{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2PYV7EC6ZEPYALMM6MJTMXLQST","short_pith_number":"pith:2PYV7EC6","canonical_record":{"source":{"id":"2505.05949","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T10:51:29Z","cross_cats_sorted":[],"title_canon_sha256":"600122431e221e49b8efd496e84b665df032e1ba0dee46551dd0b31057aed739","abstract_canon_sha256":"0b8a59fb8dcdd7f873732dc7866ff786fa51d7af745aed0a972c9690da0b2f96"},"schema_version":"1.0"},"canonical_sha256":"d3f15f905ec91f802d8cf313365d7094edc326cddf40d7942c5bc3cfa6e8ccc5","source":{"kind":"arxiv","id":"2505.05949","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05949","created_at":"2026-07-05T11:00:50Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05949v1","created_at":"2026-07-05T11:00:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05949","created_at":"2026-07-05T11:00:50Z"},{"alias_kind":"pith_short_12","alias_value":"2PYV7EC6ZEPY","created_at":"2026-07-05T11:00:50Z"},{"alias_kind":"pith_short_16","alias_value":"2PYV7EC6ZEPYALMM","created_at":"2026-07-05T11:00:50Z"},{"alias_kind":"pith_short_8","alias_value":"2PYV7EC6","created_at":"2026-07-05T11:00:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2PYV7EC6ZEPYALMM6MJTMXLQST","target":"record","payload":{"canonical_record":{"source":{"id":"2505.05949","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T10:51:29Z","cross_cats_sorted":[],"title_canon_sha256":"600122431e221e49b8efd496e84b665df032e1ba0dee46551dd0b31057aed739","abstract_canon_sha256":"0b8a59fb8dcdd7f873732dc7866ff786fa51d7af745aed0a972c9690da0b2f96"},"schema_version":"1.0"},"canonical_sha256":"d3f15f905ec91f802d8cf313365d7094edc326cddf40d7942c5bc3cfa6e8ccc5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:50.389969Z","signature_b64":"JXP6n8NbFn7GXrIL7qDZXCJGUMubPsrdOYCHbocJ0i0g2vVx3JJP/x7+G6r0n7WsMPNpuCCtCRTnmeZuDNplDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3f15f905ec91f802d8cf313365d7094edc326cddf40d7942c5bc3cfa6e8ccc5","last_reissued_at":"2026-07-05T11:00:50.389467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:50.389467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.05949","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:00:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aupxap+xBDmJknCo5GeXlCSSgeGvrm5tIEoMxydbl7SdpSwzP0bikneYpuqfioTBixkf+D5pBM58mbPOxn5CAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T03:26:56.579808Z"},"content_sha256":"9285697aa6266031b5361b3bd0a1bae2d8048510c03661a672f4cbee8e8807d2","schema_version":"1.0","event_id":"sha256:9285697aa6266031b5361b3bd0a1bae2d8048510c03661a672f4cbee8e8807d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2PYV7EC6ZEPYALMM6MJTMXLQST","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NeoQA: Evidence-based Question Answering with Generated News Events","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Iryna Gurevych, Leonardo F. R. Ribeiro, Markus Dreyer, Max Glockner, Xiang Jiang","submitted_at":"2025-05-09T10:51:29Z","abstract_excerpt":"Evaluating Retrieval-Augmented Generation (RAG) in large language models (LLMs) is challenging because benchmarks can quickly become stale. Questions initially requiring retrieval may become answerable from pretraining knowledge as newer models incorporate more recent information during pretraining, making it difficult to distinguish evidence-based reasoning from recall. We introduce NeoQA (News Events for Out-of-training Question Answering), a benchmark designed to address this issue. To construct NeoQA, we generated timelines and knowledge bases of fictional news events and entities along wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05949","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/2505.05949/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:00:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yhAzIVaqhZNskHlJcQPP+yKUKJrHpN9Jn4lk0YeM/Z+k1TUZqj0j1zFacUXaeNFZ5yuvgtu4fhCpkYXJtwrbDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T03:26:56.580315Z"},"content_sha256":"8e4375d1a82e848eef5b969430dc0fd2d5aee0ee06bd9ca5d17617b10493836b","schema_version":"1.0","event_id":"sha256:8e4375d1a82e848eef5b969430dc0fd2d5aee0ee06bd9ca5d17617b10493836b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2PYV7EC6ZEPYALMM6MJTMXLQST/bundle.json","state_url":"https://pith.science/pith/2PYV7EC6ZEPYALMM6MJTMXLQST/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2PYV7EC6ZEPYALMM6MJTMXLQST/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T03:26:56Z","links":{"resolver":"https://pith.science/pith/2PYV7EC6ZEPYALMM6MJTMXLQST","bundle":"https://pith.science/pith/2PYV7EC6ZEPYALMM6MJTMXLQST/bundle.json","state":"https://pith.science/pith/2PYV7EC6ZEPYALMM6MJTMXLQST/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2PYV7EC6ZEPYALMM6MJTMXLQST/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2PYV7EC6ZEPYALMM6MJTMXLQST","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":"0b8a59fb8dcdd7f873732dc7866ff786fa51d7af745aed0a972c9690da0b2f96","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T10:51:29Z","title_canon_sha256":"600122431e221e49b8efd496e84b665df032e1ba0dee46551dd0b31057aed739"},"schema_version":"1.0","source":{"id":"2505.05949","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05949","created_at":"2026-07-05T11:00:50Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05949v1","created_at":"2026-07-05T11:00:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05949","created_at":"2026-07-05T11:00:50Z"},{"alias_kind":"pith_short_12","alias_value":"2PYV7EC6ZEPY","created_at":"2026-07-05T11:00:50Z"},{"alias_kind":"pith_short_16","alias_value":"2PYV7EC6ZEPYALMM","created_at":"2026-07-05T11:00:50Z"},{"alias_kind":"pith_short_8","alias_value":"2PYV7EC6","created_at":"2026-07-05T11:00:50Z"}],"graph_snapshots":[{"event_id":"sha256:8e4375d1a82e848eef5b969430dc0fd2d5aee0ee06bd9ca5d17617b10493836b","target":"graph","created_at":"2026-07-05T11:00:50Z","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/2505.05949/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating Retrieval-Augmented Generation (RAG) in large language models (LLMs) is challenging because benchmarks can quickly become stale. Questions initially requiring retrieval may become answerable from pretraining knowledge as newer models incorporate more recent information during pretraining, making it difficult to distinguish evidence-based reasoning from recall. We introduce NeoQA (News Events for Out-of-training Question Answering), a benchmark designed to address this issue. To construct NeoQA, we generated timelines and knowledge bases of fictional news events and entities along wi","authors_text":"Iryna Gurevych, Leonardo F. R. Ribeiro, Markus Dreyer, Max Glockner, Xiang Jiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T10:51:29Z","title":"NeoQA: Evidence-based Question Answering with Generated News Events"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05949","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":"sha256:9285697aa6266031b5361b3bd0a1bae2d8048510c03661a672f4cbee8e8807d2","target":"record","created_at":"2026-07-05T11:00:50Z","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":"0b8a59fb8dcdd7f873732dc7866ff786fa51d7af745aed0a972c9690da0b2f96","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T10:51:29Z","title_canon_sha256":"600122431e221e49b8efd496e84b665df032e1ba0dee46551dd0b31057aed739"},"schema_version":"1.0","source":{"id":"2505.05949","kind":"arxiv","version":1}},"canonical_sha256":"d3f15f905ec91f802d8cf313365d7094edc326cddf40d7942c5bc3cfa6e8ccc5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3f15f905ec91f802d8cf313365d7094edc326cddf40d7942c5bc3cfa6e8ccc5","first_computed_at":"2026-07-05T11:00:50.389467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:50.389467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JXP6n8NbFn7GXrIL7qDZXCJGUMubPsrdOYCHbocJ0i0g2vVx3JJP/x7+G6r0n7WsMPNpuCCtCRTnmeZuDNplDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:50.389969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.05949","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9285697aa6266031b5361b3bd0a1bae2d8048510c03661a672f4cbee8e8807d2","sha256:8e4375d1a82e848eef5b969430dc0fd2d5aee0ee06bd9ca5d17617b10493836b"],"state_sha256":"9f5173d0910e3a6eca7b610b9922660905b494cee841bc648753ddc988cad02e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5IpyoDbf3IE7szQOkk3C+PRewXdMrv+cYCLIWMZkeGyk8PUpvGORVRhF2D2hv9uMfES9/VeM9BN4kabpb5ADCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T03:26:56.584610Z","bundle_sha256":"0c83b40823164d4879607ad7cd877e54fee3dd0e90ded42f1646bd3ef5afa831"}}