{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KLD74A3DRSL7HKBC3XXXIJC43W","short_pith_number":"pith:KLD74A3D","schema_version":"1.0","canonical_sha256":"52c7fe03638c97f3a822ddef74245cdd85450c32b825f59aec3b52cc8dc9b3bd","source":{"kind":"arxiv","id":"2402.09259","version":2},"attestation_state":"computed","paper":{"title":"SyntaxShap: Syntax-aware Explainability Method for Text Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kenza Amara, Mennatallah El-Assady, Rita Sevastjanova","submitted_at":"2024-02-14T15:45:56Z","abstract_excerpt":"To harness the power of large language models in safety-critical domains, we need to ensure the explainability of their predictions. However, despite the significant attention to model interpretability, there remains an unexplored domain in explaining sequence-to-sequence tasks using methods tailored for textual data. This paper introduces SyntaxShap, a local, model-agnostic explainability method for text generation that takes into consideration the syntax in the text data. The presented work extends Shapley values to account for parsing-based syntactic dependencies. Taking a game theoric appr"},"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":"2402.09259","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-14T15:45:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5aa736858b60c47df2535a33ba34f9e6272342322eec19a0dbb61b460089abab","abstract_canon_sha256":"bb4a638ab77207282919fe6a60507c02c0cb59125ddf5d0494939862714b8900"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:19.506407Z","signature_b64":"uSBaY+4Ag3ijh+Jk6sRERlz/jIGzaM+HEfUT3t1sHK3hPyCd4VpzsMnogpkCfpB0oaWI7Z4ihadpaMujRk40CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52c7fe03638c97f3a822ddef74245cdd85450c32b825f59aec3b52cc8dc9b3bd","last_reissued_at":"2026-07-05T08:26:19.505888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:19.505888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SyntaxShap: Syntax-aware Explainability Method for Text Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kenza Amara, Mennatallah El-Assady, Rita Sevastjanova","submitted_at":"2024-02-14T15:45:56Z","abstract_excerpt":"To harness the power of large language models in safety-critical domains, we need to ensure the explainability of their predictions. However, despite the significant attention to model interpretability, there remains an unexplored domain in explaining sequence-to-sequence tasks using methods tailored for textual data. This paper introduces SyntaxShap, a local, model-agnostic explainability method for text generation that takes into consideration the syntax in the text data. The presented work extends Shapley values to account for parsing-based syntactic dependencies. Taking a game theoric appr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09259","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/2402.09259/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":"2402.09259","created_at":"2026-07-05T08:26:19.505948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09259v2","created_at":"2026-07-05T08:26:19.505948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09259","created_at":"2026-07-05T08:26:19.505948+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLD74A3DRSL7","created_at":"2026-07-05T08:26:19.505948+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLD74A3DRSL7HKBC","created_at":"2026-07-05T08:26:19.505948+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLD74A3D","created_at":"2026-07-05T08:26:19.505948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.07610","citing_title":"Concept-Level Explainability for Auditing & Steering LLM Responses","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KLD74A3DRSL7HKBC3XXXIJC43W","json":"https://pith.science/pith/KLD74A3DRSL7HKBC3XXXIJC43W.json","graph_json":"https://pith.science/api/pith-number/KLD74A3DRSL7HKBC3XXXIJC43W/graph.json","events_json":"https://pith.science/api/pith-number/KLD74A3DRSL7HKBC3XXXIJC43W/events.json","paper":"https://pith.science/paper/KLD74A3D"},"agent_actions":{"view_html":"https://pith.science/pith/KLD74A3DRSL7HKBC3XXXIJC43W","download_json":"https://pith.science/pith/KLD74A3DRSL7HKBC3XXXIJC43W.json","view_paper":"https://pith.science/paper/KLD74A3D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09259&json=true","fetch_graph":"https://pith.science/api/pith-number/KLD74A3DRSL7HKBC3XXXIJC43W/graph.json","fetch_events":"https://pith.science/api/pith-number/KLD74A3DRSL7HKBC3XXXIJC43W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLD74A3DRSL7HKBC3XXXIJC43W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLD74A3DRSL7HKBC3XXXIJC43W/action/storage_attestation","attest_author":"https://pith.science/pith/KLD74A3DRSL7HKBC3XXXIJC43W/action/author_attestation","sign_citation":"https://pith.science/pith/KLD74A3DRSL7HKBC3XXXIJC43W/action/citation_signature","submit_replication":"https://pith.science/pith/KLD74A3DRSL7HKBC3XXXIJC43W/action/replication_record"}},"created_at":"2026-07-05T08:26:19.505948+00:00","updated_at":"2026-07-05T08:26:19.505948+00:00"}