{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HJFVP4IF47V45PYGELMSRLGFEY","short_pith_number":"pith:HJFVP4IF","schema_version":"1.0","canonical_sha256":"3a4b57f105e7ebcebf0622d928acc526205d42382a0f12c86be8ca4edcfa400c","source":{"kind":"arxiv","id":"2407.12679","version":1},"attestation_state":"computed","paper":{"title":"Goldfish: Vision-Language Understanding of Arbitrarily Long Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deyao Zhu, Eslam Abdelrahman, Essam Sleiman, Jian Ding, J\\\"urgen Schmidhuber, Kirolos Ataallah, Mingchen Zhuge, Mohamed Elhoseiny, Xiaoqian Shen","submitted_at":"2024-07-17T15:59:32Z","abstract_excerpt":"Most current LLM-based models for video understanding can process videos within minutes. However, they struggle with lengthy videos due to challenges such as \"noise and redundancy\", as well as \"memory and computation\" constraints. In this paper, we present Goldfish, a methodology tailored for comprehending videos of arbitrary lengths. We also introduce the TVQA-long benchmark, specifically designed to evaluate models' capabilities in understanding long videos with questions in both vision and text content. Goldfish approaches these challenges with an efficient retrieval mechanism that initiall"},"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":"2407.12679","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T15:59:32Z","cross_cats_sorted":[],"title_canon_sha256":"f3cbecf7e194117d2880757765715c818a43b3c8209a4062eac1fa0cbc79974a","abstract_canon_sha256":"ac84a7d7209b5b581ec2be872b8e938b44c8f51001b7ce83479c25be4f7be965"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:08.297687Z","signature_b64":"av7T8wsX2L8+qu/H+kXeprfXckQfGUWh0rw+YtGgOwYD9XMa8XzffpFKxnz57EDAXY3Zuw333JWJ0kyFbbHgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a4b57f105e7ebcebf0622d928acc526205d42382a0f12c86be8ca4edcfa400c","last_reissued_at":"2026-07-05T08:45:08.297102Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:08.297102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Goldfish: Vision-Language Understanding of Arbitrarily Long Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deyao Zhu, Eslam Abdelrahman, Essam Sleiman, Jian Ding, J\\\"urgen Schmidhuber, Kirolos Ataallah, Mingchen Zhuge, Mohamed Elhoseiny, Xiaoqian Shen","submitted_at":"2024-07-17T15:59:32Z","abstract_excerpt":"Most current LLM-based models for video understanding can process videos within minutes. However, they struggle with lengthy videos due to challenges such as \"noise and redundancy\", as well as \"memory and computation\" constraints. In this paper, we present Goldfish, a methodology tailored for comprehending videos of arbitrary lengths. We also introduce the TVQA-long benchmark, specifically designed to evaluate models' capabilities in understanding long videos with questions in both vision and text content. Goldfish approaches these challenges with an efficient retrieval mechanism that initiall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12679","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/2407.12679/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":"2407.12679","created_at":"2026-07-05T08:45:08.297177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12679v1","created_at":"2026-07-05T08:45:08.297177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12679","created_at":"2026-07-05T08:45:08.297177+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJFVP4IF47V4","created_at":"2026-07-05T08:45:08.297177+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJFVP4IF47V45PYG","created_at":"2026-07-05T08:45:08.297177+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJFVP4IF","created_at":"2026-07-05T08:45:08.297177+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30288","citing_title":"VisReflect: Latent Visual Reflection for Fine-Grained Perception in Long Visual Context","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31069","citing_title":"Towards Effective Long-Video Event Prediction via Multi-Level Event Semantics Mining","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23198","citing_title":"StoryTR: Narrative-Centric Video Temporal Retrieval with Theory of Mind Reasoning","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HJFVP4IF47V45PYGELMSRLGFEY","json":"https://pith.science/pith/HJFVP4IF47V45PYGELMSRLGFEY.json","graph_json":"https://pith.science/api/pith-number/HJFVP4IF47V45PYGELMSRLGFEY/graph.json","events_json":"https://pith.science/api/pith-number/HJFVP4IF47V45PYGELMSRLGFEY/events.json","paper":"https://pith.science/paper/HJFVP4IF"},"agent_actions":{"view_html":"https://pith.science/pith/HJFVP4IF47V45PYGELMSRLGFEY","download_json":"https://pith.science/pith/HJFVP4IF47V45PYGELMSRLGFEY.json","view_paper":"https://pith.science/paper/HJFVP4IF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12679&json=true","fetch_graph":"https://pith.science/api/pith-number/HJFVP4IF47V45PYGELMSRLGFEY/graph.json","fetch_events":"https://pith.science/api/pith-number/HJFVP4IF47V45PYGELMSRLGFEY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJFVP4IF47V45PYGELMSRLGFEY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJFVP4IF47V45PYGELMSRLGFEY/action/storage_attestation","attest_author":"https://pith.science/pith/HJFVP4IF47V45PYGELMSRLGFEY/action/author_attestation","sign_citation":"https://pith.science/pith/HJFVP4IF47V45PYGELMSRLGFEY/action/citation_signature","submit_replication":"https://pith.science/pith/HJFVP4IF47V45PYGELMSRLGFEY/action/replication_record"}},"created_at":"2026-07-05T08:45:08.297177+00:00","updated_at":"2026-07-05T08:45:08.297177+00:00"}