{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ARA5YNZ3AMM2RJ5BN2G5ZJR2EF","short_pith_number":"pith:ARA5YNZ3","canonical_record":{"source":{"id":"2312.08870","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T09:47:59Z","cross_cats_sorted":[],"title_canon_sha256":"83b64f150f0143c0c382a45f2be8545aed6f21f3c0d07431cff6cf0edecf5572","abstract_canon_sha256":"b2d12e1b480bcaeb34766ae1a944a91479b39730dd165ee234200c0981e7bb37"},"schema_version":"1.0"},"canonical_sha256":"0441dc373b0319a8a7a16e8ddca63a2173c0662abc8a4248c6363f802026f01c","source":{"kind":"arxiv","id":"2312.08870","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08870","created_at":"2026-07-05T10:22:43Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08870v2","created_at":"2026-07-05T10:22:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08870","created_at":"2026-07-05T10:22:43Z"},{"alias_kind":"pith_short_12","alias_value":"ARA5YNZ3AMM2","created_at":"2026-07-05T10:22:43Z"},{"alias_kind":"pith_short_16","alias_value":"ARA5YNZ3AMM2RJ5B","created_at":"2026-07-05T10:22:43Z"},{"alias_kind":"pith_short_8","alias_value":"ARA5YNZ3","created_at":"2026-07-05T10:22:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ARA5YNZ3AMM2RJ5BN2G5ZJR2EF","target":"record","payload":{"canonical_record":{"source":{"id":"2312.08870","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T09:47:59Z","cross_cats_sorted":[],"title_canon_sha256":"83b64f150f0143c0c382a45f2be8545aed6f21f3c0d07431cff6cf0edecf5572","abstract_canon_sha256":"b2d12e1b480bcaeb34766ae1a944a91479b39730dd165ee234200c0981e7bb37"},"schema_version":"1.0"},"canonical_sha256":"0441dc373b0319a8a7a16e8ddca63a2173c0662abc8a4248c6363f802026f01c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:43.566920Z","signature_b64":"rvHWsXtGtdli5R704jwQck7dzOEii2lcRRxqeNSPq3RX+HC8wU61A7+Denh+nVqRk2/ncqJPqn5laYN1VXDJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0441dc373b0319a8a7a16e8ddca63a2173c0662abc8a4248c6363f802026f01c","last_reissued_at":"2026-07-05T10:22:43.566232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:43.566232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.08870","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:22:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ggu7griHLBHMmdnuQgfXlqVc8F7uE4BN37Y4slj7MUqinBfbG7MH3xfbgr4PxZSnJikRzfIQ+gFoqt0opvAfCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:31:36.379867Z"},"content_sha256":"726c6c367b833fd8f15cc42c3cffd0a1f662ab4533e1d793ef815dfda8785979","schema_version":"1.0","event_id":"sha256:726c6c367b833fd8f15cc42c3cffd0a1f662ab4533e1d793ef815dfda8785979"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ARA5YNZ3AMM2RJ5BN2G5ZJR2EF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vista-LLaMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Ma, Heng Wang, Jiashi Feng, Xiaojie Jin, Yi Yang, Yuchen Xian","submitted_at":"2023-12-12T09:47:59Z","abstract_excerpt":"Recent advances in large video-language models have displayed promising outcomes in video comprehension. Current approaches straightforwardly convert video into language tokens and employ large language models for multi-modal tasks. However, this method often leads to the generation of irrelevant content, commonly known as \"hallucination\", as the length of the text increases and the impact of the video diminishes. To address this problem, we propose Vista-LLaMA, a novel framework that maintains the consistent distance between all visual tokens and any language tokens, irrespective of the gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08870","kind":"arxiv","version":2},"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/2312.08870/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":"2026-07-05T10:22:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q63me6VuVbObtoJYICStozlJUEUwuu6uaJV5padtp4+aXt9nuJC0U9amf0zCbn6FekkeS/R9W5ykW1H0yXB5Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:31:36.380705Z"},"content_sha256":"e4ef19975f72a3fb7f7fbd098df3adaae3a8420846a3fbf47916d7cfcec386d2","schema_version":"1.0","event_id":"sha256:e4ef19975f72a3fb7f7fbd098df3adaae3a8420846a3fbf47916d7cfcec386d2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ARA5YNZ3AMM2RJ5BN2G5ZJR2EF/bundle.json","state_url":"https://pith.science/pith/ARA5YNZ3AMM2RJ5BN2G5ZJR2EF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ARA5YNZ3AMM2RJ5BN2G5ZJR2EF/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":"2026-08-05T23:31:36Z","links":{"resolver":"https://pith.science/pith/ARA5YNZ3AMM2RJ5BN2G5ZJR2EF","bundle":"https://pith.science/pith/ARA5YNZ3AMM2RJ5BN2G5ZJR2EF/bundle.json","state":"https://pith.science/pith/ARA5YNZ3AMM2RJ5BN2G5ZJR2EF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ARA5YNZ3AMM2RJ5BN2G5ZJR2EF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ARA5YNZ3AMM2RJ5BN2G5ZJR2EF","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":"b2d12e1b480bcaeb34766ae1a944a91479b39730dd165ee234200c0981e7bb37","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T09:47:59Z","title_canon_sha256":"83b64f150f0143c0c382a45f2be8545aed6f21f3c0d07431cff6cf0edecf5572"},"schema_version":"1.0","source":{"id":"2312.08870","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08870","created_at":"2026-07-05T10:22:43Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08870v2","created_at":"2026-07-05T10:22:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08870","created_at":"2026-07-05T10:22:43Z"},{"alias_kind":"pith_short_12","alias_value":"ARA5YNZ3AMM2","created_at":"2026-07-05T10:22:43Z"},{"alias_kind":"pith_short_16","alias_value":"ARA5YNZ3AMM2RJ5B","created_at":"2026-07-05T10:22:43Z"},{"alias_kind":"pith_short_8","alias_value":"ARA5YNZ3","created_at":"2026-07-05T10:22:43Z"}],"graph_snapshots":[{"event_id":"sha256:e4ef19975f72a3fb7f7fbd098df3adaae3a8420846a3fbf47916d7cfcec386d2","target":"graph","created_at":"2026-07-05T10:22:43Z","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/2312.08870/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large video-language models have displayed promising outcomes in video comprehension. Current approaches straightforwardly convert video into language tokens and employ large language models for multi-modal tasks. However, this method often leads to the generation of irrelevant content, commonly known as \"hallucination\", as the length of the text increases and the impact of the video diminishes. To address this problem, we propose Vista-LLaMA, a novel framework that maintains the consistent distance between all visual tokens and any language tokens, irrespective of the gener","authors_text":"Fan Ma, Heng Wang, Jiashi Feng, Xiaojie Jin, Yi Yang, Yuchen Xian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T09:47:59Z","title":"Vista-LLaMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08870","kind":"arxiv","version":2},"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":"sha256:726c6c367b833fd8f15cc42c3cffd0a1f662ab4533e1d793ef815dfda8785979","target":"record","created_at":"2026-07-05T10:22:43Z","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":"b2d12e1b480bcaeb34766ae1a944a91479b39730dd165ee234200c0981e7bb37","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T09:47:59Z","title_canon_sha256":"83b64f150f0143c0c382a45f2be8545aed6f21f3c0d07431cff6cf0edecf5572"},"schema_version":"1.0","source":{"id":"2312.08870","kind":"arxiv","version":2}},"canonical_sha256":"0441dc373b0319a8a7a16e8ddca63a2173c0662abc8a4248c6363f802026f01c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0441dc373b0319a8a7a16e8ddca63a2173c0662abc8a4248c6363f802026f01c","first_computed_at":"2026-07-05T10:22:43.566232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:43.566232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rvHWsXtGtdli5R704jwQck7dzOEii2lcRRxqeNSPq3RX+HC8wU61A7+Denh+nVqRk2/ncqJPqn5laYN1VXDJDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:43.566920Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.08870","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:726c6c367b833fd8f15cc42c3cffd0a1f662ab4533e1d793ef815dfda8785979","sha256:e4ef19975f72a3fb7f7fbd098df3adaae3a8420846a3fbf47916d7cfcec386d2"],"state_sha256":"a4e4c646670f43178d80357dc0cf912ad0e1e9aa3322da98289f1cafb40dd574"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+YfR00hUPTGYIeh6nvNLREUT3utJsNPrRv12WowYztk+6lcGgr2bjwv6iKJfSbTpZeNTDh8Ohq65w6F2s5YBBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:31:36.385554Z","bundle_sha256":"c0bfc2b8ccc450fbd4f97e36562d3f1fc03ea12b8d21476ccd4d463b82616997"}}