short_12","alias_value":"DF3WPDWZHZNM","created_at":"2026-05-27T02:06:12Z"},{"alias_kind":"pith_short_16","alias_value":"DF3WPDWZHZNMR5PP","created_at":"2026-05-27T02:06:12Z"},{"alias_kind":"pith_short_8","alias_value":"DF3WPDWZ","created_at":"2026-05-27T02:06:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DF3WPDWZHZNMR5PPY74HOQK55H","target":"record","payload":{"canonical_record":{"source":{"id":"2408.05560","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-10T13:52:40Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"c0a18256919068ef1eb0d99f03dcf1b06233a5122f10e93459ba81de844e52b1","abstract_canon_sha256":"c4e9f16b899e55a1bd9f55ef03aae5571e91326c25ed116a5f2f0a96e5e0731c"},"schema_version":"1.0"},"canonical_sha256":"1977678ed93e5ac8f5efc7f877415de9f5705a5f58294d44757fa4ada01b3da5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:06:12.716964Z","signature_b64":"9g9avhVLwI/jzbAFx4bnkbjU82B1Aa6dhY6c7YRj2d/4FUTq5wJhYuST1V5WhTcS3eAPAKcdvrfVgqRV6RcNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1977678ed93e5ac8f5efc7f877415de9f5705a5f58294d44757fa4ada01b3da5","last_reissued_at":"2026-05-27T02:06:12.716287Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:06:12.716287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.05560","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":"2026-05-27T02:06:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8uorI1YeC8ddAZ2QYtJb+LsGkZRqmo9H3q3gKVX31RjeM9t9RVUjGinBj5lDXx65uLSRdAerC2zM9wQTgrO4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T08:48:13.857923Z"},"content_sha256":"e76a91ed82cc5b791e3f697557202e3511b2467f3078689fffcea5d53f177c82","schema_version":"1.0","event_id":"sha256:e76a91ed82cc5b791e3f697557202e3511b2467f3078689fffcea5d53f177c82"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DF3WPDWZHZNMR5PPY74HOQK55H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Incremental Gauss-Newton Descent for Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mario Zanon, Mikalai Korbit","submitted_at":"2024-08-10T13:52:40Z","abstract_excerpt":"Stochastic gradient updates are widely used for their efficiency and scalability, but their effective step sizes can depend strongly on feature scaling and local model sensitivity. Gauss-Newton methods address such scale effects through curvature information, but in their standard mini-batch form they require matrix-vector products, linear solves, or structured approximations. This paper studies the special case of scalar-output losses evaluated one sample at a time. In this setting, the generalized Gauss-Newton matrix has rank at most one, and its only possible nonzero curvature direction is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05560","kind":"arxiv","version":2},"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/2408.05560/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":"2026-05-27T02:06:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wQweRtK8yp5/8F1xuPfygTOTY0dv7zGXo3Nzwc475PN/54VtvNA3SPGwnF6/QN/diX8CVeOfs4f/vORh4Ug5DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T08:48:13.858400Z"},"content_sha256":"7fa3be2bef959899b987e59762be13776dc29037e5ab05ea7e0b76f5757a8629","schema_version":"1.0","event_id":"sha256:7fa3be2bef959899b987e59762be13776dc29037e5ab05ea7e0b76f5757a8629"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DF3WPDWZHZNMR5PPY74HOQK55H/bundle.json","state_url":"https://pith.science/pith/DF3WPDWZHZNMR5PPY74HOQK55H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DF3WPDWZHZNMR5PPY74HOQK55H/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":"2026-06-06T08:48:13Z","links":{"resolver":"https://pith.science/pith/DF3WPDWZHZNMR5PPY74HOQK55H","bundle":"https://pith.science/pith/DF3WPDWZHZNMR5PPY74HOQK55H/bundle.json","state":"https://pith.science/pith/DF3WPDWZHZNMR5PPY74HOQK55H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DF3WPDWZHZNMR5PPY74HOQK55H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DF3WPDWZHZNMR5PPY74HOQK55H","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":"c4e9f16b899e55a1bd9f55ef03aae5571e91326c25ed116a5f2f0a96e5e0731c","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-10T13:52:40Z","title_canon_sha256":"c0a18256919068ef1eb0d99f03dcf1b06233a5122f10e93459ba81de844e52b1"},"schema_version":"1.0","source":{"id":"2408.05560","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.05560","created_at":"2026-05-27T02:06:12Z"},{"alias_kind":"arxiv_version","alias_value":"2408.05560v2","created_at":"2026-05-27T02:06:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05560","created_at":"2026-05-27T02:06:12Z"},{"alias_kind":"pith_short_12","alias_value":"DF3WPDWZHZNM","created_at":"2026-05-27T02:06:12Z"},{"alias_kind":"pith_short_16","alias_value":"DF3WPDWZHZNMR5PP","created_at":"2026-05-27T02:06:12Z"},{"alias_kind":"pith_short_8","alias_value":"DF3WPDWZ","created_at":"2026-05-27T02:06:12Z"}],"graph_snapshots":[{"event_id":"sha256:7fa3be2bef959899b987e59762be13776dc29037e5ab05ea7e0b76f5757a8629","target":"graph","created_at":"2026-05-27T02:06:12Z","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/2408.05560/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stochastic gradient updates are widely used for their efficiency and scalability, but their effective step sizes can depend strongly on feature scaling and local model sensitivity. Gauss-Newton methods address such scale effects through curvature information, but in their standard mini-batch form they require matrix-vector products, linear solves, or structured approximations. This paper studies the special case of scalar-output losses evaluated one sample at a time. In this setting, the generalized Gauss-Newton matrix has rank at most one, and its only possible nonzero curvature direction is ","authors_text":"Mario Zanon, Mikalai Korbit","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-10T13:52:40Z","title":"Incremental Gauss-Newton Descent for Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05560","kind":"arxiv","version":2},"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:e76a91ed82cc5b791e3f697557202e3511b2467f3078689fffcea5d53f177c82","target":"record","created_at":"2026-05-27T02:06:12Z","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":"c4e9f16b899e55a1bd9f55ef03aae5571e91326c25ed116a5f2f0a96e5e0731c","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-10T13:52:40Z","title_canon_sha256":"c0a18256919068ef1eb0d99f03dcf1b06233a5122f10e93459ba81de844e52b1"},"schema_version":"1.0","source":{"id":"2408.05560","kind":"arxiv","version":2}},"canonical_sha256":"1977678ed93e5ac8f5efc7f877415de9f5705a5f58294d44757fa4ada01b3da5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1977678ed93e5ac8f5efc7f877415de9f5705a5f58294d44757fa4ada01b3da5","first_computed_at":"2026-05-27T02:06:12.716287Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T02:06:12.716287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9g9avhVLwI/jzbAFx4bnkbjU82B1Aa6dhY6c7YRj2d/4FUTq5wJhYuST1V5WhTcS3eAPAKcdvrfVgqRV6RcNDQ==","signature_status":"signed_v1","signed_at":"2026-05-27T02:06:12.716964Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.05560","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e76a91ed82cc5b791e3f697557202e3511b2467f3078689fffcea5d53f177c82","sha256:7fa3be2bef959899b987e59762be13776dc29037e5ab05ea7e0b76f5757a8629"],"state_sha256":"45ebd226b81102d3c922abf40be001d03788d1f6b70954744455bd050cd35631"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SY/ZkX+BYsubDXXJ7jLx4iuP1LwwSY/m0b/ZIp1OtnN2cn0ij9YEkBxSDXaSgB98WCxiKCh7LnxMIZ1Xb/E4AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T08:48:13.861542Z","bundle_sha256":"3da3414872ede7637683e467da38796fef18321e4b5260075359207752364d05"}}