{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6A5FVFJCVOJ6DPSLX267PYJNHE","short_pith_number":"pith:6A5FVFJC","canonical_record":{"source":{"id":"2405.03875","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T21:46:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"61bd99fd9e5ec81d63fa4269891ad3d6d07c4e0d8bdca186c9c1b642c61d17ad","abstract_canon_sha256":"a947797af276f18f6c81e13c98249fb579b6b5000fc35d40c3039353cd511910"},"schema_version":"1.0"},"canonical_sha256":"f03a5a9522ab93e1be4bbebdf7e12d3918abc94718dbea153ce65db2c1e210a7","source":{"kind":"arxiv","id":"2405.03875","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03875","created_at":"2026-07-05T08:16:12Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03875v1","created_at":"2026-07-05T08:16:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03875","created_at":"2026-07-05T08:16:12Z"},{"alias_kind":"pith_short_12","alias_value":"6A5FVFJCVOJ6","created_at":"2026-07-05T08:16:12Z"},{"alias_kind":"pith_short_16","alias_value":"6A5FVFJCVOJ6DPSL","created_at":"2026-07-05T08:16:12Z"},{"alias_kind":"pith_short_8","alias_value":"6A5FVFJC","created_at":"2026-07-05T08:16:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6A5FVFJCVOJ6DPSLX267PYJNHE","target":"record","payload":{"canonical_record":{"source":{"id":"2405.03875","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T21:46:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"61bd99fd9e5ec81d63fa4269891ad3d6d07c4e0d8bdca186c9c1b642c61d17ad","abstract_canon_sha256":"a947797af276f18f6c81e13c98249fb579b6b5000fc35d40c3039353cd511910"},"schema_version":"1.0"},"canonical_sha256":"f03a5a9522ab93e1be4bbebdf7e12d3918abc94718dbea153ce65db2c1e210a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:12.129720Z","signature_b64":"7vmcffPGAVQsv/9erxsGMxI2AE7lQUp8+d+5yYXOobB4uv3MCxmGyL7Psv+4xwSPB7coUy69n+ZppbxujA2NAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f03a5a9522ab93e1be4bbebdf7e12d3918abc94718dbea153ce65db2c1e210a7","last_reissued_at":"2026-07-05T08:16:12.129211Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:12.129211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.03875","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":"2026-07-05T08:16:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ja2eFFkEL72qzxnP5uO901lMGJkM7RAGR7Fotr/om3LvRHsNB228Yi5c4H64UKeBw7m0mUonbGCPugqEVkziCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:59:24.180088Z"},"content_sha256":"8915b678afeb9deab770b033b349778d1381d7b92fd51b3a64faad34060c2c00","schema_version":"1.0","event_id":"sha256:8915b678afeb9deab770b033b349778d1381d7b92fd51b3a64faad34060c2c00"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6A5FVFJCVOJ6DPSLX267PYJNHE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking Data Shapley for Data Selection Tasks: Misleads and Merits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"James Zou, Jiachen T. Wang, Ruoxi Jia, Tianji Yang, Yongchan Kwon","submitted_at":"2024-05-06T21:46:10Z","abstract_excerpt":"Data Shapley provides a principled approach to data valuation and plays a crucial role in data-centric machine learning (ML) research. Data selection is considered a standard application of Data Shapley. However, its data selection performance has shown to be inconsistent across settings in the literature. This study aims to deepen our understanding of this phenomenon. We introduce a hypothesis testing framework and show that Data Shapley's performance can be no better than random selection without specific constraints on utility functions. We identify a class of utility functions, monotonical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03875","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/2405.03875/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":"2026-07-05T08:16:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q43yhnzgwAn0cYpCJRi1LH4fMHspFwqwU8ANfd1YUOqmbkgV/DCpKvjQtjTG0HYDDsa1uApbE1UrWsQ3sQB7Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:59:24.180583Z"},"content_sha256":"89e79b7fd47516168f6916b9f1cbe01533246b336345f6a5380599274914ec95","schema_version":"1.0","event_id":"sha256:89e79b7fd47516168f6916b9f1cbe01533246b336345f6a5380599274914ec95"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6A5FVFJCVOJ6DPSLX267PYJNHE/bundle.json","state_url":"https://pith.science/pith/6A5FVFJCVOJ6DPSLX267PYJNHE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6A5FVFJCVOJ6DPSLX267PYJNHE/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":"2026-08-08T13:59:24Z","links":{"resolver":"https://pith.science/pith/6A5FVFJCVOJ6DPSLX267PYJNHE","bundle":"https://pith.science/pith/6A5FVFJCVOJ6DPSLX267PYJNHE/bundle.json","state":"https://pith.science/pith/6A5FVFJCVOJ6DPSLX267PYJNHE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6A5FVFJCVOJ6DPSLX267PYJNHE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6A5FVFJCVOJ6DPSLX267PYJNHE","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":"a947797af276f18f6c81e13c98249fb579b6b5000fc35d40c3039353cd511910","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T21:46:10Z","title_canon_sha256":"61bd99fd9e5ec81d63fa4269891ad3d6d07c4e0d8bdca186c9c1b642c61d17ad"},"schema_version":"1.0","source":{"id":"2405.03875","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03875","created_at":"2026-07-05T08:16:12Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03875v1","created_at":"2026-07-05T08:16:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03875","created_at":"2026-07-05T08:16:12Z"},{"alias_kind":"pith_short_12","alias_value":"6A5FVFJCVOJ6","created_at":"2026-07-05T08:16:12Z"},{"alias_kind":"pith_short_16","alias_value":"6A5FVFJCVOJ6DPSL","created_at":"2026-07-05T08:16:12Z"},{"alias_kind":"pith_short_8","alias_value":"6A5FVFJC","created_at":"2026-07-05T08:16:12Z"}],"graph_snapshots":[{"event_id":"sha256:89e79b7fd47516168f6916b9f1cbe01533246b336345f6a5380599274914ec95","target":"graph","created_at":"2026-07-05T08:16:12Z","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/2405.03875/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data Shapley provides a principled approach to data valuation and plays a crucial role in data-centric machine learning (ML) research. Data selection is considered a standard application of Data Shapley. However, its data selection performance has shown to be inconsistent across settings in the literature. This study aims to deepen our understanding of this phenomenon. We introduce a hypothesis testing framework and show that Data Shapley's performance can be no better than random selection without specific constraints on utility functions. We identify a class of utility functions, monotonical","authors_text":"James Zou, Jiachen T. Wang, Ruoxi Jia, Tianji Yang, Yongchan Kwon","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T21:46:10Z","title":"Rethinking Data Shapley for Data Selection Tasks: Misleads and Merits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03875","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":"sha256:8915b678afeb9deab770b033b349778d1381d7b92fd51b3a64faad34060c2c00","target":"record","created_at":"2026-07-05T08:16:12Z","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":"a947797af276f18f6c81e13c98249fb579b6b5000fc35d40c3039353cd511910","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T21:46:10Z","title_canon_sha256":"61bd99fd9e5ec81d63fa4269891ad3d6d07c4e0d8bdca186c9c1b642c61d17ad"},"schema_version":"1.0","source":{"id":"2405.03875","kind":"arxiv","version":1}},"canonical_sha256":"f03a5a9522ab93e1be4bbebdf7e12d3918abc94718dbea153ce65db2c1e210a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f03a5a9522ab93e1be4bbebdf7e12d3918abc94718dbea153ce65db2c1e210a7","first_computed_at":"2026-07-05T08:16:12.129211Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:12.129211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7vmcffPGAVQsv/9erxsGMxI2AE7lQUp8+d+5yYXOobB4uv3MCxmGyL7Psv+4xwSPB7coUy69n+ZppbxujA2NAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:12.129720Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.03875","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8915b678afeb9deab770b033b349778d1381d7b92fd51b3a64faad34060c2c00","sha256:89e79b7fd47516168f6916b9f1cbe01533246b336345f6a5380599274914ec95"],"state_sha256":"d2eb04a621daefd48cbbe3356795588a0ef8b787d4e0025d93de1d416f82981f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ukxyOI5QrO2YxiUVlhcyPQrk73N0QJh6EluQXs2Q0hryrJaFvZZ6QFXsq932xcui4xLw1LDlBXosIYyAhSugBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:59:24.184816Z","bundle_sha256":"45975d357fbda683f72a3eb0444243e4e790e931cd079bcce265295c8a8ce8a4"}}