{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XTNSBWRQHF5YH7KUOKDL74IZE3","short_pith_number":"pith:XTNSBWRQ","canonical_record":{"source":{"id":"2303.02961","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-06T08:32:50Z","cross_cats_sorted":[],"title_canon_sha256":"a95928eeeb555e2c4f88725e8f90635d5d4f71d1fbcdda765b046a9e7f039ade","abstract_canon_sha256":"8ff62b966453b5ec5db325a8a36d71246224fc76356b053075ed3dcece96c9b4"},"schema_version":"1.0"},"canonical_sha256":"bcdb20da30397b83fd547286bff11926e3bd56fe6fd6ae42562a016a3968d74d","source":{"kind":"arxiv","id":"2303.02961","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.02961","created_at":"2026-07-05T05:48:17Z"},{"alias_kind":"arxiv_version","alias_value":"2303.02961v1","created_at":"2026-07-05T05:48:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02961","created_at":"2026-07-05T05:48:17Z"},{"alias_kind":"pith_short_12","alias_value":"XTNSBWRQHF5Y","created_at":"2026-07-05T05:48:17Z"},{"alias_kind":"pith_short_16","alias_value":"XTNSBWRQHF5YH7KU","created_at":"2026-07-05T05:48:17Z"},{"alias_kind":"pith_short_8","alias_value":"XTNSBWRQ","created_at":"2026-07-05T05:48:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XTNSBWRQHF5YH7KUOKDL74IZE3","target":"record","payload":{"canonical_record":{"source":{"id":"2303.02961","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-06T08:32:50Z","cross_cats_sorted":[],"title_canon_sha256":"a95928eeeb555e2c4f88725e8f90635d5d4f71d1fbcdda765b046a9e7f039ade","abstract_canon_sha256":"8ff62b966453b5ec5db325a8a36d71246224fc76356b053075ed3dcece96c9b4"},"schema_version":"1.0"},"canonical_sha256":"bcdb20da30397b83fd547286bff11926e3bd56fe6fd6ae42562a016a3968d74d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:17.568039Z","signature_b64":"56omKff/rg+Ifh8hR5qj7TrVVK6WSn7QdCCVnVn0gwj6kS3yjhmUNg8rjoygzaIxS/ZbmcioZ1gTbG1Q5V2MAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcdb20da30397b83fd547286bff11926e3bd56fe6fd6ae42562a016a3968d74d","last_reissued_at":"2026-07-05T05:48:17.567580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:17.567580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.02961","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":"2026-07-05T05:48:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8aolny1wKxfAwJbo2jxiW9SN6uRemHzANZlLovnf17z9pwH+zbJNeztHEA0h+wZbHGzACcGfMEqVys61ODn3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:59:18.072759Z"},"content_sha256":"1d2dd8139ebdf3f7170737fc96e4104b32da59a2163fb4956c2af25acefa01e1","schema_version":"1.0","event_id":"sha256:1d2dd8139ebdf3f7170737fc96e4104b32da59a2163fb4956c2af25acefa01e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XTNSBWRQHF5YH7KUOKDL74IZE3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Models See Hallucinations: Evaluating the Factuality in Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hui Liu, Xiaojun Wan","submitted_at":"2023-03-06T08:32:50Z","abstract_excerpt":"Video captioning aims to describe events in a video with natural language. In recent years, many works have focused on improving captioning models' performance. However, like other text generation tasks, it risks introducing factual errors not supported by the input video. These factual errors can seriously affect the quality of the generated text, sometimes making it completely unusable. Although factual consistency has received much research attention in text-to-text tasks (e.g., summarization), it is less studied in the context of vision-based text generation. In this work, we conduct a det"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02961","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/2303.02961/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":"2026-07-05T05:48:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ub8/wRKHOHw3uvVCQH1Mn8nEBwsOkaG8Am3aiQwvZTfDRtvwRhQY4hFhsohk15sNDWlwGQAaeyKnW3sxDwiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:59:18.073261Z"},"content_sha256":"8d57660d1d64ad5aa81ef8ad724808525de092f00835f713654c776d62219833","schema_version":"1.0","event_id":"sha256:8d57660d1d64ad5aa81ef8ad724808525de092f00835f713654c776d62219833"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XTNSBWRQHF5YH7KUOKDL74IZE3/bundle.json","state_url":"https://pith.science/pith/XTNSBWRQHF5YH7KUOKDL74IZE3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XTNSBWRQHF5YH7KUOKDL74IZE3/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":"2026-08-06T09:59:18Z","links":{"resolver":"https://pith.science/pith/XTNSBWRQHF5YH7KUOKDL74IZE3","bundle":"https://pith.science/pith/XTNSBWRQHF5YH7KUOKDL74IZE3/bundle.json","state":"https://pith.science/pith/XTNSBWRQHF5YH7KUOKDL74IZE3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XTNSBWRQHF5YH7KUOKDL74IZE3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XTNSBWRQHF5YH7KUOKDL74IZE3","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":"8ff62b966453b5ec5db325a8a36d71246224fc76356b053075ed3dcece96c9b4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-06T08:32:50Z","title_canon_sha256":"a95928eeeb555e2c4f88725e8f90635d5d4f71d1fbcdda765b046a9e7f039ade"},"schema_version":"1.0","source":{"id":"2303.02961","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.02961","created_at":"2026-07-05T05:48:17Z"},{"alias_kind":"arxiv_version","alias_value":"2303.02961v1","created_at":"2026-07-05T05:48:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02961","created_at":"2026-07-05T05:48:17Z"},{"alias_kind":"pith_short_12","alias_value":"XTNSBWRQHF5Y","created_at":"2026-07-05T05:48:17Z"},{"alias_kind":"pith_short_16","alias_value":"XTNSBWRQHF5YH7KU","created_at":"2026-07-05T05:48:17Z"},{"alias_kind":"pith_short_8","alias_value":"XTNSBWRQ","created_at":"2026-07-05T05:48:17Z"}],"graph_snapshots":[{"event_id":"sha256:8d57660d1d64ad5aa81ef8ad724808525de092f00835f713654c776d62219833","target":"graph","created_at":"2026-07-05T05:48:17Z","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/2303.02961/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video captioning aims to describe events in a video with natural language. In recent years, many works have focused on improving captioning models' performance. However, like other text generation tasks, it risks introducing factual errors not supported by the input video. These factual errors can seriously affect the quality of the generated text, sometimes making it completely unusable. Although factual consistency has received much research attention in text-to-text tasks (e.g., summarization), it is less studied in the context of vision-based text generation. In this work, we conduct a det","authors_text":"Hui Liu, Xiaojun Wan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-06T08:32:50Z","title":"Models See Hallucinations: Evaluating the Factuality in Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02961","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":"sha256:1d2dd8139ebdf3f7170737fc96e4104b32da59a2163fb4956c2af25acefa01e1","target":"record","created_at":"2026-07-05T05:48:17Z","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":"8ff62b966453b5ec5db325a8a36d71246224fc76356b053075ed3dcece96c9b4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-06T08:32:50Z","title_canon_sha256":"a95928eeeb555e2c4f88725e8f90635d5d4f71d1fbcdda765b046a9e7f039ade"},"schema_version":"1.0","source":{"id":"2303.02961","kind":"arxiv","version":1}},"canonical_sha256":"bcdb20da30397b83fd547286bff11926e3bd56fe6fd6ae42562a016a3968d74d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcdb20da30397b83fd547286bff11926e3bd56fe6fd6ae42562a016a3968d74d","first_computed_at":"2026-07-05T05:48:17.567580Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:48:17.567580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"56omKff/rg+Ifh8hR5qj7TrVVK6WSn7QdCCVnVn0gwj6kS3yjhmUNg8rjoygzaIxS/ZbmcioZ1gTbG1Q5V2MAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:48:17.568039Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.02961","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d2dd8139ebdf3f7170737fc96e4104b32da59a2163fb4956c2af25acefa01e1","sha256:8d57660d1d64ad5aa81ef8ad724808525de092f00835f713654c776d62219833"],"state_sha256":"a73c2195e7c15ef92670971f16ea16fe0cb10fdc875cc28fe81cbf31d283b6f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ufbBQ3JM4lS+D7GG94BzeazvoAWPr1l/xrQm3zVsJmx2wiXJ8l7OoCPrspSW/l1G62rH4uLYuNE1OXDGhu6+BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:59:18.081007Z","bundle_sha256":"de6963067cf35ad8fb8f0892705bca839af0072a663740d2baf12febb076e597"}}