{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UP3EEE6WSVVNIUJEGYY7ZRA4AT","short_pith_number":"pith:UP3EEE6W","schema_version":"1.0","canonical_sha256":"a3f64213d6956ad451243631fcc41c04cfa418a65db7e9ce9117ab2580f20132","source":{"kind":"arxiv","id":"2506.04026","version":1},"attestation_state":"computed","paper":{"title":"On the Usage of Gaussian Process for Efficient Data Valuation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ath\\'ena\\\"is Gautier, Cl\\'ement B\\'enesse, Patrick Mesana, S\\'ebastien Gambs","submitted_at":"2025-06-04T14:53:51Z","abstract_excerpt":"In machine learning, knowing the impact of a given datum on model training is a fundamental task referred to as Data Valuation. Building on previous works from the literature, we have designed a novel canonical decomposition allowing practitioners to analyze any data valuation method as the combination of two parts: a utility function that captures characteristics from a given model and an aggregation procedure that merges such information. We also propose to use Gaussian Processes as a means to easily access the utility function on ``sub-models'', which are models trained on a subset of the t"},"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":"2506.04026","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-04T14:53:51Z","cross_cats_sorted":[],"title_canon_sha256":"afe3a5cb2e5633d743e3e0dda0d1b2c4056fdc72bf1add824cd0dd78522792fc","abstract_canon_sha256":"fd7efd40ca93c0c724be3c3cfe5cc1556a12a1be530c037e6b9f4c53ba3ccccf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:55.661532Z","signature_b64":"qf4kXiO7VF9Ljdeq4TlfVimN6RwEwxMpOg/v7ZPlxmw28DqqXYu7xdv3HE31nCrsAJ4OrhpGGgzM3D9v8ZFVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3f64213d6956ad451243631fcc41c04cfa418a65db7e9ce9117ab2580f20132","last_reissued_at":"2026-07-05T11:15:55.661009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:55.661009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Usage of Gaussian Process for Efficient Data Valuation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ath\\'ena\\\"is Gautier, Cl\\'ement B\\'enesse, Patrick Mesana, S\\'ebastien Gambs","submitted_at":"2025-06-04T14:53:51Z","abstract_excerpt":"In machine learning, knowing the impact of a given datum on model training is a fundamental task referred to as Data Valuation. Building on previous works from the literature, we have designed a novel canonical decomposition allowing practitioners to analyze any data valuation method as the combination of two parts: a utility function that captures characteristics from a given model and an aggregation procedure that merges such information. We also propose to use Gaussian Processes as a means to easily access the utility function on ``sub-models'', which are models trained on a subset of the t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04026","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/2506.04026/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":"2506.04026","created_at":"2026-07-05T11:15:55.661069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04026v1","created_at":"2026-07-05T11:15:55.661069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04026","created_at":"2026-07-05T11:15:55.661069+00:00"},{"alias_kind":"pith_short_12","alias_value":"UP3EEE6WSVVN","created_at":"2026-07-05T11:15:55.661069+00:00"},{"alias_kind":"pith_short_16","alias_value":"UP3EEE6WSVVNIUJE","created_at":"2026-07-05T11:15:55.661069+00:00"},{"alias_kind":"pith_short_8","alias_value":"UP3EEE6W","created_at":"2026-07-05T11:15:55.661069+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UP3EEE6WSVVNIUJEGYY7ZRA4AT","json":"https://pith.science/pith/UP3EEE6WSVVNIUJEGYY7ZRA4AT.json","graph_json":"https://pith.science/api/pith-number/UP3EEE6WSVVNIUJEGYY7ZRA4AT/graph.json","events_json":"https://pith.science/api/pith-number/UP3EEE6WSVVNIUJEGYY7ZRA4AT/events.json","paper":"https://pith.science/paper/UP3EEE6W"},"agent_actions":{"view_html":"https://pith.science/pith/UP3EEE6WSVVNIUJEGYY7ZRA4AT","download_json":"https://pith.science/pith/UP3EEE6WSVVNIUJEGYY7ZRA4AT.json","view_paper":"https://pith.science/paper/UP3EEE6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04026&json=true","fetch_graph":"https://pith.science/api/pith-number/UP3EEE6WSVVNIUJEGYY7ZRA4AT/graph.json","fetch_events":"https://pith.science/api/pith-number/UP3EEE6WSVVNIUJEGYY7ZRA4AT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UP3EEE6WSVVNIUJEGYY7ZRA4AT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UP3EEE6WSVVNIUJEGYY7ZRA4AT/action/storage_attestation","attest_author":"https://pith.science/pith/UP3EEE6WSVVNIUJEGYY7ZRA4AT/action/author_attestation","sign_citation":"https://pith.science/pith/UP3EEE6WSVVNIUJEGYY7ZRA4AT/action/citation_signature","submit_replication":"https://pith.science/pith/UP3EEE6WSVVNIUJEGYY7ZRA4AT/action/replication_record"}},"created_at":"2026-07-05T11:15:55.661069+00:00","updated_at":"2026-07-05T11:15:55.661069+00:00"}