{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FVD2FTN7FOBU35LABNIAJ2CYWO","short_pith_number":"pith:FVD2FTN7","schema_version":"1.0","canonical_sha256":"2d47a2cdbf2b834df5600b5004e858b3b9e868e3702e192eee988cfae55dd42d","source":{"kind":"arxiv","id":"2405.18253","version":3},"attestation_state":"computed","paper":{"title":"Proper Dataset Valuation by Pointwise Mutual Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"James Zou, Rui Ray Chen, Shuran Zheng, Xuan Qi, Yongchan Kwon","submitted_at":"2024-05-28T15:04:17Z","abstract_excerpt":"Data plays a central role in advancements in modern artificial intelligence, with high-quality data emerging as a key driver of model performance. This has prompted the development of principled and effective data curation methods in recent years. However, existing methods largely rely on heuristics, and whether they are truly effective remains unclear. For instance, standard evaluation methods that assess a trained model's performance on specific benchmarks may incentivize assigning high scores to data that merely resembles the test set. This issue exemplifies Goodhart's law: when a measure b"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.18253","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T15:04:17Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"1a609013f8aa6e85b0d23c09495307feff3bdc394f627bf5e511b7cb5df41b44","abstract_canon_sha256":"7792378a56be7e8cc133453212ecfc7de2057f6680e66bd7bead1046f9b25e47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:32.275681Z","signature_b64":"3guNop2Axp8Gjb+WGoLDDGnkldnO0tkM4U8p1/jOIKZlMe/bR+03YNKWu0Cd6EfYCGnQfzXAUGWiDFnJqwA8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d47a2cdbf2b834df5600b5004e858b3b9e868e3702e192eee988cfae55dd42d","last_reissued_at":"2026-07-05T11:11:32.275133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:32.275133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Proper Dataset Valuation by Pointwise Mutual Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"James Zou, Rui Ray Chen, Shuran Zheng, Xuan Qi, Yongchan Kwon","submitted_at":"2024-05-28T15:04:17Z","abstract_excerpt":"Data plays a central role in advancements in modern artificial intelligence, with high-quality data emerging as a key driver of model performance. This has prompted the development of principled and effective data curation methods in recent years. However, existing methods largely rely on heuristics, and whether they are truly effective remains unclear. For instance, standard evaluation methods that assess a trained model's performance on specific benchmarks may incentivize assigning high scores to data that merely resembles the test set. This issue exemplifies Goodhart's law: when a measure b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18253","kind":"arxiv","version":3},"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/2405.18253/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.18253","created_at":"2026-07-05T11:11:32.275208+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18253v3","created_at":"2026-07-05T11:11:32.275208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18253","created_at":"2026-07-05T11:11:32.275208+00:00"},{"alias_kind":"pith_short_12","alias_value":"FVD2FTN7FOBU","created_at":"2026-07-05T11:11:32.275208+00:00"},{"alias_kind":"pith_short_16","alias_value":"FVD2FTN7FOBU35LA","created_at":"2026-07-05T11:11:32.275208+00:00"},{"alias_kind":"pith_short_8","alias_value":"FVD2FTN7","created_at":"2026-07-05T11:11:32.275208+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.21794","citing_title":"Multi-agent Adaptive Mechanism Design","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FVD2FTN7FOBU35LABNIAJ2CYWO","json":"https://pith.science/pith/FVD2FTN7FOBU35LABNIAJ2CYWO.json","graph_json":"https://pith.science/api/pith-number/FVD2FTN7FOBU35LABNIAJ2CYWO/graph.json","events_json":"https://pith.science/api/pith-number/FVD2FTN7FOBU35LABNIAJ2CYWO/events.json","paper":"https://pith.science/paper/FVD2FTN7"},"agent_actions":{"view_html":"https://pith.science/pith/FVD2FTN7FOBU35LABNIAJ2CYWO","download_json":"https://pith.science/pith/FVD2FTN7FOBU35LABNIAJ2CYWO.json","view_paper":"https://pith.science/paper/FVD2FTN7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18253&json=true","fetch_graph":"https://pith.science/api/pith-number/FVD2FTN7FOBU35LABNIAJ2CYWO/graph.json","fetch_events":"https://pith.science/api/pith-number/FVD2FTN7FOBU35LABNIAJ2CYWO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FVD2FTN7FOBU35LABNIAJ2CYWO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FVD2FTN7FOBU35LABNIAJ2CYWO/action/storage_attestation","attest_author":"https://pith.science/pith/FVD2FTN7FOBU35LABNIAJ2CYWO/action/author_attestation","sign_citation":"https://pith.science/pith/FVD2FTN7FOBU35LABNIAJ2CYWO/action/citation_signature","submit_replication":"https://pith.science/pith/FVD2FTN7FOBU35LABNIAJ2CYWO/action/replication_record"}},"created_at":"2026-07-05T11:11:32.275208+00:00","updated_at":"2026-07-05T11:11:32.275208+00:00"}