{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:R5MI2WXZD6FPWALQM3LK5HZRBU","short_pith_number":"pith:R5MI2WXZ","canonical_record":{"source":{"id":"2103.00123","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-27T04:09:32Z","cross_cats_sorted":[],"title_canon_sha256":"fa0f2497da74a7cdcc38696939903ced50e94dd6843b1518b7767c8d64fc8201","abstract_canon_sha256":"988cdff6e5ce57eab159a5d4c698831e2f543943022583fe3db6d5735e90ffd2"},"schema_version":"1.0"},"canonical_sha256":"8f588d5af91f8afb017066d6ae9f310d312f2e6106c0c05917e751fc7f2247a2","source":{"kind":"arxiv","id":"2103.00123","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.00123","created_at":"2026-07-05T02:48:36Z"},{"alias_kind":"arxiv_version","alias_value":"2103.00123v2","created_at":"2026-07-05T02:48:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.00123","created_at":"2026-07-05T02:48:36Z"},{"alias_kind":"pith_short_12","alias_value":"R5MI2WXZD6FP","created_at":"2026-07-05T02:48:36Z"},{"alias_kind":"pith_short_16","alias_value":"R5MI2WXZD6FPWALQ","created_at":"2026-07-05T02:48:36Z"},{"alias_kind":"pith_short_8","alias_value":"R5MI2WXZ","created_at":"2026-07-05T02:48:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:R5MI2WXZD6FPWALQM3LK5HZRBU","target":"record","payload":{"canonical_record":{"source":{"id":"2103.00123","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-27T04:09:32Z","cross_cats_sorted":[],"title_canon_sha256":"fa0f2497da74a7cdcc38696939903ced50e94dd6843b1518b7767c8d64fc8201","abstract_canon_sha256":"988cdff6e5ce57eab159a5d4c698831e2f543943022583fe3db6d5735e90ffd2"},"schema_version":"1.0"},"canonical_sha256":"8f588d5af91f8afb017066d6ae9f310d312f2e6106c0c05917e751fc7f2247a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:36.280526Z","signature_b64":"kggY71e/VbVHfZruPlFTh/zWQC5yENpYgkeC3nFyLby81fnbHwgUw+vnR+6/ySoZvwglcyZlBSKQ5a5hMTWQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f588d5af91f8afb017066d6ae9f310d312f2e6106c0c05917e751fc7f2247a2","last_reissued_at":"2026-07-05T02:48:36.280119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:36.280119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.00123","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":"2026-07-05T02:48:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fqkRcozU2YXQGFFV2VEzte74ntiHEjCGKYQ4YTPwl40dtHIE+lCA0Ph2CvI+jSQj379sP8PRAR2Z0tN11EKnCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:15:55.208240Z"},"content_sha256":"2c5194be9d6a1e1091d2d4f393765ef698843b6ba5a051733678464aac02cc36","schema_version":"1.0","event_id":"sha256:2c5194be9d6a1e1091d2d4f393765ef698843b6ba5a051733678464aac02cc36"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:R5MI2WXZD6FPWALQM3LK5HZRBU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abir De, Durga Sivasubramanian, Ganesh Ramakrishnan, Krishnateja Killamsetty, Rishabh Iyer","submitted_at":"2021-02-27T04:09:32Z","abstract_excerpt":"The great success of modern machine learning models on large datasets is contingent on extensive computational resources with high financial and environmental costs. One way to address this is by extracting subsets that generalize on par with the full data. In this work, we propose a general framework, GRAD-MATCH, which finds subsets that closely match the gradient of the training or validation set. We find such subsets effectively using an orthogonal matching pursuit algorithm. We show rigorous theoretical and convergence guarantees of the proposed algorithm and, through our extensive experim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.00123","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/2103.00123/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":"2026-07-05T02:48:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z5v2dKNrTpIDgNl8D5/V1t0+tCPDrjt9PT3zwl+41Uot7hNoZmqaCvnY0jYNrQYkIvMKUl2UQRNSr3hA0f59AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:15:55.208981Z"},"content_sha256":"989f1ab7534e8e511769e041ce3166512e7f1531879160b189d70646978e5408","schema_version":"1.0","event_id":"sha256:989f1ab7534e8e511769e041ce3166512e7f1531879160b189d70646978e5408"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R5MI2WXZD6FPWALQM3LK5HZRBU/bundle.json","state_url":"https://pith.science/pith/R5MI2WXZD6FPWALQM3LK5HZRBU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R5MI2WXZD6FPWALQM3LK5HZRBU/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":"2026-08-07T17:15:55Z","links":{"resolver":"https://pith.science/pith/R5MI2WXZD6FPWALQM3LK5HZRBU","bundle":"https://pith.science/pith/R5MI2WXZD6FPWALQM3LK5HZRBU/bundle.json","state":"https://pith.science/pith/R5MI2WXZD6FPWALQM3LK5HZRBU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R5MI2WXZD6FPWALQM3LK5HZRBU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:R5MI2WXZD6FPWALQM3LK5HZRBU","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":"988cdff6e5ce57eab159a5d4c698831e2f543943022583fe3db6d5735e90ffd2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-27T04:09:32Z","title_canon_sha256":"fa0f2497da74a7cdcc38696939903ced50e94dd6843b1518b7767c8d64fc8201"},"schema_version":"1.0","source":{"id":"2103.00123","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.00123","created_at":"2026-07-05T02:48:36Z"},{"alias_kind":"arxiv_version","alias_value":"2103.00123v2","created_at":"2026-07-05T02:48:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.00123","created_at":"2026-07-05T02:48:36Z"},{"alias_kind":"pith_short_12","alias_value":"R5MI2WXZD6FP","created_at":"2026-07-05T02:48:36Z"},{"alias_kind":"pith_short_16","alias_value":"R5MI2WXZD6FPWALQ","created_at":"2026-07-05T02:48:36Z"},{"alias_kind":"pith_short_8","alias_value":"R5MI2WXZ","created_at":"2026-07-05T02:48:36Z"}],"graph_snapshots":[{"event_id":"sha256:989f1ab7534e8e511769e041ce3166512e7f1531879160b189d70646978e5408","target":"graph","created_at":"2026-07-05T02:48:36Z","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/2103.00123/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The great success of modern machine learning models on large datasets is contingent on extensive computational resources with high financial and environmental costs. One way to address this is by extracting subsets that generalize on par with the full data. In this work, we propose a general framework, GRAD-MATCH, which finds subsets that closely match the gradient of the training or validation set. We find such subsets effectively using an orthogonal matching pursuit algorithm. We show rigorous theoretical and convergence guarantees of the proposed algorithm and, through our extensive experim","authors_text":"Abir De, Durga Sivasubramanian, Ganesh Ramakrishnan, Krishnateja Killamsetty, Rishabh Iyer","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-27T04:09:32Z","title":"GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.00123","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":"sha256:2c5194be9d6a1e1091d2d4f393765ef698843b6ba5a051733678464aac02cc36","target":"record","created_at":"2026-07-05T02:48:36Z","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":"988cdff6e5ce57eab159a5d4c698831e2f543943022583fe3db6d5735e90ffd2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-27T04:09:32Z","title_canon_sha256":"fa0f2497da74a7cdcc38696939903ced50e94dd6843b1518b7767c8d64fc8201"},"schema_version":"1.0","source":{"id":"2103.00123","kind":"arxiv","version":2}},"canonical_sha256":"8f588d5af91f8afb017066d6ae9f310d312f2e6106c0c05917e751fc7f2247a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f588d5af91f8afb017066d6ae9f310d312f2e6106c0c05917e751fc7f2247a2","first_computed_at":"2026-07-05T02:48:36.280119Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:36.280119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kggY71e/VbVHfZruPlFTh/zWQC5yENpYgkeC3nFyLby81fnbHwgUw+vnR+6/ySoZvwglcyZlBSKQ5a5hMTWQCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:36.280526Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.00123","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c5194be9d6a1e1091d2d4f393765ef698843b6ba5a051733678464aac02cc36","sha256:989f1ab7534e8e511769e041ce3166512e7f1531879160b189d70646978e5408"],"state_sha256":"c2dbc0cfa08f13aeb6bae162f1ac7918617fa33d80a9b12ef9c00b5d13fe5d8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8lgtvfa2XIs+T1AQ4hkWmWj4IE0/3O4h0RnDsogkCL0JuQtJYCz9T941YWbU6Dyf531XQU2JfXimo9+Ynmd0BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:15:55.213622Z","bundle_sha256":"e356c7a172665339ca76749490e63cb9d59b16b7c54f3ee51fd9d2239423b495"}}