{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:AHR6OPRMDRSQZN47LQMLFWDG7L","short_pith_number":"pith:AHR6OPRM","canonical_record":{"source":{"id":"1802.05374","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-15T01:02:36Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"679b936bc4a3d7884646dec9c72d2a36a95dff4e5f6839d885c0e553439002dd","abstract_canon_sha256":"fa213ad8fbc2f189baf556cae59fb4685d7f6807b540bfdc379bff4168b814f1"},"schema_version":"1.0"},"canonical_sha256":"01e3e73e2c1c650cb79f5c18b2d866faec8583d2a94465ade27583739b9cf578","source":{"kind":"arxiv","id":"1802.05374","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.05374","created_at":"2026-05-18T00:14:40Z"},{"alias_kind":"arxiv_version","alias_value":"1802.05374v2","created_at":"2026-05-18T00:14:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05374","created_at":"2026-05-18T00:14:40Z"},{"alias_kind":"pith_short_12","alias_value":"AHR6OPRMDRSQ","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AHR6OPRMDRSQZN47","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AHR6OPRM","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:AHR6OPRMDRSQZN47LQMLFWDG7L","target":"record","payload":{"canonical_record":{"source":{"id":"1802.05374","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-15T01:02:36Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"679b936bc4a3d7884646dec9c72d2a36a95dff4e5f6839d885c0e553439002dd","abstract_canon_sha256":"fa213ad8fbc2f189baf556cae59fb4685d7f6807b540bfdc379bff4168b814f1"},"schema_version":"1.0"},"canonical_sha256":"01e3e73e2c1c650cb79f5c18b2d866faec8583d2a94465ade27583739b9cf578","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:40.326627Z","signature_b64":"YsyCkEN+MTwp0s+HFujuT0/rNVVTyRv5wiaqCSHdG61IlNoSR3ePO0XGf1ysNPh/sE2iRD5FJdW+jN33i4hPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01e3e73e2c1c650cb79f5c18b2d866faec8583d2a94465ade27583739b9cf578","last_reissued_at":"2026-05-18T00:14:40.325970Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:40.325970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.05374","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":"2026-05-18T00:14:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y3pujmSsfIAXrR9c4rwxjQYjxbcIiAfvjr5vwcAWd+uTDCfRdHshZyx6G+I/TWQiev86T30YuSbhNhRBKEuVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:25:22.540729Z"},"content_sha256":"9c542111579bcc5556381e83cecb0649864da7709958b2ec06f6d85441aa9d89","schema_version":"1.0","event_id":"sha256:9c542111579bcc5556381e83cecb0649864da7709958b2ec06f6d85441aa9d89"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:AHR6OPRMDRSQZN47LQMLFWDG7L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Progressive Batching L-BFGS Method for Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Dheevatsa Mudigere, Hao-Jun Michael Shi, Jorge Nocedal, Ping Tak Peter Tang, Raghu Bollapragada","submitted_at":"2018-02-15T01:02:36Z","abstract_excerpt":"The standard L-BFGS method relies on gradient approximations that are not dominated by noise, so that search directions are descent directions, the line search is reliable, and quasi-Newton updating yields useful quadratic models of the objective function. All of this appears to call for a full batch approach, but since small batch sizes give rise to faster algorithms with better generalization properties, L-BFGS is currently not considered an algorithm of choice for large-scale machine learning applications. One need not, however, choose between the two extremes represented by the full batch "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05374","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":""},"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":"2026-05-18T00:14:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AzBl1+vWNqIYYE6lECKarhFmdn69YXc8gSXE3Hf9CgbE8OntsaUv2KUqh+AoYeMEvKEmnYNqzeOM/d8HoSdWDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:25:22.541168Z"},"content_sha256":"384ed200cd540439a2ad7cd1a32654515dd20a5ebbea156c0df7bab0e65a7ce3","schema_version":"1.0","event_id":"sha256:384ed200cd540439a2ad7cd1a32654515dd20a5ebbea156c0df7bab0e65a7ce3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AHR6OPRMDRSQZN47LQMLFWDG7L/bundle.json","state_url":"https://pith.science/pith/AHR6OPRMDRSQZN47LQMLFWDG7L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AHR6OPRMDRSQZN47LQMLFWDG7L/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":"2026-08-04T01:25:22Z","links":{"resolver":"https://pith.science/pith/AHR6OPRMDRSQZN47LQMLFWDG7L","bundle":"https://pith.science/pith/AHR6OPRMDRSQZN47LQMLFWDG7L/bundle.json","state":"https://pith.science/pith/AHR6OPRMDRSQZN47LQMLFWDG7L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AHR6OPRMDRSQZN47LQMLFWDG7L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:AHR6OPRMDRSQZN47LQMLFWDG7L","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":"fa213ad8fbc2f189baf556cae59fb4685d7f6807b540bfdc379bff4168b814f1","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-15T01:02:36Z","title_canon_sha256":"679b936bc4a3d7884646dec9c72d2a36a95dff4e5f6839d885c0e553439002dd"},"schema_version":"1.0","source":{"id":"1802.05374","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.05374","created_at":"2026-05-18T00:14:40Z"},{"alias_kind":"arxiv_version","alias_value":"1802.05374v2","created_at":"2026-05-18T00:14:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05374","created_at":"2026-05-18T00:14:40Z"},{"alias_kind":"pith_short_12","alias_value":"AHR6OPRMDRSQ","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AHR6OPRMDRSQZN47","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AHR6OPRM","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:384ed200cd540439a2ad7cd1a32654515dd20a5ebbea156c0df7bab0e65a7ce3","target":"graph","created_at":"2026-05-18T00:14:40Z","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"},"paper":{"abstract_excerpt":"The standard L-BFGS method relies on gradient approximations that are not dominated by noise, so that search directions are descent directions, the line search is reliable, and quasi-Newton updating yields useful quadratic models of the objective function. All of this appears to call for a full batch approach, but since small batch sizes give rise to faster algorithms with better generalization properties, L-BFGS is currently not considered an algorithm of choice for large-scale machine learning applications. One need not, however, choose between the two extremes represented by the full batch ","authors_text":"Dheevatsa Mudigere, Hao-Jun Michael Shi, Jorge Nocedal, Ping Tak Peter Tang, Raghu Bollapragada","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-15T01:02:36Z","title":"A Progressive Batching L-BFGS Method for Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05374","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":"sha256:9c542111579bcc5556381e83cecb0649864da7709958b2ec06f6d85441aa9d89","target":"record","created_at":"2026-05-18T00:14:40Z","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":"fa213ad8fbc2f189baf556cae59fb4685d7f6807b540bfdc379bff4168b814f1","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-15T01:02:36Z","title_canon_sha256":"679b936bc4a3d7884646dec9c72d2a36a95dff4e5f6839d885c0e553439002dd"},"schema_version":"1.0","source":{"id":"1802.05374","kind":"arxiv","version":2}},"canonical_sha256":"01e3e73e2c1c650cb79f5c18b2d866faec8583d2a94465ade27583739b9cf578","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01e3e73e2c1c650cb79f5c18b2d866faec8583d2a94465ade27583739b9cf578","first_computed_at":"2026-05-18T00:14:40.325970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:40.325970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YsyCkEN+MTwp0s+HFujuT0/rNVVTyRv5wiaqCSHdG61IlNoSR3ePO0XGf1ysNPh/sE2iRD5FJdW+jN33i4hPBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:40.326627Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.05374","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c542111579bcc5556381e83cecb0649864da7709958b2ec06f6d85441aa9d89","sha256:384ed200cd540439a2ad7cd1a32654515dd20a5ebbea156c0df7bab0e65a7ce3"],"state_sha256":"76af2762317635d1a966a7b31534de635ab34faaa0e3b6ef27e1b6af26fef318"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g+o9zCkijXDTemosiXRIwtN38Gt1+d/3bkFdobiKeL4uhmx6rNHeKfIt/6VnNEmXXzoI+GAAHxgjQD8q8boGCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T01:25:22.544586Z","bundle_sha256":"1b9babbe1317d57f32b7ed46ebfe69bdd078eb783cc89df5d07707892b3f5264"}}