{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EDCLSZMHHC2XN7A2B2NSMXDXMN","short_pith_number":"pith:EDCLSZMH","canonical_record":{"source":{"id":"2305.14540","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T21:50:06Z","cross_cats_sorted":[],"title_canon_sha256":"77e38b6b833e8a666b804d150323dc4f50aa51c47b6b08086dce43c96beb082a","abstract_canon_sha256":"011ae5577f6f25a29f7f75538c5265558edcf70a0fd97d41125d6e8d7daad35e"},"schema_version":"1.0"},"canonical_sha256":"20c4b9658738b576fc1a0e9b265c77637d4f8666c6171eac77c0476ba0219fbf","source":{"kind":"arxiv","id":"2305.14540","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14540","created_at":"2026-07-05T06:13:24Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14540v1","created_at":"2026-07-05T06:13:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14540","created_at":"2026-07-05T06:13:24Z"},{"alias_kind":"pith_short_12","alias_value":"EDCLSZMHHC2X","created_at":"2026-07-05T06:13:24Z"},{"alias_kind":"pith_short_16","alias_value":"EDCLSZMHHC2XN7A2","created_at":"2026-07-05T06:13:24Z"},{"alias_kind":"pith_short_8","alias_value":"EDCLSZMH","created_at":"2026-07-05T06:13:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EDCLSZMHHC2XN7A2B2NSMXDXMN","target":"record","payload":{"canonical_record":{"source":{"id":"2305.14540","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T21:50:06Z","cross_cats_sorted":[],"title_canon_sha256":"77e38b6b833e8a666b804d150323dc4f50aa51c47b6b08086dce43c96beb082a","abstract_canon_sha256":"011ae5577f6f25a29f7f75538c5265558edcf70a0fd97d41125d6e8d7daad35e"},"schema_version":"1.0"},"canonical_sha256":"20c4b9658738b576fc1a0e9b265c77637d4f8666c6171eac77c0476ba0219fbf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:24.631402Z","signature_b64":"rCQIEBbo8DqRdpJf2uxVU0jdq/bSutr3H39XN997F0wvX9SNqF1PqIwkJr9doeDCnJFjI1Q0zGJS2jtjGlE7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20c4b9658738b576fc1a0e9b265c77637d4f8666c6171eac77c0476ba0219fbf","last_reissued_at":"2026-07-05T06:13:24.631013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:24.631013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.14540","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":"2026-07-05T06:13:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I2xSL3qQSLZSVHWiMHRxilTHZDfK1lKmILXmZ5LkSY4uPUo3Gr196VsxTaAJ/0fSZb+p/NGQNozfCKdTPcApDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:31:28.249688Z"},"content_sha256":"62a0d4a675a3c421464e065f04425a8ad4b6599c6d57d645ded184c8dac38508","schema_version":"1.0","event_id":"sha256:62a0d4a675a3c421464e065f04425a8ad4b6599c6d57d645ded184c8dac38508"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EDCLSZMHHC2XN7A2B2NSMXDXMN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander R. Fabbri, Caiming Xiong, Chien-Sheng Wu, Divyansh Agarwal, Philippe Laban, Shafiq Joty, Wojciech Kry\\'sci\\'nski","submitted_at":"2023-05-23T21:50:06Z","abstract_excerpt":"With the recent appearance of LLMs in practical settings, having methods that can effectively detect factual inconsistencies is crucial to reduce the propagation of misinformation and improve trust in model outputs. When testing on existing factual consistency benchmarks, we find that a few large language models (LLMs) perform competitively on classification benchmarks for factual inconsistency detection compared to traditional non-LLM methods. However, a closer analysis reveals that most LLMs fail on more complex formulations of the task and exposes issues with existing evaluation benchmarks,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14540","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/2305.14540/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":"2026-07-05T06:13:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QNDou/yCnCKmuH12oVF5n6QuMBwhWW9rGQtIJiUtPEoL5LzERPPXyUvmUfbgimySBZb2aBLA5URG17U+RkjbAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:31:28.250364Z"},"content_sha256":"23035c3872fcd4c68075343ef79a3f05c2984b0ce7a6d64159d56aa499b8170a","schema_version":"1.0","event_id":"sha256:23035c3872fcd4c68075343ef79a3f05c2984b0ce7a6d64159d56aa499b8170a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EDCLSZMHHC2XN7A2B2NSMXDXMN/bundle.json","state_url":"https://pith.science/pith/EDCLSZMHHC2XN7A2B2NSMXDXMN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EDCLSZMHHC2XN7A2B2NSMXDXMN/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":"2026-08-03T20:31:28Z","links":{"resolver":"https://pith.science/pith/EDCLSZMHHC2XN7A2B2NSMXDXMN","bundle":"https://pith.science/pith/EDCLSZMHHC2XN7A2B2NSMXDXMN/bundle.json","state":"https://pith.science/pith/EDCLSZMHHC2XN7A2B2NSMXDXMN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EDCLSZMHHC2XN7A2B2NSMXDXMN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EDCLSZMHHC2XN7A2B2NSMXDXMN","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":"011ae5577f6f25a29f7f75538c5265558edcf70a0fd97d41125d6e8d7daad35e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T21:50:06Z","title_canon_sha256":"77e38b6b833e8a666b804d150323dc4f50aa51c47b6b08086dce43c96beb082a"},"schema_version":"1.0","source":{"id":"2305.14540","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14540","created_at":"2026-07-05T06:13:24Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14540v1","created_at":"2026-07-05T06:13:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14540","created_at":"2026-07-05T06:13:24Z"},{"alias_kind":"pith_short_12","alias_value":"EDCLSZMHHC2X","created_at":"2026-07-05T06:13:24Z"},{"alias_kind":"pith_short_16","alias_value":"EDCLSZMHHC2XN7A2","created_at":"2026-07-05T06:13:24Z"},{"alias_kind":"pith_short_8","alias_value":"EDCLSZMH","created_at":"2026-07-05T06:13:24Z"}],"graph_snapshots":[{"event_id":"sha256:23035c3872fcd4c68075343ef79a3f05c2984b0ce7a6d64159d56aa499b8170a","target":"graph","created_at":"2026-07-05T06:13:24Z","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/2305.14540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the recent appearance of LLMs in practical settings, having methods that can effectively detect factual inconsistencies is crucial to reduce the propagation of misinformation and improve trust in model outputs. When testing on existing factual consistency benchmarks, we find that a few large language models (LLMs) perform competitively on classification benchmarks for factual inconsistency detection compared to traditional non-LLM methods. However, a closer analysis reveals that most LLMs fail on more complex formulations of the task and exposes issues with existing evaluation benchmarks,","authors_text":"Alexander R. Fabbri, Caiming Xiong, Chien-Sheng Wu, Divyansh Agarwal, Philippe Laban, Shafiq Joty, Wojciech Kry\\'sci\\'nski","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T21:50:06Z","title":"LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14540","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":"sha256:62a0d4a675a3c421464e065f04425a8ad4b6599c6d57d645ded184c8dac38508","target":"record","created_at":"2026-07-05T06:13:24Z","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":"011ae5577f6f25a29f7f75538c5265558edcf70a0fd97d41125d6e8d7daad35e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T21:50:06Z","title_canon_sha256":"77e38b6b833e8a666b804d150323dc4f50aa51c47b6b08086dce43c96beb082a"},"schema_version":"1.0","source":{"id":"2305.14540","kind":"arxiv","version":1}},"canonical_sha256":"20c4b9658738b576fc1a0e9b265c77637d4f8666c6171eac77c0476ba0219fbf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20c4b9658738b576fc1a0e9b265c77637d4f8666c6171eac77c0476ba0219fbf","first_computed_at":"2026-07-05T06:13:24.631013Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:24.631013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rCQIEBbo8DqRdpJf2uxVU0jdq/bSutr3H39XN997F0wvX9SNqF1PqIwkJr9doeDCnJFjI1Q0zGJS2jtjGlE7Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:24.631402Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14540","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62a0d4a675a3c421464e065f04425a8ad4b6599c6d57d645ded184c8dac38508","sha256:23035c3872fcd4c68075343ef79a3f05c2984b0ce7a6d64159d56aa499b8170a"],"state_sha256":"851fe13e74255247f452af0a117e377a5909652402c27d19c609e6ae8fc76c18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"21uswvzMP1/gyL1uBNfhq1I18Yum1Wv8lzWjADgk1utQ+aTzRNk/aH18OFT8c8S7yQ6YXUi6Pzz4FyU3eCAHDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:31:28.257463Z","bundle_sha256":"45c3368b7b06b8afa8d0994752881a8c5a636fdf5e45770500b00ae3df725d50"}}