{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KSR3PYEGM4RSGW63JR4QN7SKC3","short_pith_number":"pith:KSR3PYEG","canonical_record":{"source":{"id":"2205.15466","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T23:44:09Z","cross_cats_sorted":["cs.GT","stat.ML"],"title_canon_sha256":"cd8a3302780a1bfd1b1f810f7efbc3b69e1e0eecc4ed5200e8e78c01b065f3c2","abstract_canon_sha256":"3bc5c8ae5eae16be49a61cad296291b3d4f924c51e5c542e5172f6175102c43d"},"schema_version":"1.0"},"canonical_sha256":"54a3b7e0866723235bdb4c7906fe4a16ea65f5fa81bd80d1c5ba2167b8123a04","source":{"kind":"arxiv","id":"2205.15466","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15466","created_at":"2026-07-05T07:25:21Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15466v7","created_at":"2026-07-05T07:25:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15466","created_at":"2026-07-05T07:25:21Z"},{"alias_kind":"pith_short_12","alias_value":"KSR3PYEGM4RS","created_at":"2026-07-05T07:25:21Z"},{"alias_kind":"pith_short_16","alias_value":"KSR3PYEGM4RSGW63","created_at":"2026-07-05T07:25:21Z"},{"alias_kind":"pith_short_8","alias_value":"KSR3PYEG","created_at":"2026-07-05T07:25:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KSR3PYEGM4RSGW63JR4QN7SKC3","target":"record","payload":{"canonical_record":{"source":{"id":"2205.15466","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T23:44:09Z","cross_cats_sorted":["cs.GT","stat.ML"],"title_canon_sha256":"cd8a3302780a1bfd1b1f810f7efbc3b69e1e0eecc4ed5200e8e78c01b065f3c2","abstract_canon_sha256":"3bc5c8ae5eae16be49a61cad296291b3d4f924c51e5c542e5172f6175102c43d"},"schema_version":"1.0"},"canonical_sha256":"54a3b7e0866723235bdb4c7906fe4a16ea65f5fa81bd80d1c5ba2167b8123a04","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:21.131717Z","signature_b64":"irwUnKTbV7kcZcms4kcQL+NtVBP7q0UGTEKTIPxLPP2kSYt5pYrUhu94BQbJ3EiAKeuXT01VtHX3i7KhmFU8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54a3b7e0866723235bdb4c7906fe4a16ea65f5fa81bd80d1c5ba2167b8123a04","last_reissued_at":"2026-07-05T07:25:21.131245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:21.131245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.15466","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:25:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ji+APsHIAK4fzbBOkrWQuAhf7bTWXbr9y4KJ1mhC9+/qvN0RpiHX6Yw4Jw7OAYL1WQ2B42UigtyothDU7C3nAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:49:53.011694Z"},"content_sha256":"ba93a1ac82aa897d8b65f541600a5d2a5d1a1ae0cba7a879c1863a9b852e26f1","schema_version":"1.0","event_id":"sha256:ba93a1ac82aa897d8b65f541600a5d2a5d1a1ae0cba7a879c1863a9b852e26f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KSR3PYEGM4RSGW63JR4QN7SKC3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Banzhaf: A Robust Data Valuation Framework for Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiachen T. Wang, Ruoxi Jia","submitted_at":"2022-05-30T23:44:09Z","abstract_excerpt":"Data valuation has wide use cases in machine learning, including improving data quality and creating economic incentives for data sharing. This paper studies the robustness of data valuation to noisy model performance scores. Particularly, we find that the inherent randomness of the widely used stochastic gradient descent can cause existing data value notions (e.g., the Shapley value and the Leave-one-out error) to produce inconsistent data value rankings across different runs. To address this challenge, we introduce the concept of safety margin, which measures the robustness of a data value n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15466","kind":"arxiv","version":7},"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/2205.15466/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":"2026-07-05T07:25:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jdHeD3S2zsDiRvQGHUHV+5p/8ceVPYD32pUoCT1NJcAmfUej2Hlt3FxeIz/Lv5Ydyd6TGplfTg0KlaahRwq1DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:49:53.012227Z"},"content_sha256":"1bcb3902a27bc62d9efc700452bb81c9a614e3e43021ac779d7cf3f75a39642c","schema_version":"1.0","event_id":"sha256:1bcb3902a27bc62d9efc700452bb81c9a614e3e43021ac779d7cf3f75a39642c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KSR3PYEGM4RSGW63JR4QN7SKC3/bundle.json","state_url":"https://pith.science/pith/KSR3PYEGM4RSGW63JR4QN7SKC3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KSR3PYEGM4RSGW63JR4QN7SKC3/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":"2026-08-19T04:49:53Z","links":{"resolver":"https://pith.science/pith/KSR3PYEGM4RSGW63JR4QN7SKC3","bundle":"https://pith.science/pith/KSR3PYEGM4RSGW63JR4QN7SKC3/bundle.json","state":"https://pith.science/pith/KSR3PYEGM4RSGW63JR4QN7SKC3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KSR3PYEGM4RSGW63JR4QN7SKC3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KSR3PYEGM4RSGW63JR4QN7SKC3","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":"3bc5c8ae5eae16be49a61cad296291b3d4f924c51e5c542e5172f6175102c43d","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T23:44:09Z","title_canon_sha256":"cd8a3302780a1bfd1b1f810f7efbc3b69e1e0eecc4ed5200e8e78c01b065f3c2"},"schema_version":"1.0","source":{"id":"2205.15466","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15466","created_at":"2026-07-05T07:25:21Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15466v7","created_at":"2026-07-05T07:25:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15466","created_at":"2026-07-05T07:25:21Z"},{"alias_kind":"pith_short_12","alias_value":"KSR3PYEGM4RS","created_at":"2026-07-05T07:25:21Z"},{"alias_kind":"pith_short_16","alias_value":"KSR3PYEGM4RSGW63","created_at":"2026-07-05T07:25:21Z"},{"alias_kind":"pith_short_8","alias_value":"KSR3PYEG","created_at":"2026-07-05T07:25:21Z"}],"graph_snapshots":[{"event_id":"sha256:1bcb3902a27bc62d9efc700452bb81c9a614e3e43021ac779d7cf3f75a39642c","target":"graph","created_at":"2026-07-05T07:25:21Z","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/2205.15466/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data valuation has wide use cases in machine learning, including improving data quality and creating economic incentives for data sharing. This paper studies the robustness of data valuation to noisy model performance scores. Particularly, we find that the inherent randomness of the widely used stochastic gradient descent can cause existing data value notions (e.g., the Shapley value and the Leave-one-out error) to produce inconsistent data value rankings across different runs. To address this challenge, we introduce the concept of safety margin, which measures the robustness of a data value n","authors_text":"Jiachen T. Wang, Ruoxi Jia","cross_cats":["cs.GT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T23:44:09Z","title":"Data Banzhaf: A Robust Data Valuation Framework for Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15466","kind":"arxiv","version":7},"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:ba93a1ac82aa897d8b65f541600a5d2a5d1a1ae0cba7a879c1863a9b852e26f1","target":"record","created_at":"2026-07-05T07:25:21Z","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":"3bc5c8ae5eae16be49a61cad296291b3d4f924c51e5c542e5172f6175102c43d","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T23:44:09Z","title_canon_sha256":"cd8a3302780a1bfd1b1f810f7efbc3b69e1e0eecc4ed5200e8e78c01b065f3c2"},"schema_version":"1.0","source":{"id":"2205.15466","kind":"arxiv","version":7}},"canonical_sha256":"54a3b7e0866723235bdb4c7906fe4a16ea65f5fa81bd80d1c5ba2167b8123a04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54a3b7e0866723235bdb4c7906fe4a16ea65f5fa81bd80d1c5ba2167b8123a04","first_computed_at":"2026-07-05T07:25:21.131245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:25:21.131245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"irwUnKTbV7kcZcms4kcQL+NtVBP7q0UGTEKTIPxLPP2kSYt5pYrUhu94BQbJ3EiAKeuXT01VtHX3i7KhmFU8AA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:25:21.131717Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.15466","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba93a1ac82aa897d8b65f541600a5d2a5d1a1ae0cba7a879c1863a9b852e26f1","sha256:1bcb3902a27bc62d9efc700452bb81c9a614e3e43021ac779d7cf3f75a39642c"],"state_sha256":"d0e4f7d44f25d0188c686df363e03ffafe1beb00c9d3595501ae7e94d243ee1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8JIYbR8iA+4mOotSsi0rhjkxIxnUjZIVOjaG2nBLSKSICbXoaFVxVvL6nLL1OK09KscX9WkHKi0RqDkficK/DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T04:49:53.016237Z","bundle_sha256":"8e679a155129cdc6f5e40397e692cb3991d912168e1ccc35f746ec5539e7d130"}}