{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PEUZORFE3UM3LYNFWXIABYCNP3","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":"9cb445199e25c64eaac46f7b0a09c5df2868809bf4a7730793b1128dd81c2dad","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T16:23:15Z","title_canon_sha256":"1ed47167778ebca474ee410f5ce781c89146d652268641423ede9c52e9473652"},"schema_version":"1.0","source":{"id":"2505.00065","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00065","created_at":"2026-07-05T10:56:41Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00065v1","created_at":"2026-07-05T10:56:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00065","created_at":"2026-07-05T10:56:41Z"},{"alias_kind":"pith_short_12","alias_value":"PEUZORFE3UM3","created_at":"2026-07-05T10:56:41Z"},{"alias_kind":"pith_short_16","alias_value":"PEUZORFE3UM3LYNF","created_at":"2026-07-05T10:56:41Z"},{"alias_kind":"pith_short_8","alias_value":"PEUZORFE","created_at":"2026-07-05T10:56:41Z"}],"graph_snapshots":[{"event_id":"sha256:1bbe363a441115edc9fb2a4633f3a02623782d0ea2e21ce705c745e2c80d11a7","target":"graph","created_at":"2026-07-05T10:56:41Z","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/2505.00065/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated considerable success in open-book question answering (QA), where the task requires generating answers grounded in a provided external context. A critical challenge in open-book QA is to ensure that model responses are based on the provided context rather than its parametric knowledge, which can be outdated, incomplete, or incorrect. Existing evaluation methods, primarily based on the LLM-as-a-judge approach, face significant limitations, including biases, scalability issues, and dependence on costly external systems. To address these challenges, w","authors_text":"Adriana Correia, Ivan Vankov, Matyo Ivanov, Victor Botev","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T16:23:15Z","title":"ConSens: Assessing context grounding in open-book question answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00065","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":"sha256:021612c4977d4e40df4ae0a75bdc1bee0b79e8bcdd0469e60c57d73eb2fa022e","target":"record","created_at":"2026-07-05T10:56:41Z","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":"9cb445199e25c64eaac46f7b0a09c5df2868809bf4a7730793b1128dd81c2dad","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T16:23:15Z","title_canon_sha256":"1ed47167778ebca474ee410f5ce781c89146d652268641423ede9c52e9473652"},"schema_version":"1.0","source":{"id":"2505.00065","kind":"arxiv","version":1}},"canonical_sha256":"79299744a4dd19b5e1a5b5d000e04d7ef64110f4fb428fad17772c1412f8e578","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79299744a4dd19b5e1a5b5d000e04d7ef64110f4fb428fad17772c1412f8e578","first_computed_at":"2026-07-05T10:56:41.372450Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:56:41.372450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IlJUt31ACS1VTK96sKrobYH/ZCbHdpveIhgj96IMyc7jfmb5OrH9LDnKP4/8yTKZMg54iXKG8P/EPw0YlpuVCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:56:41.373020Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.00065","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:021612c4977d4e40df4ae0a75bdc1bee0b79e8bcdd0469e60c57d73eb2fa022e","sha256:1bbe363a441115edc9fb2a4633f3a02623782d0ea2e21ce705c745e2c80d11a7"],"state_sha256":"63ea85035393708a61b840f54dc3a42d2b3b97467cfe5a5613c74513fc5769f9"}