{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DUC3BMNIO3JOJA7QVCPOEKE4NM","short_pith_number":"pith:DUC3BMNI","schema_version":"1.0","canonical_sha256":"1d05b0b1a876d2e483f0a89ee2289c6b37a316b9c45d3268eae62b9215d8c08f","source":{"kind":"arxiv","id":"2604.07967","version":3},"attestation_state":"computed","paper":{"title":"AtomEval: Validity-Aware Atomic Evaluation of Adversarial Claim Rewriting in Fact Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"AtomEval evaluates adversarial claims by decomposing them into atomic SROM components to better detect factual corruptions.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hanze Jia, Hongyi Cen, Jingyi Zheng, Mingxin Wang, Tan Tang, Yule Liu","submitted_at":"2026-04-09T08:32:35Z","abstract_excerpt":"Large language models (LLMs) can rewrite refuted claims to evade evidence-based fact verifiers, but conventional attack success rate (ASR) can be inflated when rewrites change, weaken, or correct the false proposition they are supposed to preserve. We introduce AtomEval, a validity-aware evaluation protocol for fixed-evidence adversarial claim rewriting. AtomEval represents claims as subject--relation--object--modifier (SROM) atoms, applies a one-way preservation gate to separate valid verifier evasion from proposition-changing rewrites, and reports validity-aware attack success rate (VASR), w"},"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":true},"canonical_record":{"source":{"id":"2604.07967","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-09T08:32:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"109d294bde1c8cd1bc337c406ff46561bcf6f82cd50b1b1105bb8e9f6b572886","abstract_canon_sha256":"2b32b8bef9b2da423f587d0fb37248a53e05a3f090cd04073f82a5388b77dc88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:46.835527Z","signature_b64":"GvcmpGDhyIn/jIYOVJ5U5GS2+PzGm4LDpR6fXXn70tKx7bw9nVy5j/zbZZL1dGmvxfz0yjmNsbTuOryMwiJHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d05b0b1a876d2e483f0a89ee2289c6b37a316b9c45d3268eae62b9215d8c08f","last_reissued_at":"2026-06-02T01:03:46.834904Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:46.834904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AtomEval: Validity-Aware Atomic Evaluation of Adversarial Claim Rewriting in Fact Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"AtomEval evaluates adversarial claims by decomposing them into atomic SROM components to better detect factual corruptions.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hanze Jia, Hongyi Cen, Jingyi Zheng, Mingxin Wang, Tan Tang, Yule Liu","submitted_at":"2026-04-09T08:32:35Z","abstract_excerpt":"Large language models (LLMs) can rewrite refuted claims to evade evidence-based fact verifiers, but conventional attack success rate (ASR) can be inflated when rewrites change, weaken, or correct the false proposition they are supposed to preserve. We introduce AtomEval, a validity-aware evaluation protocol for fixed-evidence adversarial claim rewriting. AtomEval represents claims as subject--relation--object--modifier (SROM) atoms, applies a one-way preservation gate to separate valid verifier evasion from proposition-changing rewrites, and reports validity-aware attack success rate (VASR), w"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on the FEVER dataset across representative attack strategies and LLM generators show that AtomEval provides more reliable evaluation signals in our experiments.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That decomposing claims into SROM atoms and applying Atomic Validity Scoring accurately captures truth-conditional consistency and detects factual corruption without introducing its own biases or missing key semantic nuances.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AtomEval introduces atomic claim decomposition and validity scoring to provide more reliable evaluation of adversarial rewrites than standard similarity metrics in fact verification.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"AtomEval evaluates adversarial claims by decomposing them into atomic SROM components to better detect factual corruptions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"59d56a0cf3155d5850aa7c6166f060f02ad0866ef7057b78b97965f6a52a43cc"},"source":{"id":"2604.07967","kind":"arxiv","version":3},"verdict":{"id":"b032e29c-aa07-4a8f-b1b9-c78af1184fe4","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T18:12:53.655768Z","strongest_claim":"Experiments on the FEVER dataset across representative attack strategies and LLM generators show that AtomEval provides more reliable evaluation signals in our experiments.","one_line_summary":"AtomEval introduces atomic claim decomposition and validity scoring to provide more reliable evaluation of adversarial rewrites than standard similarity metrics in fact verification.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That decomposing claims into SROM atoms and applying Atomic Validity Scoring accurately captures truth-conditional consistency and detects factual corruption without introducing its own biases or missing key semantic nuances.","pith_extraction_headline":"AtomEval evaluates adversarial claims by decomposing them into atomic SROM components to better detect factual corruptions."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.07967/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":2,"snapshot_sha256":"e0832def088f423003060e63522f38e83daf1b5784d2a3a96111b76d11d49c7b"},"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":"2604.07967","created_at":"2026-06-02T01:03:46.834970+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.07967v3","created_at":"2026-06-02T01:03:46.834970+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.07967","created_at":"2026-06-02T01:03:46.834970+00:00"},{"alias_kind":"pith_short_12","alias_value":"DUC3BMNIO3JO","created_at":"2026-06-02T01:03:46.834970+00:00"},{"alias_kind":"pith_short_16","alias_value":"DUC3BMNIO3JOJA7Q","created_at":"2026-06-02T01:03:46.834970+00:00"},{"alias_kind":"pith_short_8","alias_value":"DUC3BMNI","created_at":"2026-06-02T01:03:46.834970+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DUC3BMNIO3JOJA7QVCPOEKE4NM","json":"https://pith.science/pith/DUC3BMNIO3JOJA7QVCPOEKE4NM.json","graph_json":"https://pith.science/api/pith-number/DUC3BMNIO3JOJA7QVCPOEKE4NM/graph.json","events_json":"https://pith.science/api/pith-number/DUC3BMNIO3JOJA7QVCPOEKE4NM/events.json","paper":"https://pith.science/paper/DUC3BMNI"},"agent_actions":{"view_html":"https://pith.science/pith/DUC3BMNIO3JOJA7QVCPOEKE4NM","download_json":"https://pith.science/pith/DUC3BMNIO3JOJA7QVCPOEKE4NM.json","view_paper":"https://pith.science/paper/DUC3BMNI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.07967&json=true","fetch_graph":"https://pith.science/api/pith-number/DUC3BMNIO3JOJA7QVCPOEKE4NM/graph.json","fetch_events":"https://pith.science/api/pith-number/DUC3BMNIO3JOJA7QVCPOEKE4NM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DUC3BMNIO3JOJA7QVCPOEKE4NM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DUC3BMNIO3JOJA7QVCPOEKE4NM/action/storage_attestation","attest_author":"https://pith.science/pith/DUC3BMNIO3JOJA7QVCPOEKE4NM/action/author_attestation","sign_citation":"https://pith.science/pith/DUC3BMNIO3JOJA7QVCPOEKE4NM/action/citation_signature","submit_replication":"https://pith.science/pith/DUC3BMNIO3JOJA7QVCPOEKE4NM/action/replication_record"}},"created_at":"2026-06-02T01:03:46.834970+00:00","updated_at":"2026-06-02T01:03:46.834970+00:00"}