{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ECXNMI6RILUWYDRTVP2B2ADIH3","short_pith_number":"pith:ECXNMI6R","canonical_record":{"source":{"id":"2002.12334","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-27T18:51:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"86203da7f152adb2aa34419a88abe02f85ebd40b4c27b143eb79118d80fb04f2","abstract_canon_sha256":"3eb62f2ee4f86360789450814dd19e5c51f241ec979cd67d5ea40eba1408f2ea"},"schema_version":"1.0"},"canonical_sha256":"20aed623d142e96c0e33abf41d00683ec06b5a43c99f391cecc434a204b37424","source":{"kind":"arxiv","id":"2002.12334","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.12334","created_at":"2026-07-05T00:44:23Z"},{"alias_kind":"arxiv_version","alias_value":"2002.12334v1","created_at":"2026-07-05T00:44:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.12334","created_at":"2026-07-05T00:44:23Z"},{"alias_kind":"pith_short_12","alias_value":"ECXNMI6RILUW","created_at":"2026-07-05T00:44:23Z"},{"alias_kind":"pith_short_16","alias_value":"ECXNMI6RILUWYDRT","created_at":"2026-07-05T00:44:23Z"},{"alias_kind":"pith_short_8","alias_value":"ECXNMI6R","created_at":"2026-07-05T00:44:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ECXNMI6RILUWYDRTVP2B2ADIH3","target":"record","payload":{"canonical_record":{"source":{"id":"2002.12334","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-27T18:51:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"86203da7f152adb2aa34419a88abe02f85ebd40b4c27b143eb79118d80fb04f2","abstract_canon_sha256":"3eb62f2ee4f86360789450814dd19e5c51f241ec979cd67d5ea40eba1408f2ea"},"schema_version":"1.0"},"canonical_sha256":"20aed623d142e96c0e33abf41d00683ec06b5a43c99f391cecc434a204b37424","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:23.047042Z","signature_b64":"CX94VQURZrjr8zxAfYgXlgZ+QwtEUqL4Y6sfKtezdC5T4S+JqvyBEpzbEivNgdMQZ65BM7i6UndpKRq/aQGRBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20aed623d142e96c0e33abf41d00683ec06b5a43c99f391cecc434a204b37424","last_reissued_at":"2026-07-05T00:44:23.046611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:23.046611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.12334","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":"2026-07-05T00:44:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hUy+CcBQUIEhv/yR/dwWhputqttRVXw25LxoRALJj9luXTjxYdijuRpceqyOOTLyECT1rfbiKJP9aiiM9vR+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:17:37.809357Z"},"content_sha256":"358e97526f848ded129e9a58ee964a93e5de2f2e39c56672eafb220bdaea6635","schema_version":"1.0","event_id":"sha256:358e97526f848ded129e9a58ee964a93e5de2f2e39c56672eafb220bdaea6635"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ECXNMI6RILUWYDRTVP2B2ADIH3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Distributional Framework for Data Valuation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amirata Ghorbani, James Zou, Michael P. Kim","submitted_at":"2020-02-27T18:51:35Z","abstract_excerpt":"Shapley value is a classic notion from game theory, historically used to quantify the contributions of individuals within groups, and more recently applied to assign values to data points when training machine learning models. Despite its foundational role, a key limitation of the data Shapley framework is that it only provides valuations for points within a fixed data set. It does not account for statistical aspects of the data and does not give a way to reason about points outside the data set. To address these limitations, we propose a novel framework -- distributional Shapley -- where the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.12334","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/2002.12334/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":"2026-07-05T00:44:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k8WGPyCzhRbAVmwItJt8kNLKw4ynmjQv1lnzgTW5VKEDqqfNrWrbncWQ4g7JFzUWCqSrTzuo09vYLd8OpFFRDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:17:37.809886Z"},"content_sha256":"3e7021161ae568a5e416c597e0f97223b5e9288021378f0f680a180d1183f2f4","schema_version":"1.0","event_id":"sha256:3e7021161ae568a5e416c597e0f97223b5e9288021378f0f680a180d1183f2f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ECXNMI6RILUWYDRTVP2B2ADIH3/bundle.json","state_url":"https://pith.science/pith/ECXNMI6RILUWYDRTVP2B2ADIH3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ECXNMI6RILUWYDRTVP2B2ADIH3/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":"2026-08-08T19:17:37Z","links":{"resolver":"https://pith.science/pith/ECXNMI6RILUWYDRTVP2B2ADIH3","bundle":"https://pith.science/pith/ECXNMI6RILUWYDRTVP2B2ADIH3/bundle.json","state":"https://pith.science/pith/ECXNMI6RILUWYDRTVP2B2ADIH3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ECXNMI6RILUWYDRTVP2B2ADIH3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ECXNMI6RILUWYDRTVP2B2ADIH3","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":"3eb62f2ee4f86360789450814dd19e5c51f241ec979cd67d5ea40eba1408f2ea","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-27T18:51:35Z","title_canon_sha256":"86203da7f152adb2aa34419a88abe02f85ebd40b4c27b143eb79118d80fb04f2"},"schema_version":"1.0","source":{"id":"2002.12334","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.12334","created_at":"2026-07-05T00:44:23Z"},{"alias_kind":"arxiv_version","alias_value":"2002.12334v1","created_at":"2026-07-05T00:44:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.12334","created_at":"2026-07-05T00:44:23Z"},{"alias_kind":"pith_short_12","alias_value":"ECXNMI6RILUW","created_at":"2026-07-05T00:44:23Z"},{"alias_kind":"pith_short_16","alias_value":"ECXNMI6RILUWYDRT","created_at":"2026-07-05T00:44:23Z"},{"alias_kind":"pith_short_8","alias_value":"ECXNMI6R","created_at":"2026-07-05T00:44:23Z"}],"graph_snapshots":[{"event_id":"sha256:3e7021161ae568a5e416c597e0f97223b5e9288021378f0f680a180d1183f2f4","target":"graph","created_at":"2026-07-05T00:44:23Z","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/2002.12334/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Shapley value is a classic notion from game theory, historically used to quantify the contributions of individuals within groups, and more recently applied to assign values to data points when training machine learning models. Despite its foundational role, a key limitation of the data Shapley framework is that it only provides valuations for points within a fixed data set. It does not account for statistical aspects of the data and does not give a way to reason about points outside the data set. To address these limitations, we propose a novel framework -- distributional Shapley -- where the ","authors_text":"Amirata Ghorbani, James Zou, Michael P. Kim","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-27T18:51:35Z","title":"A Distributional Framework for Data Valuation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.12334","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":"sha256:358e97526f848ded129e9a58ee964a93e5de2f2e39c56672eafb220bdaea6635","target":"record","created_at":"2026-07-05T00:44:23Z","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":"3eb62f2ee4f86360789450814dd19e5c51f241ec979cd67d5ea40eba1408f2ea","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-27T18:51:35Z","title_canon_sha256":"86203da7f152adb2aa34419a88abe02f85ebd40b4c27b143eb79118d80fb04f2"},"schema_version":"1.0","source":{"id":"2002.12334","kind":"arxiv","version":1}},"canonical_sha256":"20aed623d142e96c0e33abf41d00683ec06b5a43c99f391cecc434a204b37424","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20aed623d142e96c0e33abf41d00683ec06b5a43c99f391cecc434a204b37424","first_computed_at":"2026-07-05T00:44:23.046611Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:44:23.046611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CX94VQURZrjr8zxAfYgXlgZ+QwtEUqL4Y6sfKtezdC5T4S+JqvyBEpzbEivNgdMQZ65BM7i6UndpKRq/aQGRBw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:44:23.047042Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.12334","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:358e97526f848ded129e9a58ee964a93e5de2f2e39c56672eafb220bdaea6635","sha256:3e7021161ae568a5e416c597e0f97223b5e9288021378f0f680a180d1183f2f4"],"state_sha256":"2e56c4441a340dfeed985adfb2376d0705e691273c1ce72e9ebd8ee3dc526b05"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kxklc+jFsiCjiiQJqq1eYU0/nHlPSSUaAzaL2m9qrbv2GxJ8rJj4uuGKopnJjvwa5dVyOCwG0+mqClxKB7D/Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:17:37.814689Z","bundle_sha256":"f3563ccd7cbff467e3db0701e6305288c3345262a17df279b6ea7327c4cfbbbd"}}