{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z4BVGFX4TF6FSMDUTPWWPDPIZH","short_pith_number":"pith:Z4BVGFX4","schema_version":"1.0","canonical_sha256":"cf035316fc997c5930749bed678de8c9df3e4a05aab84e960480f97a975f1b88","source":{"kind":"arxiv","id":"2505.04775","version":2},"attestation_state":"computed","paper":{"title":"Prediction via Shapley Value Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amr Alkhatib, Henrik Bostr\\\"om, Michalis Vazirgiannis, Roman Bresson","submitted_at":"2025-05-07T19:51:17Z","abstract_excerpt":"Shapley values have several desirable, theoretically well-supported, properties for explaining black-box model predictions. Traditionally, Shapley values are computed post-hoc, leading to additional computational cost at inference time. To overcome this, a novel method, called ViaSHAP, is proposed, that learns a function to compute Shapley values, from which the predictions can be derived directly by summation. Two approaches to implement the proposed method are explored; one based on the universal approximation theorem and the other on the Kolmogorov-Arnold representation theorem. Results fro"},"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":"2505.04775","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-07T19:51:17Z","cross_cats_sorted":[],"title_canon_sha256":"31012bcedf151c9eb7a7c24d7a93999afaee96ed7f5c904ed4b618df50e9a401","abstract_canon_sha256":"41f18a1049f29abce8839a47b620d6dadb6d2b3bc3207bd8921f8b3439e24d4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:55.799182Z","signature_b64":"KGjKfo/3yfaa0CkBcUQyLEu5nWzkqafHJ1ly/BrJOJGAYCfcE3yGb88aRH6snUB0eewywrUlavzYLNqxH0jDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf035316fc997c5930749bed678de8c9df3e4a05aab84e960480f97a975f1b88","last_reissued_at":"2026-07-05T11:36:55.798660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:55.798660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prediction via Shapley Value Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amr Alkhatib, Henrik Bostr\\\"om, Michalis Vazirgiannis, Roman Bresson","submitted_at":"2025-05-07T19:51:17Z","abstract_excerpt":"Shapley values have several desirable, theoretically well-supported, properties for explaining black-box model predictions. Traditionally, Shapley values are computed post-hoc, leading to additional computational cost at inference time. To overcome this, a novel method, called ViaSHAP, is proposed, that learns a function to compute Shapley values, from which the predictions can be derived directly by summation. Two approaches to implement the proposed method are explored; one based on the universal approximation theorem and the other on the Kolmogorov-Arnold representation theorem. Results fro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04775","kind":"arxiv","version":2},"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/2505.04775/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":"2505.04775","created_at":"2026-07-05T11:36:55.798717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04775v2","created_at":"2026-07-05T11:36:55.798717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04775","created_at":"2026-07-05T11:36:55.798717+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z4BVGFX4TF6F","created_at":"2026-07-05T11:36:55.798717+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z4BVGFX4TF6FSMDU","created_at":"2026-07-05T11:36:55.798717+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z4BVGFX4","created_at":"2026-07-05T11:36:55.798717+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/Z4BVGFX4TF6FSMDUTPWWPDPIZH","json":"https://pith.science/pith/Z4BVGFX4TF6FSMDUTPWWPDPIZH.json","graph_json":"https://pith.science/api/pith-number/Z4BVGFX4TF6FSMDUTPWWPDPIZH/graph.json","events_json":"https://pith.science/api/pith-number/Z4BVGFX4TF6FSMDUTPWWPDPIZH/events.json","paper":"https://pith.science/paper/Z4BVGFX4"},"agent_actions":{"view_html":"https://pith.science/pith/Z4BVGFX4TF6FSMDUTPWWPDPIZH","download_json":"https://pith.science/pith/Z4BVGFX4TF6FSMDUTPWWPDPIZH.json","view_paper":"https://pith.science/paper/Z4BVGFX4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04775&json=true","fetch_graph":"https://pith.science/api/pith-number/Z4BVGFX4TF6FSMDUTPWWPDPIZH/graph.json","fetch_events":"https://pith.science/api/pith-number/Z4BVGFX4TF6FSMDUTPWWPDPIZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z4BVGFX4TF6FSMDUTPWWPDPIZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z4BVGFX4TF6FSMDUTPWWPDPIZH/action/storage_attestation","attest_author":"https://pith.science/pith/Z4BVGFX4TF6FSMDUTPWWPDPIZH/action/author_attestation","sign_citation":"https://pith.science/pith/Z4BVGFX4TF6FSMDUTPWWPDPIZH/action/citation_signature","submit_replication":"https://pith.science/pith/Z4BVGFX4TF6FSMDUTPWWPDPIZH/action/replication_record"}},"created_at":"2026-07-05T11:36:55.798717+00:00","updated_at":"2026-07-05T11:36:55.798717+00:00"}