{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QO6XCM2M7JBXDF5KEUST22EFQ5","short_pith_number":"pith:QO6XCM2M","canonical_record":{"source":{"id":"2310.07931","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T23:01:29Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"a167c0c623258c835d8d1d5bbd5b66d7230e37c4af850e37855936b05b9cda5b","abstract_canon_sha256":"e25e26852daca929e9352f970f19da097c68511c9acc469d2814ed84ed9d5809"},"schema_version":"1.0"},"canonical_sha256":"83bd71334cfa437197aa25253d688587785b579aadcf5d65bf2f3fe11da339b8","source":{"kind":"arxiv","id":"2310.07931","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07931","created_at":"2026-07-05T06:59:58Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07931v1","created_at":"2026-07-05T06:59:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07931","created_at":"2026-07-05T06:59:58Z"},{"alias_kind":"pith_short_12","alias_value":"QO6XCM2M7JBX","created_at":"2026-07-05T06:59:58Z"},{"alias_kind":"pith_short_16","alias_value":"QO6XCM2M7JBXDF5K","created_at":"2026-07-05T06:59:58Z"},{"alias_kind":"pith_short_8","alias_value":"QO6XCM2M","created_at":"2026-07-05T06:59:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QO6XCM2M7JBXDF5KEUST22EFQ5","target":"record","payload":{"canonical_record":{"source":{"id":"2310.07931","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T23:01:29Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"a167c0c623258c835d8d1d5bbd5b66d7230e37c4af850e37855936b05b9cda5b","abstract_canon_sha256":"e25e26852daca929e9352f970f19da097c68511c9acc469d2814ed84ed9d5809"},"schema_version":"1.0"},"canonical_sha256":"83bd71334cfa437197aa25253d688587785b579aadcf5d65bf2f3fe11da339b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:58.361883Z","signature_b64":"hLLbXoFmnnjBuDz/NMCyk3CwX2QAJQKKV4kJMaPQjJZhMPFmiD5BdfW5xHaqmqntu61le2Nda0W7SKWZubWrBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83bd71334cfa437197aa25253d688587785b579aadcf5d65bf2f3fe11da339b8","last_reissued_at":"2026-07-05T06:59:58.361376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:58.361376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.07931","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":"2026-07-05T06:59:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vKm1VNZS14bO9WEFH650N1ZW1GGS/vbo5VErzR+fVirEZEV4EhXue2sHdR80kbonHpdkAdIpw5xVPESmsJa7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:53:07.023108Z"},"content_sha256":"bfc35e1942424cc860bd6f188cbeeed1d26386efab9745d695d9258112378f48","schema_version":"1.0","event_id":"sha256:bfc35e1942424cc860bd6f188cbeeed1d26386efab9745d695d9258112378f48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QO6XCM2M7JBXDF5KEUST22EFQ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Adyasha Maharana, Mohit Bansal, Prateek Yadav","submitted_at":"2023-10-11T23:01:29Z","abstract_excerpt":"Analytical theories suggest that higher-quality data can lead to lower test errors in models trained on a fixed data budget. Moreover, a model can be trained on a lower compute budget without compromising performance if a dataset can be stripped of its redundancies. Coreset selection (or data pruning) seeks to select a subset of the training data so as to maximize the performance of models trained on this subset, also referred to as coreset. There are two dominant approaches: (1) geometry-based data selection for maximizing data diversity in the coreset, and (2) functions that assign difficult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07931","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/2310.07931/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":"2026-07-05T06:59:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TnarwARcahrqig6YhCrnmEVNZBKtcsglifbFIIbZNr+UiiMQGLLjFCu2I4dCSGeDZUDJVs6fUWASus+bnRnSBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:53:07.023512Z"},"content_sha256":"1d3a8bb20110c803bb8ba3b9a02c9cb6d245279d759ed818d1cc85a8523fc064","schema_version":"1.0","event_id":"sha256:1d3a8bb20110c803bb8ba3b9a02c9cb6d245279d759ed818d1cc85a8523fc064"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QO6XCM2M7JBXDF5KEUST22EFQ5/bundle.json","state_url":"https://pith.science/pith/QO6XCM2M7JBXDF5KEUST22EFQ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QO6XCM2M7JBXDF5KEUST22EFQ5/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":"2026-08-05T20:53:07Z","links":{"resolver":"https://pith.science/pith/QO6XCM2M7JBXDF5KEUST22EFQ5","bundle":"https://pith.science/pith/QO6XCM2M7JBXDF5KEUST22EFQ5/bundle.json","state":"https://pith.science/pith/QO6XCM2M7JBXDF5KEUST22EFQ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QO6XCM2M7JBXDF5KEUST22EFQ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QO6XCM2M7JBXDF5KEUST22EFQ5","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":"e25e26852daca929e9352f970f19da097c68511c9acc469d2814ed84ed9d5809","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T23:01:29Z","title_canon_sha256":"a167c0c623258c835d8d1d5bbd5b66d7230e37c4af850e37855936b05b9cda5b"},"schema_version":"1.0","source":{"id":"2310.07931","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07931","created_at":"2026-07-05T06:59:58Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07931v1","created_at":"2026-07-05T06:59:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07931","created_at":"2026-07-05T06:59:58Z"},{"alias_kind":"pith_short_12","alias_value":"QO6XCM2M7JBX","created_at":"2026-07-05T06:59:58Z"},{"alias_kind":"pith_short_16","alias_value":"QO6XCM2M7JBXDF5K","created_at":"2026-07-05T06:59:58Z"},{"alias_kind":"pith_short_8","alias_value":"QO6XCM2M","created_at":"2026-07-05T06:59:58Z"}],"graph_snapshots":[{"event_id":"sha256:1d3a8bb20110c803bb8ba3b9a02c9cb6d245279d759ed818d1cc85a8523fc064","target":"graph","created_at":"2026-07-05T06:59:58Z","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/2310.07931/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Analytical theories suggest that higher-quality data can lead to lower test errors in models trained on a fixed data budget. Moreover, a model can be trained on a lower compute budget without compromising performance if a dataset can be stripped of its redundancies. Coreset selection (or data pruning) seeks to select a subset of the training data so as to maximize the performance of models trained on this subset, also referred to as coreset. There are two dominant approaches: (1) geometry-based data selection for maximizing data diversity in the coreset, and (2) functions that assign difficult","authors_text":"Adyasha Maharana, Mohit Bansal, Prateek Yadav","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T23:01:29Z","title":"D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07931","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:bfc35e1942424cc860bd6f188cbeeed1d26386efab9745d695d9258112378f48","target":"record","created_at":"2026-07-05T06:59:58Z","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":"e25e26852daca929e9352f970f19da097c68511c9acc469d2814ed84ed9d5809","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T23:01:29Z","title_canon_sha256":"a167c0c623258c835d8d1d5bbd5b66d7230e37c4af850e37855936b05b9cda5b"},"schema_version":"1.0","source":{"id":"2310.07931","kind":"arxiv","version":1}},"canonical_sha256":"83bd71334cfa437197aa25253d688587785b579aadcf5d65bf2f3fe11da339b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83bd71334cfa437197aa25253d688587785b579aadcf5d65bf2f3fe11da339b8","first_computed_at":"2026-07-05T06:59:58.361376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:58.361376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hLLbXoFmnnjBuDz/NMCyk3CwX2QAJQKKV4kJMaPQjJZhMPFmiD5BdfW5xHaqmqntu61le2Nda0W7SKWZubWrBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:58.361883Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.07931","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfc35e1942424cc860bd6f188cbeeed1d26386efab9745d695d9258112378f48","sha256:1d3a8bb20110c803bb8ba3b9a02c9cb6d245279d759ed818d1cc85a8523fc064"],"state_sha256":"feadf41bbc9366ac721fb9f800c81fa20533bc243684dcb1e7b1c62af20565eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JgNUm9dVRPDD21Wznu8Dw1H5upBe+Q+DSsrW8u7umGGzTQIN1XLwOCgYRBkrRMH8cYAqrLdrHHIvwo0XGcV0CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:53:07.025830Z","bundle_sha256":"2385434f8e489f8dac523f938dc9d61ce53550d01e8b90c2486024a99809f8e1"}}