{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AHSFNLW3DVHNEDUBZ5E7NII6PZ","short_pith_number":"pith:AHSFNLW3","schema_version":"1.0","canonical_sha256":"01e456aedb1d4ed20e81cf49f6a11e7e73a30da46a41aac575e470876e41bf0b","source":{"kind":"arxiv","id":"2510.22138","version":3},"attestation_state":"computed","paper":{"title":"Tractable Shapley Values and Interactions via Tensor Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Li, Farzaneh Heidari, Guillaume Rabusseau","submitted_at":"2025-10-25T03:21:20Z","abstract_excerpt":"We show how to replace the O(2^n) coalition enumeration over n features behind Shapley values and Shapley-style interaction indices with a few-evaluation scheme on a tensor-network (TN) surrogate: TN-SHAP. The key idea is to represent a predictor's local behavior as a factorized multilinear map, so that coalitional quantities become linear probes of a coefficient tensor. TN-SHAP replaces exhaustive coalition sweeps with just a small number of targeted evaluations to extract order-k Shapley interactions. In particular, both order-1 (single-feature) and order-2 (pairwise) computations have cost "},"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":"2510.22138","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-25T03:21:20Z","cross_cats_sorted":[],"title_canon_sha256":"b0de10b219bedc7ae4605d6b4c13fc4262bd667ab88a28bd51023df64b664183","abstract_canon_sha256":"25441efc951383b76f551445400dde3d1cd71ad6db2b975f7cc236d992defe59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:10.300290Z","signature_b64":"UbwF9bSCIhFmJriMpwsrtdJVO75reF42zHqZ2yth2gnzOnrTWh5cavZCVN++iMNyfx9AJVt1doo2LthBj6AnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01e456aedb1d4ed20e81cf49f6a11e7e73a30da46a41aac575e470876e41bf0b","last_reissued_at":"2026-06-02T02:04:10.299794Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:10.299794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tractable Shapley Values and Interactions via Tensor Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Li, Farzaneh Heidari, Guillaume Rabusseau","submitted_at":"2025-10-25T03:21:20Z","abstract_excerpt":"We show how to replace the O(2^n) coalition enumeration over n features behind Shapley values and Shapley-style interaction indices with a few-evaluation scheme on a tensor-network (TN) surrogate: TN-SHAP. The key idea is to represent a predictor's local behavior as a factorized multilinear map, so that coalitional quantities become linear probes of a coefficient tensor. TN-SHAP replaces exhaustive coalition sweeps with just a small number of targeted evaluations to extract order-k Shapley interactions. In particular, both order-1 (single-feature) and order-2 (pairwise) computations have cost "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.22138","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/2510.22138/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":"2510.22138","created_at":"2026-06-02T02:04:10.299855+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.22138v3","created_at":"2026-06-02T02:04:10.299855+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.22138","created_at":"2026-06-02T02:04:10.299855+00:00"},{"alias_kind":"pith_short_12","alias_value":"AHSFNLW3DVHN","created_at":"2026-06-02T02:04:10.299855+00:00"},{"alias_kind":"pith_short_16","alias_value":"AHSFNLW3DVHNEDUB","created_at":"2026-06-02T02:04:10.299855+00:00"},{"alias_kind":"pith_short_8","alias_value":"AHSFNLW3","created_at":"2026-06-02T02:04:10.299855+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.11471","citing_title":"On the Approximation Complexity of Matrix Product Operator Born Machines","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AHSFNLW3DVHNEDUBZ5E7NII6PZ","json":"https://pith.science/pith/AHSFNLW3DVHNEDUBZ5E7NII6PZ.json","graph_json":"https://pith.science/api/pith-number/AHSFNLW3DVHNEDUBZ5E7NII6PZ/graph.json","events_json":"https://pith.science/api/pith-number/AHSFNLW3DVHNEDUBZ5E7NII6PZ/events.json","paper":"https://pith.science/paper/AHSFNLW3"},"agent_actions":{"view_html":"https://pith.science/pith/AHSFNLW3DVHNEDUBZ5E7NII6PZ","download_json":"https://pith.science/pith/AHSFNLW3DVHNEDUBZ5E7NII6PZ.json","view_paper":"https://pith.science/paper/AHSFNLW3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.22138&json=true","fetch_graph":"https://pith.science/api/pith-number/AHSFNLW3DVHNEDUBZ5E7NII6PZ/graph.json","fetch_events":"https://pith.science/api/pith-number/AHSFNLW3DVHNEDUBZ5E7NII6PZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AHSFNLW3DVHNEDUBZ5E7NII6PZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AHSFNLW3DVHNEDUBZ5E7NII6PZ/action/storage_attestation","attest_author":"https://pith.science/pith/AHSFNLW3DVHNEDUBZ5E7NII6PZ/action/author_attestation","sign_citation":"https://pith.science/pith/AHSFNLW3DVHNEDUBZ5E7NII6PZ/action/citation_signature","submit_replication":"https://pith.science/pith/AHSFNLW3DVHNEDUBZ5E7NII6PZ/action/replication_record"}},"created_at":"2026-06-02T02:04:10.299855+00:00","updated_at":"2026-06-02T02:04:10.299855+00:00"}