{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TZADY4KHZ7H2AU7CEXIV4FVQTU","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":"3a036c0dc1bd65a088f178a858c2f731ac85bee90b994a21d4206e1ff3db10f7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-20T13:21:27Z","title_canon_sha256":"328ff62ee07c9317419a4d2037c896ea56cdb71a51870a5f5e3d5210643dcbea"},"schema_version":"1.0","source":{"id":"2607.18360","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18360","created_at":"2026-07-22T00:22:43Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18360v1","created_at":"2026-07-22T00:22:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18360","created_at":"2026-07-22T00:22:43Z"},{"alias_kind":"pith_short_12","alias_value":"TZADY4KHZ7H2","created_at":"2026-07-22T00:22:43Z"},{"alias_kind":"pith_short_16","alias_value":"TZADY4KHZ7H2AU7C","created_at":"2026-07-22T00:22:43Z"},{"alias_kind":"pith_short_8","alias_value":"TZADY4KH","created_at":"2026-07-22T00:22:43Z"}],"graph_snapshots":[{"event_id":"sha256:5f318039e6c48e3bd6108028736d88dfa365714a6690e16476dca3d4e6b35846","target":"graph","created_at":"2026-07-22T00:22:43Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.18360/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) now routinely draft literature reviews and assist with academic writing, which means a higher risk of fabricated references: GPTZero found 53 papers with hallucinated citations among NeurIPS 2025's accepted set. Rule- and LLM-based verifiers are emerging, but no shared benchmark compares them and gives detailed failure diagnostics. We close that gap with HALLMARK (Hallucination benchmark): 2,526 BibTeX entries spanning 14 hallucination types, three difficulty tiers, six diagnostic sub-tests per entry, and a contamination-resistant held-out split. On it we evaluate ","authors_text":"Patrik Reizinger, Wieland Brendel","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-20T13:21:27Z","title":"HALLMARK: Diagnosing Three Failure Modes in LLM Citation Verifiers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18360","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e1831f0e7944bb0ca80a7da52af770bc4ee2da98294826caf0b658f60381cdd2","target":"record","created_at":"2026-07-22T00:22:43Z","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":"3a036c0dc1bd65a088f178a858c2f731ac85bee90b994a21d4206e1ff3db10f7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-20T13:21:27Z","title_canon_sha256":"328ff62ee07c9317419a4d2037c896ea56cdb71a51870a5f5e3d5210643dcbea"},"schema_version":"1.0","source":{"id":"2607.18360","kind":"arxiv","version":1}},"canonical_sha256":"9e403c7147cfcfa053e225d15e16b09d316bfe3f1bc6244f4708144e4e9e1053","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e403c7147cfcfa053e225d15e16b09d316bfe3f1bc6244f4708144e4e9e1053","first_computed_at":"2026-07-22T00:22:43.416532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T00:22:43.416532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r3pbY+jLQ9y+Q4YKV7CmqmkJOH4uyPMND5zFJOvgY/I+NbTgy9uxjb1gkfx/nx+jePdLuTEDz50AlgycTXO9Cg==","signature_status":"signed_v1","signed_at":"2026-07-22T00:22:43.417347Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18360","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1831f0e7944bb0ca80a7da52af770bc4ee2da98294826caf0b658f60381cdd2","sha256:5f318039e6c48e3bd6108028736d88dfa365714a6690e16476dca3d4e6b35846"],"state_sha256":"b52386a18feb81e41ff8fd30d1170a891dc16fc76e82cd7c4d31dac02b448d80"}