{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PAEYFRIM7PJWRGZ5IM3OWTIJGU","short_pith_number":"pith:PAEYFRIM","schema_version":"1.0","canonical_sha256":"780982c50cfbd3689b3d4336eb4d093517910a4cf124e7ef184ef8cb5fba0d76","source":{"kind":"arxiv","id":"2506.08713","version":2},"attestation_state":"computed","paper":{"title":"Explainable Compliance Detection with Multi-Hop Natural Language Inference on Assurance Case Structure","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Dusica Marijan, Fariz Ikhwantri","submitted_at":"2025-06-10T11:56:06Z","abstract_excerpt":"Ensuring complex systems meet regulations typically requires checking the validity of assurance cases through a claim-argument-evidence framework. Some challenges in this process include the complicated nature of legal and technical texts, the need for model explanations, and limited access to assurance case data. We propose a compliance detection approach based on Natural Language Inference (NLI): EXplainable CompLiance detection with Argumentative Inference of Multi-hop reasoning (EXCLAIM). We formulate the claim-argument-evidence structure of an assurance case as a multi-hop inference for e"},"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":"2506.08713","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T11:56:06Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"eb30820acbdcf9d26d0e82166ad30120153af84ba5384b22751985850ab6e845","abstract_canon_sha256":"f96c29abaf86f2edba45bc252709252a67cacdf818b412c116fecffb095206fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:28.408942Z","signature_b64":"Qetks7FwYReNnn2ljzpvd1u5iY3vAqcDHaDLLVcGVRyo69lJ8Gu2x5qfNbUoAfoDmN5AZaqrRulEAqDGqXzSDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"780982c50cfbd3689b3d4336eb4d093517910a4cf124e7ef184ef8cb5fba0d76","last_reissued_at":"2026-07-05T11:31:28.408448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:28.408448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explainable Compliance Detection with Multi-Hop Natural Language Inference on Assurance Case Structure","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Dusica Marijan, Fariz Ikhwantri","submitted_at":"2025-06-10T11:56:06Z","abstract_excerpt":"Ensuring complex systems meet regulations typically requires checking the validity of assurance cases through a claim-argument-evidence framework. Some challenges in this process include the complicated nature of legal and technical texts, the need for model explanations, and limited access to assurance case data. We propose a compliance detection approach based on Natural Language Inference (NLI): EXplainable CompLiance detection with Argumentative Inference of Multi-hop reasoning (EXCLAIM). We formulate the claim-argument-evidence structure of an assurance case as a multi-hop inference for e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08713","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/2506.08713/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":"2506.08713","created_at":"2026-07-05T11:31:28.408506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08713v2","created_at":"2026-07-05T11:31:28.408506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08713","created_at":"2026-07-05T11:31:28.408506+00:00"},{"alias_kind":"pith_short_12","alias_value":"PAEYFRIM7PJW","created_at":"2026-07-05T11:31:28.408506+00:00"},{"alias_kind":"pith_short_16","alias_value":"PAEYFRIM7PJWRGZ5","created_at":"2026-07-05T11:31:28.408506+00:00"},{"alias_kind":"pith_short_8","alias_value":"PAEYFRIM","created_at":"2026-07-05T11:31:28.408506+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20577","citing_title":"Evaluating Assurance Cases as Text-Attributed Graphs for Structure and Provenance Analysis","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PAEYFRIM7PJWRGZ5IM3OWTIJGU","json":"https://pith.science/pith/PAEYFRIM7PJWRGZ5IM3OWTIJGU.json","graph_json":"https://pith.science/api/pith-number/PAEYFRIM7PJWRGZ5IM3OWTIJGU/graph.json","events_json":"https://pith.science/api/pith-number/PAEYFRIM7PJWRGZ5IM3OWTIJGU/events.json","paper":"https://pith.science/paper/PAEYFRIM"},"agent_actions":{"view_html":"https://pith.science/pith/PAEYFRIM7PJWRGZ5IM3OWTIJGU","download_json":"https://pith.science/pith/PAEYFRIM7PJWRGZ5IM3OWTIJGU.json","view_paper":"https://pith.science/paper/PAEYFRIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08713&json=true","fetch_graph":"https://pith.science/api/pith-number/PAEYFRIM7PJWRGZ5IM3OWTIJGU/graph.json","fetch_events":"https://pith.science/api/pith-number/PAEYFRIM7PJWRGZ5IM3OWTIJGU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PAEYFRIM7PJWRGZ5IM3OWTIJGU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PAEYFRIM7PJWRGZ5IM3OWTIJGU/action/storage_attestation","attest_author":"https://pith.science/pith/PAEYFRIM7PJWRGZ5IM3OWTIJGU/action/author_attestation","sign_citation":"https://pith.science/pith/PAEYFRIM7PJWRGZ5IM3OWTIJGU/action/citation_signature","submit_replication":"https://pith.science/pith/PAEYFRIM7PJWRGZ5IM3OWTIJGU/action/replication_record"}},"created_at":"2026-07-05T11:31:28.408506+00:00","updated_at":"2026-07-05T11:31:28.408506+00:00"}