{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZKH6JUL3ZWKLAYBYYWKY6MQ3KX","short_pith_number":"pith:ZKH6JUL3","schema_version":"1.0","canonical_sha256":"ca8fe4d17bcd94b06038c5958f321b55ddae9e0a9d14307e4b1862fc30bd328c","source":{"kind":"arxiv","id":"2305.09400","version":1},"attestation_state":"computed","paper":{"title":"Consistent Multi-Granular Rationale Extraction for Explainable Multi-hop Fact Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deyu Zhou, Jiasheng Si, Yingjie Zhu","submitted_at":"2023-05-16T12:31:53Z","abstract_excerpt":"The success of deep learning models on multi-hop fact verification has prompted researchers to understand the behavior behind their veracity. One possible way is erasure search: obtaining the rationale by entirely removing a subset of input without compromising the veracity prediction. Although extensively explored, existing approaches fall within the scope of the single-granular (tokens or sentences) explanation, which inevitably leads to explanation redundancy and inconsistency. To address such issues, this paper explores the viability of multi-granular rationale extraction with consistency "},"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":"2305.09400","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-16T12:31:53Z","cross_cats_sorted":[],"title_canon_sha256":"b9c3793b9a94ac36dcf8c3d5c7df05146bfaa8a121ea78a8420b58977097c602","abstract_canon_sha256":"e6a4d828304149c39af9eba02f8dd1237153e1eb0aa40422d25d91d7b296c91f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:10:47.529306Z","signature_b64":"DyvQJXNuvsi2sMldLOqRgCUc+nQLthWEdomdiWM7n13CC5RtyLKsIu1viqOSSQpFLyA4QkdmDR0QrPG+LQ+4Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca8fe4d17bcd94b06038c5958f321b55ddae9e0a9d14307e4b1862fc30bd328c","last_reissued_at":"2026-07-05T06:10:47.528875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:10:47.528875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Consistent Multi-Granular Rationale Extraction for Explainable Multi-hop Fact Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deyu Zhou, Jiasheng Si, Yingjie Zhu","submitted_at":"2023-05-16T12:31:53Z","abstract_excerpt":"The success of deep learning models on multi-hop fact verification has prompted researchers to understand the behavior behind their veracity. One possible way is erasure search: obtaining the rationale by entirely removing a subset of input without compromising the veracity prediction. Although extensively explored, existing approaches fall within the scope of the single-granular (tokens or sentences) explanation, which inevitably leads to explanation redundancy and inconsistency. To address such issues, this paper explores the viability of multi-granular rationale extraction with consistency "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09400","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/2305.09400/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":"2305.09400","created_at":"2026-07-05T06:10:47.528931+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.09400v1","created_at":"2026-07-05T06:10:47.528931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09400","created_at":"2026-07-05T06:10:47.528931+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKH6JUL3ZWKL","created_at":"2026-07-05T06:10:47.528931+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKH6JUL3ZWKLAYBY","created_at":"2026-07-05T06:10:47.528931+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKH6JUL3","created_at":"2026-07-05T06:10:47.528931+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07446","citing_title":"Fact in Fragments: Deconstructing Complex Claims via LLM-based Atomic Fact Extraction and Verification","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZKH6JUL3ZWKLAYBYYWKY6MQ3KX","json":"https://pith.science/pith/ZKH6JUL3ZWKLAYBYYWKY6MQ3KX.json","graph_json":"https://pith.science/api/pith-number/ZKH6JUL3ZWKLAYBYYWKY6MQ3KX/graph.json","events_json":"https://pith.science/api/pith-number/ZKH6JUL3ZWKLAYBYYWKY6MQ3KX/events.json","paper":"https://pith.science/paper/ZKH6JUL3"},"agent_actions":{"view_html":"https://pith.science/pith/ZKH6JUL3ZWKLAYBYYWKY6MQ3KX","download_json":"https://pith.science/pith/ZKH6JUL3ZWKLAYBYYWKY6MQ3KX.json","view_paper":"https://pith.science/paper/ZKH6JUL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.09400&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKH6JUL3ZWKLAYBYYWKY6MQ3KX/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKH6JUL3ZWKLAYBYYWKY6MQ3KX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKH6JUL3ZWKLAYBYYWKY6MQ3KX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKH6JUL3ZWKLAYBYYWKY6MQ3KX/action/storage_attestation","attest_author":"https://pith.science/pith/ZKH6JUL3ZWKLAYBYYWKY6MQ3KX/action/author_attestation","sign_citation":"https://pith.science/pith/ZKH6JUL3ZWKLAYBYYWKY6MQ3KX/action/citation_signature","submit_replication":"https://pith.science/pith/ZKH6JUL3ZWKLAYBYYWKY6MQ3KX/action/replication_record"}},"created_at":"2026-07-05T06:10:47.528931+00:00","updated_at":"2026-07-05T06:10:47.528931+00:00"}