{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:LDW4QRJII4SHMZHIRVYP5L4Y6Y","short_pith_number":"pith:LDW4QRJI","canonical_record":{"source":{"id":"1906.01827","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-05T05:10:37Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"cda9e8dba12c056c1fdaddc80e13e80ea740e84d273139720d4ef6ea1cfad212","abstract_canon_sha256":"101e553783c31181164c51363e6130bbcbf9f382fae065c6259b74879ecc901d"},"schema_version":"1.0"},"canonical_sha256":"58edc8452847247664e88d70feaf98f618c0a22a816797518ff1ccd0c681bf03","source":{"kind":"arxiv","id":"1906.01827","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.01827","created_at":"2026-07-05T01:51:58Z"},{"alias_kind":"arxiv_version","alias_value":"1906.01827v3","created_at":"2026-07-05T01:51:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01827","created_at":"2026-07-05T01:51:58Z"},{"alias_kind":"pith_short_12","alias_value":"LDW4QRJII4SH","created_at":"2026-07-05T01:51:58Z"},{"alias_kind":"pith_short_16","alias_value":"LDW4QRJII4SHMZHI","created_at":"2026-07-05T01:51:58Z"},{"alias_kind":"pith_short_8","alias_value":"LDW4QRJI","created_at":"2026-07-05T01:51:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:LDW4QRJII4SHMZHIRVYP5L4Y6Y","target":"record","payload":{"canonical_record":{"source":{"id":"1906.01827","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-05T05:10:37Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"cda9e8dba12c056c1fdaddc80e13e80ea740e84d273139720d4ef6ea1cfad212","abstract_canon_sha256":"101e553783c31181164c51363e6130bbcbf9f382fae065c6259b74879ecc901d"},"schema_version":"1.0"},"canonical_sha256":"58edc8452847247664e88d70feaf98f618c0a22a816797518ff1ccd0c681bf03","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:58.805934Z","signature_b64":"UeWJaQ/l9KzUOPCF2zFUVIGUq/X/k2fwFJtJnpBJcuCcLwJ9EF3mBzfWOBcjIoci3vNzx2F0T/rxH+9swSheAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58edc8452847247664e88d70feaf98f618c0a22a816797518ff1ccd0c681bf03","last_reissued_at":"2026-07-05T01:51:58.805433Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:58.805433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.01827","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:51:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gDXF4MQNNq3nRepfBoIdit5Sgzis83UubWahDXl7ZIJPF8ZcMZKsa0xUzQfZ+5WmppfJG2a/dndJ+NqX0dIwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:29:31.070824Z"},"content_sha256":"fa51f415314bd38a3d49964cfd859042b4b3a710e5a589fb7059e26186d2d215","schema_version":"1.0","event_id":"sha256:fa51f415314bd38a3d49964cfd859042b4b3a710e5a589fb7059e26186d2d215"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:LDW4QRJII4SHMZHIRVYP5L4Y6Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Coresets for Data-efficient Training of Machine Learning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Baharan Mirzasoleiman, Jeff Bilmes, Jure Leskovec","submitted_at":"2019-06-05T05:10:37Z","abstract_excerpt":"Incremental gradient (IG) methods, such as stochastic gradient descent and its variants are commonly used for large scale optimization in machine learning. Despite the sustained effort to make IG methods more data-efficient, it remains an open question how to select a training data subset that can theoretically and practically perform on par with the full dataset. Here we develop CRAIG, a method to select a weighted subset (or coreset) of training data that closely estimates the full gradient by maximizing a submodular function. We prove that applying IG to this subset is guaranteed to converg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01827","kind":"arxiv","version":3},"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/1906.01827/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":"2026-07-05T01:51:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N8nd1We00+8QhcZNg7WdgXt2wiRNmWEmrSApzY780ckBqnR7Y2FYkMn46IU72xSjKBKuBNp/AsjkYy4//wOvDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:29:31.071352Z"},"content_sha256":"c925e2440d5fc07577a89832fbc9d944f5c8a6eff32e242a39d372650cad1696","schema_version":"1.0","event_id":"sha256:c925e2440d5fc07577a89832fbc9d944f5c8a6eff32e242a39d372650cad1696"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LDW4QRJII4SHMZHIRVYP5L4Y6Y/bundle.json","state_url":"https://pith.science/pith/LDW4QRJII4SHMZHIRVYP5L4Y6Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LDW4QRJII4SHMZHIRVYP5L4Y6Y/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":"2026-08-07T18:29:31Z","links":{"resolver":"https://pith.science/pith/LDW4QRJII4SHMZHIRVYP5L4Y6Y","bundle":"https://pith.science/pith/LDW4QRJII4SHMZHIRVYP5L4Y6Y/bundle.json","state":"https://pith.science/pith/LDW4QRJII4SHMZHIRVYP5L4Y6Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LDW4QRJII4SHMZHIRVYP5L4Y6Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:LDW4QRJII4SHMZHIRVYP5L4Y6Y","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":"101e553783c31181164c51363e6130bbcbf9f382fae065c6259b74879ecc901d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-05T05:10:37Z","title_canon_sha256":"cda9e8dba12c056c1fdaddc80e13e80ea740e84d273139720d4ef6ea1cfad212"},"schema_version":"1.0","source":{"id":"1906.01827","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.01827","created_at":"2026-07-05T01:51:58Z"},{"alias_kind":"arxiv_version","alias_value":"1906.01827v3","created_at":"2026-07-05T01:51:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01827","created_at":"2026-07-05T01:51:58Z"},{"alias_kind":"pith_short_12","alias_value":"LDW4QRJII4SH","created_at":"2026-07-05T01:51:58Z"},{"alias_kind":"pith_short_16","alias_value":"LDW4QRJII4SHMZHI","created_at":"2026-07-05T01:51:58Z"},{"alias_kind":"pith_short_8","alias_value":"LDW4QRJI","created_at":"2026-07-05T01:51:58Z"}],"graph_snapshots":[{"event_id":"sha256:c925e2440d5fc07577a89832fbc9d944f5c8a6eff32e242a39d372650cad1696","target":"graph","created_at":"2026-07-05T01:51:58Z","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/1906.01827/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Incremental gradient (IG) methods, such as stochastic gradient descent and its variants are commonly used for large scale optimization in machine learning. Despite the sustained effort to make IG methods more data-efficient, it remains an open question how to select a training data subset that can theoretically and practically perform on par with the full dataset. Here we develop CRAIG, a method to select a weighted subset (or coreset) of training data that closely estimates the full gradient by maximizing a submodular function. We prove that applying IG to this subset is guaranteed to converg","authors_text":"Baharan Mirzasoleiman, Jeff Bilmes, Jure Leskovec","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-05T05:10:37Z","title":"Coresets for Data-efficient Training of Machine Learning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01827","kind":"arxiv","version":3},"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:fa51f415314bd38a3d49964cfd859042b4b3a710e5a589fb7059e26186d2d215","target":"record","created_at":"2026-07-05T01:51:58Z","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":"101e553783c31181164c51363e6130bbcbf9f382fae065c6259b74879ecc901d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-05T05:10:37Z","title_canon_sha256":"cda9e8dba12c056c1fdaddc80e13e80ea740e84d273139720d4ef6ea1cfad212"},"schema_version":"1.0","source":{"id":"1906.01827","kind":"arxiv","version":3}},"canonical_sha256":"58edc8452847247664e88d70feaf98f618c0a22a816797518ff1ccd0c681bf03","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58edc8452847247664e88d70feaf98f618c0a22a816797518ff1ccd0c681bf03","first_computed_at":"2026-07-05T01:51:58.805433Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:51:58.805433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UeWJaQ/l9KzUOPCF2zFUVIGUq/X/k2fwFJtJnpBJcuCcLwJ9EF3mBzfWOBcjIoci3vNzx2F0T/rxH+9swSheAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:51:58.805934Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.01827","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa51f415314bd38a3d49964cfd859042b4b3a710e5a589fb7059e26186d2d215","sha256:c925e2440d5fc07577a89832fbc9d944f5c8a6eff32e242a39d372650cad1696"],"state_sha256":"96411517498fdc24c9a34bf076e5ceef3f46525a238268333a25b11bbb03c2ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VS2/2ISzHXBSdyR3ynRm9L40cEu/9mh/Y6fOAulFXLP0gsYXmNeVJj5jXRKdSUEDE5oXHopn+/DnEtDsbLhACw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:29:31.076454Z","bundle_sha256":"32a37df18f8cc268a1f2ea714460da254176e3cadd67be6f1125a5705b5d040f"}}