{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HJFVP4IF47V45PYGELMSRLGFEY","short_pith_number":"pith:HJFVP4IF","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"},"canonical_sha256":"3a4b57f105e7ebcebf0622d928acc526205d42382a0f12c86be8ca4edcfa400c","source":{"kind":"arxiv","id":"2407.12679","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12679","created_at":"2026-07-05T08:45:08Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12679v1","created_at":"2026-07-05T08:45:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12679","created_at":"2026-07-05T08:45:08Z"},{"alias_kind":"pith_short_12","alias_value":"HJFVP4IF47V4","created_at":"2026-07-05T08:45:08Z"},{"alias_kind":"pith_short_16","alias_value":"HJFVP4IF47V45PYG","created_at":"2026-07-05T08:45:08Z"},{"alias_kind":"pith_short_8","alias_value":"HJFVP4IF","created_at":"2026-07-05T08:45:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HJFVP4IF47V45PYGELMSRLGFEY","target":"record","payload":{"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"},"canonical_sha256":"3a4b57f105e7ebcebf0622d928acc526205d42382a0f12c86be8ca4edcfa400c","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"},"source_kind":"arxiv","source_id":"2407.12679","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":"2026-07-05T08:45:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qC53sJAEOxuqgA3hcrtJa+qFIxRSMkQbvYmmEv1wwrjCZCI4IMMgecx430gaiAUvv5duBHn1Oqq6hQXK+r17DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T10:32:15.691808Z"},"content_sha256":"662bc252ee5569eb536a991a25fcdbb27ee18373563e47a360ea55215251bc6d","schema_version":"1.0","event_id":"sha256:662bc252ee5569eb536a991a25fcdbb27ee18373563e47a360ea55215251bc6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HJFVP4IF47V45PYGELMSRLGFEY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:45:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xPilGml8d+wD9VmQsLNONnt19QWGQpR5152NtyrKLKumhcaTWy0oJhSzX+g4IfgeqapLr2zYTBRt5UCm+vANAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T10:32:15.692197Z"},"content_sha256":"47ea5bc6c323aa91868687500ff81c2aba6247e78906c071209a9c68548c10ea","schema_version":"1.0","event_id":"sha256:47ea5bc6c323aa91868687500ff81c2aba6247e78906c071209a9c68548c10ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HJFVP4IF47V45PYGELMSRLGFEY/bundle.json","state_url":"https://pith.science/pith/HJFVP4IF47V45PYGELMSRLGFEY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HJFVP4IF47V45PYGELMSRLGFEY/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":"2026-07-13T10:32:15Z","links":{"resolver":"https://pith.science/pith/HJFVP4IF47V45PYGELMSRLGFEY","bundle":"https://pith.science/pith/HJFVP4IF47V45PYGELMSRLGFEY/bundle.json","state":"https://pith.science/pith/HJFVP4IF47V45PYGELMSRLGFEY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HJFVP4IF47V45PYGELMSRLGFEY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HJFVP4IF47V45PYGELMSRLGFEY","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":"ac84a7d7209b5b581ec2be872b8e938b44c8f51001b7ce83479c25be4f7be965","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T15:59:32Z","title_canon_sha256":"f3cbecf7e194117d2880757765715c818a43b3c8209a4062eac1fa0cbc79974a"},"schema_version":"1.0","source":{"id":"2407.12679","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12679","created_at":"2026-07-05T08:45:08Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12679v1","created_at":"2026-07-05T08:45:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12679","created_at":"2026-07-05T08:45:08Z"},{"alias_kind":"pith_short_12","alias_value":"HJFVP4IF47V4","created_at":"2026-07-05T08:45:08Z"},{"alias_kind":"pith_short_16","alias_value":"HJFVP4IF47V45PYG","created_at":"2026-07-05T08:45:08Z"},{"alias_kind":"pith_short_8","alias_value":"HJFVP4IF","created_at":"2026-07-05T08:45:08Z"}],"graph_snapshots":[{"event_id":"sha256:47ea5bc6c323aa91868687500ff81c2aba6247e78906c071209a9c68548c10ea","target":"graph","created_at":"2026-07-05T08:45:08Z","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/2407.12679/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Deyao Zhu, Eslam Abdelrahman, Essam Sleiman, Jian Ding, J\\\"urgen Schmidhuber, Kirolos Ataallah, Mingchen Zhuge, Mohamed Elhoseiny, Xiaoqian Shen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T15:59:32Z","title":"Goldfish: Vision-Language Understanding of Arbitrarily Long Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12679","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":"sha256:662bc252ee5569eb536a991a25fcdbb27ee18373563e47a360ea55215251bc6d","target":"record","created_at":"2026-07-05T08:45:08Z","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":"ac84a7d7209b5b581ec2be872b8e938b44c8f51001b7ce83479c25be4f7be965","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T15:59:32Z","title_canon_sha256":"f3cbecf7e194117d2880757765715c818a43b3c8209a4062eac1fa0cbc79974a"},"schema_version":"1.0","source":{"id":"2407.12679","kind":"arxiv","version":1}},"canonical_sha256":"3a4b57f105e7ebcebf0622d928acc526205d42382a0f12c86be8ca4edcfa400c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a4b57f105e7ebcebf0622d928acc526205d42382a0f12c86be8ca4edcfa400c","first_computed_at":"2026-07-05T08:45:08.297102Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:08.297102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"av7T8wsX2L8+qu/H+kXeprfXckQfGUWh0rw+YtGgOwYD9XMa8XzffpFKxnz57EDAXY3Zuw333JWJ0kyFbbHgBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:08.297687Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12679","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:662bc252ee5569eb536a991a25fcdbb27ee18373563e47a360ea55215251bc6d","sha256:47ea5bc6c323aa91868687500ff81c2aba6247e78906c071209a9c68548c10ea"],"state_sha256":"305856e106eb1014fd58a7d7211a20a0a164bfe1645e4be3d98902eca7d60567"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QGrDq1sX+ezMFe/IngnxMMiuPD3FvRdQB/vIIEqYbie4wotH6xAFusxKNNNnekVm9t9ERkl+j7r+mqwSeiXCCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T10:32:15.694719Z","bundle_sha256":"e8051342472d837deff84692b0aaae3e8e712a0e4722df4e1ea415456838cbea"}}