{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5TTQIQAVBONAXXW4JW74AZCE33","short_pith_number":"pith:5TTQIQAV","schema_version":"1.0","canonical_sha256":"ece70440150b9a0bdedc4dbfc06444defd18b2f2e60a8ae32d03a912a176275f","source":{"kind":"arxiv","id":"2401.09861","version":1},"attestation_state":"computed","paper":{"title":"Temporal Insight Enhancement: Mitigating Temporal Hallucination in Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jun Sun, Li Sun, Liuan Wang, Takayuki Okatani","submitted_at":"2024-01-18T10:18:48Z","abstract_excerpt":"Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced the comprehension of multimedia content, bringing together diverse modalities such as text, images, and videos. However, a critical challenge faced by these models, especially when processing video inputs, is the occurrence of hallucinations - erroneous perceptions or interpretations, particularly at the event level. This study introduces an innovative method to address event-level hallucinations in MLLMs, focusing on specific temporal understanding in video content. Our approach leverages a novel frame"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.09861","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-18T10:18:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a1d1a23fe61915ac8690df4af4024bb791e9736e3512eb2aa62349606e9179c","abstract_canon_sha256":"563386353107aaf36a04d485827633a94ec8a197c2460ee369b41f84f2169de1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:03.411552Z","signature_b64":"twR+c4UJtpyXNrhg0yo2b9dPyCarTle3bxl0l5XTxTq0QNssUAsJ2szeK94S5Kg1Eu+CWrMccLpMJZpTUrdiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ece70440150b9a0bdedc4dbfc06444defd18b2f2e60a8ae32d03a912a176275f","last_reissued_at":"2026-07-05T07:35:03.411140Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:03.411140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal Insight Enhancement: Mitigating Temporal Hallucination in Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jun Sun, Li Sun, Liuan Wang, Takayuki Okatani","submitted_at":"2024-01-18T10:18:48Z","abstract_excerpt":"Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced the comprehension of multimedia content, bringing together diverse modalities such as text, images, and videos. However, a critical challenge faced by these models, especially when processing video inputs, is the occurrence of hallucinations - erroneous perceptions or interpretations, particularly at the event level. This study introduces an innovative method to address event-level hallucinations in MLLMs, focusing on specific temporal understanding in video content. Our approach leverages a novel frame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09861","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/2401.09861/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.09861","created_at":"2026-07-05T07:35:03.411211+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.09861v1","created_at":"2026-07-05T07:35:03.411211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09861","created_at":"2026-07-05T07:35:03.411211+00:00"},{"alias_kind":"pith_short_12","alias_value":"5TTQIQAVBONA","created_at":"2026-07-05T07:35:03.411211+00:00"},{"alias_kind":"pith_short_16","alias_value":"5TTQIQAVBONAXXW4","created_at":"2026-07-05T07:35:03.411211+00:00"},{"alias_kind":"pith_short_8","alias_value":"5TTQIQAV","created_at":"2026-07-05T07:35:03.411211+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.10674","citing_title":"Can Multimodal LLMs do Visual Temporal Understanding and Reasoning? The answer is No!","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5TTQIQAVBONAXXW4JW74AZCE33","json":"https://pith.science/pith/5TTQIQAVBONAXXW4JW74AZCE33.json","graph_json":"https://pith.science/api/pith-number/5TTQIQAVBONAXXW4JW74AZCE33/graph.json","events_json":"https://pith.science/api/pith-number/5TTQIQAVBONAXXW4JW74AZCE33/events.json","paper":"https://pith.science/paper/5TTQIQAV"},"agent_actions":{"view_html":"https://pith.science/pith/5TTQIQAVBONAXXW4JW74AZCE33","download_json":"https://pith.science/pith/5TTQIQAVBONAXXW4JW74AZCE33.json","view_paper":"https://pith.science/paper/5TTQIQAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.09861&json=true","fetch_graph":"https://pith.science/api/pith-number/5TTQIQAVBONAXXW4JW74AZCE33/graph.json","fetch_events":"https://pith.science/api/pith-number/5TTQIQAVBONAXXW4JW74AZCE33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5TTQIQAVBONAXXW4JW74AZCE33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5TTQIQAVBONAXXW4JW74AZCE33/action/storage_attestation","attest_author":"https://pith.science/pith/5TTQIQAVBONAXXW4JW74AZCE33/action/author_attestation","sign_citation":"https://pith.science/pith/5TTQIQAVBONAXXW4JW74AZCE33/action/citation_signature","submit_replication":"https://pith.science/pith/5TTQIQAVBONAXXW4JW74AZCE33/action/replication_record"}},"created_at":"2026-07-05T07:35:03.411211+00:00","updated_at":"2026-07-05T07:35:03.411211+00:00"}