{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VA3NFOT7KOBGT6AULOKXQN5LXO","short_pith_number":"pith:VA3NFOT7","schema_version":"1.0","canonical_sha256":"a836d2ba7f538269f8145b957837abbbaefe75e1ee217f24cc5a8f5cfd60e251","source":{"kind":"arxiv","id":"2607.03374","version":1},"attestation_state":"computed","paper":{"title":"An Asymptotic Analysis of the Shapley Value for Dataset Valuation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.GT","authors_text":"Benjamin Heymann, Maxime Vono, M\\'elissa Tamine, Patrick Loiseau","submitted_at":"2026-07-03T14:28:25Z","abstract_excerpt":"We propose an asymptotic analysis of the Shapley value in a dataset valuation setting in which utilities are modeled as smooth functionals of empirical distributions via reproducing kernel Hilbert space (RKHS) mean embeddings. We prove that, despite its combinatorial definition, the Shapley value of a data source is asymptotically captured by a simple leading term. This term can be interpreted as the first-order contribution of a dataset relative to the surrounding data population. It also identifies the scale of the Shapley value as the number of data sources grows and provides a framework fo"},"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":"2607.03374","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.GT","submitted_at":"2026-07-03T14:28:25Z","cross_cats_sorted":[],"title_canon_sha256":"ba66ae799c6b3be302dae192b7c5d146a2116a3072311c5e0a4f23faeeb2d8b8","abstract_canon_sha256":"8141db70ed4c83e66cec384f1612bb10ba44668c423f4d38fb5124fe70f5e0e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:17:40.149126Z","signature_b64":"KOh516hQcyIZ9HAhNnaR8L0HSk8fVclK7EQ36QpsGgzBKWlFh4O0UuyENZOdPqHvZUZCF+UKp3+mB2AOQjB8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a836d2ba7f538269f8145b957837abbbaefe75e1ee217f24cc5a8f5cfd60e251","last_reissued_at":"2026-07-07T02:17:40.148532Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:17:40.148532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Asymptotic Analysis of the Shapley Value for Dataset Valuation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.GT","authors_text":"Benjamin Heymann, Maxime Vono, M\\'elissa Tamine, Patrick Loiseau","submitted_at":"2026-07-03T14:28:25Z","abstract_excerpt":"We propose an asymptotic analysis of the Shapley value in a dataset valuation setting in which utilities are modeled as smooth functionals of empirical distributions via reproducing kernel Hilbert space (RKHS) mean embeddings. We prove that, despite its combinatorial definition, the Shapley value of a data source is asymptotically captured by a simple leading term. This term can be interpreted as the first-order contribution of a dataset relative to the surrounding data population. It also identifies the scale of the Shapley value as the number of data sources grows and provides a framework fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03374","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/2607.03374/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":"2607.03374","created_at":"2026-07-07T02:17:40.148614+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.03374v1","created_at":"2026-07-07T02:17:40.148614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03374","created_at":"2026-07-07T02:17:40.148614+00:00"},{"alias_kind":"pith_short_12","alias_value":"VA3NFOT7KOBG","created_at":"2026-07-07T02:17:40.148614+00:00"},{"alias_kind":"pith_short_16","alias_value":"VA3NFOT7KOBGT6AU","created_at":"2026-07-07T02:17:40.148614+00:00"},{"alias_kind":"pith_short_8","alias_value":"VA3NFOT7","created_at":"2026-07-07T02:17:40.148614+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/VA3NFOT7KOBGT6AULOKXQN5LXO","json":"https://pith.science/pith/VA3NFOT7KOBGT6AULOKXQN5LXO.json","graph_json":"https://pith.science/api/pith-number/VA3NFOT7KOBGT6AULOKXQN5LXO/graph.json","events_json":"https://pith.science/api/pith-number/VA3NFOT7KOBGT6AULOKXQN5LXO/events.json","paper":"https://pith.science/paper/VA3NFOT7"},"agent_actions":{"view_html":"https://pith.science/pith/VA3NFOT7KOBGT6AULOKXQN5LXO","download_json":"https://pith.science/pith/VA3NFOT7KOBGT6AULOKXQN5LXO.json","view_paper":"https://pith.science/paper/VA3NFOT7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.03374&json=true","fetch_graph":"https://pith.science/api/pith-number/VA3NFOT7KOBGT6AULOKXQN5LXO/graph.json","fetch_events":"https://pith.science/api/pith-number/VA3NFOT7KOBGT6AULOKXQN5LXO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VA3NFOT7KOBGT6AULOKXQN5LXO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VA3NFOT7KOBGT6AULOKXQN5LXO/action/storage_attestation","attest_author":"https://pith.science/pith/VA3NFOT7KOBGT6AULOKXQN5LXO/action/author_attestation","sign_citation":"https://pith.science/pith/VA3NFOT7KOBGT6AULOKXQN5LXO/action/citation_signature","submit_replication":"https://pith.science/pith/VA3NFOT7KOBGT6AULOKXQN5LXO/action/replication_record"}},"created_at":"2026-07-07T02:17:40.148614+00:00","updated_at":"2026-07-07T02:17:40.148614+00:00"}