{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PBCD2KZZABMO7QP2GKEEBADTHB","short_pith_number":"pith:PBCD2KZZ","schema_version":"1.0","canonical_sha256":"78443d2b390058efc1fa3288408073387e2fa0525bcf7e69d4aba53b4ae49757","source":{"kind":"arxiv","id":"2509.05199","version":1},"attestation_state":"computed","paper":{"title":"Triadic Fusion of Cognitive, Functional, and Causal Dimensions for Explainable LLMs: The TAXAL Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Carlos Pel\\'aez-Gonz\\'alez, Cristina Zuheros, David Herrera-Poyatos, Francisco Herrera, Rosana Montes, Virilo Tejedor","submitted_at":"2025-09-05T15:58:49Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly being deployed in high-risk domains where opacity, bias, and instability undermine trust and accountability. Traditional explainability methods, focused on surface outputs, do not capture the reasoning pathways, planning logic, and systemic impacts of agentic LLMs.\n  We introduce TAXAL (Triadic Alignment for eXplainability in Agentic LLMs), a triadic fusion framework that unites three complementary dimensions: cognitive (user understanding), functional (practical utility), and causal (faithful reasoning). TAXAL provides a unified, role-sensitive 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":"2509.05199","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-05T15:58:49Z","cross_cats_sorted":[],"title_canon_sha256":"82ac24fa804a524ca8fc388d22f78291f787b0c9cacff6ff0cf4d2ae384099cd","abstract_canon_sha256":"cd89fa281f0f28d8a54cd1a1eb6c49a142dfb68dbdf31e84ae8e154f6b6d8a38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:37.673183Z","signature_b64":"YRW7aPIFMPAF9cUet+ObAhMEGzaRCMy18jP7shW398pBUevAo6FYiseSqABonIEKHwV0fUd6dDw0ptUnhBKlAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78443d2b390058efc1fa3288408073387e2fa0525bcf7e69d4aba53b4ae49757","last_reissued_at":"2026-07-05T12:05:37.672668Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:37.672668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Triadic Fusion of Cognitive, Functional, and Causal Dimensions for Explainable LLMs: The TAXAL Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Carlos Pel\\'aez-Gonz\\'alez, Cristina Zuheros, David Herrera-Poyatos, Francisco Herrera, Rosana Montes, Virilo Tejedor","submitted_at":"2025-09-05T15:58:49Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly being deployed in high-risk domains where opacity, bias, and instability undermine trust and accountability. Traditional explainability methods, focused on surface outputs, do not capture the reasoning pathways, planning logic, and systemic impacts of agentic LLMs.\n  We introduce TAXAL (Triadic Alignment for eXplainability in Agentic LLMs), a triadic fusion framework that unites three complementary dimensions: cognitive (user understanding), functional (practical utility), and causal (faithful reasoning). TAXAL provides a unified, role-sensitive fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05199","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/2509.05199/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":"2509.05199","created_at":"2026-07-05T12:05:37.672727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.05199v1","created_at":"2026-07-05T12:05:37.672727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05199","created_at":"2026-07-05T12:05:37.672727+00:00"},{"alias_kind":"pith_short_12","alias_value":"PBCD2KZZABMO","created_at":"2026-07-05T12:05:37.672727+00:00"},{"alias_kind":"pith_short_16","alias_value":"PBCD2KZZABMO7QP2","created_at":"2026-07-05T12:05:37.672727+00:00"},{"alias_kind":"pith_short_8","alias_value":"PBCD2KZZ","created_at":"2026-07-05T12:05:37.672727+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/PBCD2KZZABMO7QP2GKEEBADTHB","json":"https://pith.science/pith/PBCD2KZZABMO7QP2GKEEBADTHB.json","graph_json":"https://pith.science/api/pith-number/PBCD2KZZABMO7QP2GKEEBADTHB/graph.json","events_json":"https://pith.science/api/pith-number/PBCD2KZZABMO7QP2GKEEBADTHB/events.json","paper":"https://pith.science/paper/PBCD2KZZ"},"agent_actions":{"view_html":"https://pith.science/pith/PBCD2KZZABMO7QP2GKEEBADTHB","download_json":"https://pith.science/pith/PBCD2KZZABMO7QP2GKEEBADTHB.json","view_paper":"https://pith.science/paper/PBCD2KZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.05199&json=true","fetch_graph":"https://pith.science/api/pith-number/PBCD2KZZABMO7QP2GKEEBADTHB/graph.json","fetch_events":"https://pith.science/api/pith-number/PBCD2KZZABMO7QP2GKEEBADTHB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PBCD2KZZABMO7QP2GKEEBADTHB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PBCD2KZZABMO7QP2GKEEBADTHB/action/storage_attestation","attest_author":"https://pith.science/pith/PBCD2KZZABMO7QP2GKEEBADTHB/action/author_attestation","sign_citation":"https://pith.science/pith/PBCD2KZZABMO7QP2GKEEBADTHB/action/citation_signature","submit_replication":"https://pith.science/pith/PBCD2KZZABMO7QP2GKEEBADTHB/action/replication_record"}},"created_at":"2026-07-05T12:05:37.672727+00:00","updated_at":"2026-07-05T12:05:37.672727+00:00"}