{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VEQOOWYBGREDTNZHHFTGCPCEE7","short_pith_number":"pith:VEQOOWYB","schema_version":"1.0","canonical_sha256":"a920e75b01344839b7273966613c4427c038ffb9dc81a28046eb9b1e4cb5812b","source":{"kind":"arxiv","id":"2606.01540","version":1},"attestation_state":"computed","paper":{"title":"TN-SHAP-G: Graph-Structured Tensor Network Surrogates for Shapley Values and Interactions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Farzaneh Heidari, Guillaume Rabusseau","submitted_at":"2026-06-01T01:41:29Z","abstract_excerpt":"Shapley values are a widely used tool for attributing importance and interactions among input variables in black-box models, but their computation involves a function defined over an exponentially large space of subsets. We propose TN-SHAP-G, a framework that exploits structure in graph-structured inputs to compute Shapley values and higher-order interaction indices efficiently. Given a predictor and a fixed masking scheme, TN-SHAP-G learns a compact, graph-aligned multilinear surrogate that approximates the masked-input behavior, represented as a tensor network whose topology mirrors the inpu"},"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":"2606.01540","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T01:41:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e833bf45f307b272522cbfea547bb44808559ec792d1a515036d15c51f09f6f2","abstract_canon_sha256":"c57bbf655c73f8a77d7adba879eeb4e722d70a5cde42f3ed5cfa752bc39c2a77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:35.882351Z","signature_b64":"YBKddj0Prr1iOeSVr9XtBzClya2ezEnj/l3b/fwDZFm46NSwv2/Z0SpXM/Q4wS3zz6t9XQIem8J3dTDgHKC+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a920e75b01344839b7273966613c4427c038ffb9dc81a28046eb9b1e4cb5812b","last_reissued_at":"2026-06-02T02:04:35.881945Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:35.881945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TN-SHAP-G: Graph-Structured Tensor Network Surrogates for Shapley Values and Interactions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Farzaneh Heidari, Guillaume Rabusseau","submitted_at":"2026-06-01T01:41:29Z","abstract_excerpt":"Shapley values are a widely used tool for attributing importance and interactions among input variables in black-box models, but their computation involves a function defined over an exponentially large space of subsets. We propose TN-SHAP-G, a framework that exploits structure in graph-structured inputs to compute Shapley values and higher-order interaction indices efficiently. Given a predictor and a fixed masking scheme, TN-SHAP-G learns a compact, graph-aligned multilinear surrogate that approximates the masked-input behavior, represented as a tensor network whose topology mirrors the inpu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01540","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/2606.01540/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":"2606.01540","created_at":"2026-06-02T02:04:35.882009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01540v1","created_at":"2026-06-02T02:04:35.882009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01540","created_at":"2026-06-02T02:04:35.882009+00:00"},{"alias_kind":"pith_short_12","alias_value":"VEQOOWYBGRED","created_at":"2026-06-02T02:04:35.882009+00:00"},{"alias_kind":"pith_short_16","alias_value":"VEQOOWYBGREDTNZH","created_at":"2026-06-02T02:04:35.882009+00:00"},{"alias_kind":"pith_short_8","alias_value":"VEQOOWYB","created_at":"2026-06-02T02:04:35.882009+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/VEQOOWYBGREDTNZHHFTGCPCEE7","json":"https://pith.science/pith/VEQOOWYBGREDTNZHHFTGCPCEE7.json","graph_json":"https://pith.science/api/pith-number/VEQOOWYBGREDTNZHHFTGCPCEE7/graph.json","events_json":"https://pith.science/api/pith-number/VEQOOWYBGREDTNZHHFTGCPCEE7/events.json","paper":"https://pith.science/paper/VEQOOWYB"},"agent_actions":{"view_html":"https://pith.science/pith/VEQOOWYBGREDTNZHHFTGCPCEE7","download_json":"https://pith.science/pith/VEQOOWYBGREDTNZHHFTGCPCEE7.json","view_paper":"https://pith.science/paper/VEQOOWYB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01540&json=true","fetch_graph":"https://pith.science/api/pith-number/VEQOOWYBGREDTNZHHFTGCPCEE7/graph.json","fetch_events":"https://pith.science/api/pith-number/VEQOOWYBGREDTNZHHFTGCPCEE7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VEQOOWYBGREDTNZHHFTGCPCEE7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VEQOOWYBGREDTNZHHFTGCPCEE7/action/storage_attestation","attest_author":"https://pith.science/pith/VEQOOWYBGREDTNZHHFTGCPCEE7/action/author_attestation","sign_citation":"https://pith.science/pith/VEQOOWYBGREDTNZHHFTGCPCEE7/action/citation_signature","submit_replication":"https://pith.science/pith/VEQOOWYBGREDTNZHHFTGCPCEE7/action/replication_record"}},"created_at":"2026-06-02T02:04:35.882009+00:00","updated_at":"2026-06-02T02:04:35.882009+00:00"}