{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XSJSGNKZVPP2OKWDGZIT2O7AMK","short_pith_number":"pith:XSJSGNKZ","schema_version":"1.0","canonical_sha256":"bc93233559abdfa72ac336513d3be062a678c39e81d850fed09752ffc222f7d7","source":{"kind":"arxiv","id":"2401.08026","version":1},"attestation_state":"computed","paper":{"title":"JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claims","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fengzhu Zeng, Wei Gao","submitted_at":"2024-01-16T00:47:36Z","abstract_excerpt":"Justification is an explanation that supports the veracity assigned to a claim in fact-checking. However, the task of justification generation is previously oversimplified as summarization of fact-check article authored by fact-checkers. Therefore, we propose a realistic approach to generate justification based on retrieved evidence. We present a new benchmark dataset called ExClaim for \\underline{Ex}plainable fact-checking of real-world \\underline{Claim}s, and introduce JustiLM, a novel few-shot \\underline{Justi}fication generation based on retrieval-augmented \\underline{L}anguage \\underline{"},"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":"2401.08026","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-16T00:47:36Z","cross_cats_sorted":[],"title_canon_sha256":"0bfce0f243ea63bdd647be17de1b93466f551fad49e5dc4725caa79b2853998b","abstract_canon_sha256":"1e634bdd21cdf7fca98e16493a6bbec65aecbf0f61e17d257fe373cf19426a34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:06.168721Z","signature_b64":"7m5jPvNTvmeBtAikqvL5Q5xbUg7KO3xRmNqsR+UY6odFe/nOiXq6J64DAyKN6EIyb7BLT7wNM6kreZ6C8vQxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc93233559abdfa72ac336513d3be062a678c39e81d850fed09752ffc222f7d7","last_reissued_at":"2026-07-05T07:34:06.168284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:06.168284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claims","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fengzhu Zeng, Wei Gao","submitted_at":"2024-01-16T00:47:36Z","abstract_excerpt":"Justification is an explanation that supports the veracity assigned to a claim in fact-checking. However, the task of justification generation is previously oversimplified as summarization of fact-check article authored by fact-checkers. Therefore, we propose a realistic approach to generate justification based on retrieved evidence. We present a new benchmark dataset called ExClaim for \\underline{Ex}plainable fact-checking of real-world \\underline{Claim}s, and introduce JustiLM, a novel few-shot \\underline{Justi}fication generation based on retrieval-augmented \\underline{L}anguage \\underline{"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08026","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/2401.08026/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":"2401.08026","created_at":"2026-07-05T07:34:06.168358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.08026v1","created_at":"2026-07-05T07:34:06.168358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08026","created_at":"2026-07-05T07:34:06.168358+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSJSGNKZVPP2","created_at":"2026-07-05T07:34:06.168358+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSJSGNKZVPP2OKWD","created_at":"2026-07-05T07:34:06.168358+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSJSGNKZ","created_at":"2026-07-05T07:34:06.168358+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05924","citing_title":"Generating Grounded Responses to Counter Misinformation via Learning Efficient Fine-Grained Critiques","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XSJSGNKZVPP2OKWDGZIT2O7AMK","json":"https://pith.science/pith/XSJSGNKZVPP2OKWDGZIT2O7AMK.json","graph_json":"https://pith.science/api/pith-number/XSJSGNKZVPP2OKWDGZIT2O7AMK/graph.json","events_json":"https://pith.science/api/pith-number/XSJSGNKZVPP2OKWDGZIT2O7AMK/events.json","paper":"https://pith.science/paper/XSJSGNKZ"},"agent_actions":{"view_html":"https://pith.science/pith/XSJSGNKZVPP2OKWDGZIT2O7AMK","download_json":"https://pith.science/pith/XSJSGNKZVPP2OKWDGZIT2O7AMK.json","view_paper":"https://pith.science/paper/XSJSGNKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.08026&json=true","fetch_graph":"https://pith.science/api/pith-number/XSJSGNKZVPP2OKWDGZIT2O7AMK/graph.json","fetch_events":"https://pith.science/api/pith-number/XSJSGNKZVPP2OKWDGZIT2O7AMK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSJSGNKZVPP2OKWDGZIT2O7AMK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSJSGNKZVPP2OKWDGZIT2O7AMK/action/storage_attestation","attest_author":"https://pith.science/pith/XSJSGNKZVPP2OKWDGZIT2O7AMK/action/author_attestation","sign_citation":"https://pith.science/pith/XSJSGNKZVPP2OKWDGZIT2O7AMK/action/citation_signature","submit_replication":"https://pith.science/pith/XSJSGNKZVPP2OKWDGZIT2O7AMK/action/replication_record"}},"created_at":"2026-07-05T07:34:06.168358+00:00","updated_at":"2026-07-05T07:34:06.168358+00:00"}