{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DUC3BMNIO3JOJA7QVCPOEKE4NM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2b32b8bef9b2da423f587d0fb37248a53e05a3f090cd04073f82a5388b77dc88","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-09T08:32:35Z","title_canon_sha256":"109d294bde1c8cd1bc337c406ff46561bcf6f82cd50b1b1105bb8e9f6b572886"},"schema_version":"1.0","source":{"id":"2604.07967","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.07967","created_at":"2026-06-02T01:03:46Z"},{"alias_kind":"arxiv_version","alias_value":"2604.07967v3","created_at":"2026-06-02T01:03:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.07967","created_at":"2026-06-02T01:03:46Z"},{"alias_kind":"pith_short_12","alias_value":"DUC3BMNIO3JO","created_at":"2026-06-02T01:03:46Z"},{"alias_kind":"pith_short_16","alias_value":"DUC3BMNIO3JOJA7Q","created_at":"2026-06-02T01:03:46Z"},{"alias_kind":"pith_short_8","alias_value":"DUC3BMNI","created_at":"2026-06-02T01:03:46Z"}],"graph_snapshots":[{"event_id":"sha256:589080c8f62181d685c549b9b633407e24ac360fbfa965421ad2fdf93bf3d61e","target":"graph","created_at":"2026-06-02T01:03:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments on the FEVER dataset across representative attack strategies and LLM generators show that AtomEval provides more reliable evaluation signals in our experiments."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"AtomEval introduces atomic claim decomposition and validity scoring to provide more reliable evaluation of adversarial rewrites than standard similarity metrics in fact verification."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"AtomEval evaluates adversarial claims by decomposing them into atomic SROM components to better detect factual corruptions."}],"snapshot_sha256":"59d56a0cf3155d5850aa7c6166f060f02ad0866ef7057b78b97965f6a52a43cc"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"e0832def088f423003060e63522f38e83daf1b5784d2a3a96111b76d11d49c7b"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.07967/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hanze Jia, Hongyi Cen, Jingyi Zheng, Mingxin Wang, Tan Tang, Yule Liu","cross_cats":["cs.AI"],"headline":"AtomEval evaluates adversarial claims by decomposing them into atomic SROM components to better detect factual corruptions.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-09T08:32:35Z","title":"AtomEval: Validity-Aware Atomic Evaluation of Adversarial Claim Rewriting in Fact Verification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.07967","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-10T18:12:53.655768Z","id":"b032e29c-aa07-4a8f-b1b9-c78af1184fe4","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"AtomEval evaluates adversarial claims by decomposing them into atomic SROM components to better detect factual corruptions.","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.","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."}},"verdict_id":"b032e29c-aa07-4a8f-b1b9-c78af1184fe4"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:aa727edd740ebd5af8eaa32808293678bbeeb50cba1b4874fbf4cfac17512606","target":"record","created_at":"2026-06-02T01:03:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2b32b8bef9b2da423f587d0fb37248a53e05a3f090cd04073f82a5388b77dc88","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-09T08:32:35Z","title_canon_sha256":"109d294bde1c8cd1bc337c406ff46561bcf6f82cd50b1b1105bb8e9f6b572886"},"schema_version":"1.0","source":{"id":"2604.07967","kind":"arxiv","version":3}},"canonical_sha256":"1d05b0b1a876d2e483f0a89ee2289c6b37a316b9c45d3268eae62b9215d8c08f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d05b0b1a876d2e483f0a89ee2289c6b37a316b9c45d3268eae62b9215d8c08f","first_computed_at":"2026-06-02T01:03:46.834904Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:46.834904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GvcmpGDhyIn/jIYOVJ5U5GS2+PzGm4LDpR6fXXn70tKx7bw9nVy5j/zbZZL1dGmvxfz0yjmNsbTuOryMwiJHCg==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:46.835527Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.07967","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa727edd740ebd5af8eaa32808293678bbeeb50cba1b4874fbf4cfac17512606","sha256:589080c8f62181d685c549b9b633407e24ac360fbfa965421ad2fdf93bf3d61e"],"state_sha256":"8d24c530d28b52ec4f35e5e25a306a440f9ece3c058e59e4c7d85d468c71d195"}