{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KFIFRRTAYOLXNM47GZZ3M5EO6A","short_pith_number":"pith:KFIFRRTA","schema_version":"1.0","canonical_sha256":"515058c660c39776b39f3673b6748ef0221e92e9e74f6aea43bd05a003a50b79","source":{"kind":"arxiv","id":"2212.01060","version":1},"attestation_state":"computed","paper":{"title":"Exploring Faithful Rationale for Multi-hop Fact Verification via Salience-Aware Graph Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Deyu Zhou, Jiasheng Si, Yingjie Zhu","submitted_at":"2022-12-02T09:54:05Z","abstract_excerpt":"The opaqueness of the multi-hop fact verification model imposes imperative requirements for explainability. One feasible way is to extract rationales, a subset of inputs, where the performance of prediction drops dramatically when being removed. Though being explainable, most rationale extraction methods for multi-hop fact verification explore the semantic information within each piece of evidence individually, while ignoring the topological information interaction among different pieces of evidence. Intuitively, a faithful rationale bears complementary information being able to extract other "},"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":"2212.01060","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-02T09:54:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6d08df67ab862c9692a25574be82df13bb11de6b6fbac4fa56c4fc26fc7401fe","abstract_canon_sha256":"7b8199cb20a20ec238d079fd2b204270cd5ba5f975d7a0f6965c509106c7bbf6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:49.154801Z","signature_b64":"fFNRsfGC0khPXxsQWutXD6UbSB2fY0H30i7tRXwhlijCi0GU5pZL3LZBE3Y3P7yB6XlIdEorSY7Sx2oTGWakCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"515058c660c39776b39f3673b6748ef0221e92e9e74f6aea43bd05a003a50b79","last_reissued_at":"2026-07-05T05:21:49.154368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:49.154368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Faithful Rationale for Multi-hop Fact Verification via Salience-Aware Graph Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Deyu Zhou, Jiasheng Si, Yingjie Zhu","submitted_at":"2022-12-02T09:54:05Z","abstract_excerpt":"The opaqueness of the multi-hop fact verification model imposes imperative requirements for explainability. One feasible way is to extract rationales, a subset of inputs, where the performance of prediction drops dramatically when being removed. Though being explainable, most rationale extraction methods for multi-hop fact verification explore the semantic information within each piece of evidence individually, while ignoring the topological information interaction among different pieces of evidence. Intuitively, a faithful rationale bears complementary information being able to extract other "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01060","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/2212.01060/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":"2212.01060","created_at":"2026-07-05T05:21:49.154426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.01060v1","created_at":"2026-07-05T05:21:49.154426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01060","created_at":"2026-07-05T05:21:49.154426+00:00"},{"alias_kind":"pith_short_12","alias_value":"KFIFRRTAYOLX","created_at":"2026-07-05T05:21:49.154426+00:00"},{"alias_kind":"pith_short_16","alias_value":"KFIFRRTAYOLXNM47","created_at":"2026-07-05T05:21:49.154426+00:00"},{"alias_kind":"pith_short_8","alias_value":"KFIFRRTA","created_at":"2026-07-05T05:21:49.154426+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":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KFIFRRTAYOLXNM47GZZ3M5EO6A","json":"https://pith.science/pith/KFIFRRTAYOLXNM47GZZ3M5EO6A.json","graph_json":"https://pith.science/api/pith-number/KFIFRRTAYOLXNM47GZZ3M5EO6A/graph.json","events_json":"https://pith.science/api/pith-number/KFIFRRTAYOLXNM47GZZ3M5EO6A/events.json","paper":"https://pith.science/paper/KFIFRRTA"},"agent_actions":{"view_html":"https://pith.science/pith/KFIFRRTAYOLXNM47GZZ3M5EO6A","download_json":"https://pith.science/pith/KFIFRRTAYOLXNM47GZZ3M5EO6A.json","view_paper":"https://pith.science/paper/KFIFRRTA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.01060&json=true","fetch_graph":"https://pith.science/api/pith-number/KFIFRRTAYOLXNM47GZZ3M5EO6A/graph.json","fetch_events":"https://pith.science/api/pith-number/KFIFRRTAYOLXNM47GZZ3M5EO6A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KFIFRRTAYOLXNM47GZZ3M5EO6A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KFIFRRTAYOLXNM47GZZ3M5EO6A/action/storage_attestation","attest_author":"https://pith.science/pith/KFIFRRTAYOLXNM47GZZ3M5EO6A/action/author_attestation","sign_citation":"https://pith.science/pith/KFIFRRTAYOLXNM47GZZ3M5EO6A/action/citation_signature","submit_replication":"https://pith.science/pith/KFIFRRTAYOLXNM47GZZ3M5EO6A/action/replication_record"}},"created_at":"2026-07-05T05:21:49.154426+00:00","updated_at":"2026-07-05T05:21:49.154426+00:00"}