{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XDYU3LP7JLZ6EPLJ6AYVU44BI7","short_pith_number":"pith:XDYU3LP7","canonical_record":{"source":{"id":"2404.03413","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-04T12:46:01Z","cross_cats_sorted":[],"title_canon_sha256":"1b31a107d5f47599dfa70006f4210edadff6ec700c5cd018de04f1638d386891","abstract_canon_sha256":"224fef405f4edd4f06cd0d34f0b4b2692bdbd8632e3120a232873ece62b7e880"},"schema_version":"1.0"},"canonical_sha256":"b8f14dadff4af3e23d69f0315a738147e50170f1c741745d0d57a833978f981a","source":{"kind":"arxiv","id":"2404.03413","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.03413","created_at":"2026-07-05T08:04:25Z"},{"alias_kind":"arxiv_version","alias_value":"2404.03413v1","created_at":"2026-07-05T08:04:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03413","created_at":"2026-07-05T08:04:25Z"},{"alias_kind":"pith_short_12","alias_value":"XDYU3LP7JLZ6","created_at":"2026-07-05T08:04:25Z"},{"alias_kind":"pith_short_16","alias_value":"XDYU3LP7JLZ6EPLJ","created_at":"2026-07-05T08:04:25Z"},{"alias_kind":"pith_short_8","alias_value":"XDYU3LP7","created_at":"2026-07-05T08:04:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XDYU3LP7JLZ6EPLJ6AYVU44BI7","target":"record","payload":{"canonical_record":{"source":{"id":"2404.03413","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-04T12:46:01Z","cross_cats_sorted":[],"title_canon_sha256":"1b31a107d5f47599dfa70006f4210edadff6ec700c5cd018de04f1638d386891","abstract_canon_sha256":"224fef405f4edd4f06cd0d34f0b4b2692bdbd8632e3120a232873ece62b7e880"},"schema_version":"1.0"},"canonical_sha256":"b8f14dadff4af3e23d69f0315a738147e50170f1c741745d0d57a833978f981a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:25.463120Z","signature_b64":"uGgvgxp8e7d+HBzVeWDODNUsdmEqKpm5y4DiccUOleKbVC7bDPpCVv6ShiFTgJr6/596Bb9YVqG2fFoohLX6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8f14dadff4af3e23d69f0315a738147e50170f1c741745d0d57a833978f981a","last_reissued_at":"2026-07-05T08:04:25.462668Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:25.462668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.03413","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":"2026-07-05T08:04:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gRK8YJ9vpZMDJnbWQ1QgGEf4912z9iTfRbXDioSMapTGhfr46Zw/tHaG5cnNHnC75uRYUdiCHk8Za5QdnVlIDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:29:12.850400Z"},"content_sha256":"3e98c93ad6c117dda5e62af038031d0e48f59a598f35eae90c26e2cdac13b4c6","schema_version":"1.0","event_id":"sha256:3e98c93ad6c117dda5e62af038031d0e48f59a598f35eae90c26e2cdac13b4c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XDYU3LP7JLZ6EPLJ6AYVU44BI7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens","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, Kirolos Ataallah, Mohamed Elhoseiny, Xiaoqian Shen","submitted_at":"2024-04-04T12:46:01Z","abstract_excerpt":"This paper introduces MiniGPT4-Video, a multimodal Large Language Model (LLM) designed specifically for video understanding. The model is capable of processing both temporal visual and textual data, making it adept at understanding the complexities of videos. Building upon the success of MiniGPT-v2, which excelled in translating visual features into the LLM space for single images and achieved impressive results on various image-text benchmarks, this paper extends the model's capabilities to process a sequence of frames, enabling it to comprehend videos. MiniGPT4-video does not only consider v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03413","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/2404.03413/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":"2026-07-05T08:04:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9sB8XBh55y2m4SQ4lJM9+K3Jo/Z+iUPQFYrPVE0/QaW03M2lAyuwRnLdxnHr7NLa0gG1VKQLe91hn1i5GeYUDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:29:12.851107Z"},"content_sha256":"12f02f4da07ca70dd8c1839f07633ebc7c2fad327e82278e02771726813ccf0c","schema_version":"1.0","event_id":"sha256:12f02f4da07ca70dd8c1839f07633ebc7c2fad327e82278e02771726813ccf0c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XDYU3LP7JLZ6EPLJ6AYVU44BI7/bundle.json","state_url":"https://pith.science/pith/XDYU3LP7JLZ6EPLJ6AYVU44BI7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XDYU3LP7JLZ6EPLJ6AYVU44BI7/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":"2026-08-03T17:29:12Z","links":{"resolver":"https://pith.science/pith/XDYU3LP7JLZ6EPLJ6AYVU44BI7","bundle":"https://pith.science/pith/XDYU3LP7JLZ6EPLJ6AYVU44BI7/bundle.json","state":"https://pith.science/pith/XDYU3LP7JLZ6EPLJ6AYVU44BI7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XDYU3LP7JLZ6EPLJ6AYVU44BI7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XDYU3LP7JLZ6EPLJ6AYVU44BI7","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":"224fef405f4edd4f06cd0d34f0b4b2692bdbd8632e3120a232873ece62b7e880","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-04T12:46:01Z","title_canon_sha256":"1b31a107d5f47599dfa70006f4210edadff6ec700c5cd018de04f1638d386891"},"schema_version":"1.0","source":{"id":"2404.03413","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.03413","created_at":"2026-07-05T08:04:25Z"},{"alias_kind":"arxiv_version","alias_value":"2404.03413v1","created_at":"2026-07-05T08:04:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03413","created_at":"2026-07-05T08:04:25Z"},{"alias_kind":"pith_short_12","alias_value":"XDYU3LP7JLZ6","created_at":"2026-07-05T08:04:25Z"},{"alias_kind":"pith_short_16","alias_value":"XDYU3LP7JLZ6EPLJ","created_at":"2026-07-05T08:04:25Z"},{"alias_kind":"pith_short_8","alias_value":"XDYU3LP7","created_at":"2026-07-05T08:04:25Z"}],"graph_snapshots":[{"event_id":"sha256:12f02f4da07ca70dd8c1839f07633ebc7c2fad327e82278e02771726813ccf0c","target":"graph","created_at":"2026-07-05T08:04:25Z","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/2404.03413/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces MiniGPT4-Video, a multimodal Large Language Model (LLM) designed specifically for video understanding. The model is capable of processing both temporal visual and textual data, making it adept at understanding the complexities of videos. Building upon the success of MiniGPT-v2, which excelled in translating visual features into the LLM space for single images and achieved impressive results on various image-text benchmarks, this paper extends the model's capabilities to process a sequence of frames, enabling it to comprehend videos. MiniGPT4-video does not only consider v","authors_text":"Deyao Zhu, Eslam Abdelrahman, Essam Sleiman, Jian Ding, Kirolos Ataallah, Mohamed Elhoseiny, Xiaoqian Shen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-04T12:46:01Z","title":"MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03413","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":"sha256:3e98c93ad6c117dda5e62af038031d0e48f59a598f35eae90c26e2cdac13b4c6","target":"record","created_at":"2026-07-05T08:04:25Z","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":"224fef405f4edd4f06cd0d34f0b4b2692bdbd8632e3120a232873ece62b7e880","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-04T12:46:01Z","title_canon_sha256":"1b31a107d5f47599dfa70006f4210edadff6ec700c5cd018de04f1638d386891"},"schema_version":"1.0","source":{"id":"2404.03413","kind":"arxiv","version":1}},"canonical_sha256":"b8f14dadff4af3e23d69f0315a738147e50170f1c741745d0d57a833978f981a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8f14dadff4af3e23d69f0315a738147e50170f1c741745d0d57a833978f981a","first_computed_at":"2026-07-05T08:04:25.462668Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:04:25.462668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uGgvgxp8e7d+HBzVeWDODNUsdmEqKpm5y4DiccUOleKbVC7bDPpCVv6ShiFTgJr6/596Bb9YVqG2fFoohLX6BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:04:25.463120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.03413","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e98c93ad6c117dda5e62af038031d0e48f59a598f35eae90c26e2cdac13b4c6","sha256:12f02f4da07ca70dd8c1839f07633ebc7c2fad327e82278e02771726813ccf0c"],"state_sha256":"c442fed17403aa502d1aa62232ad0b72257363b3ae2667215785cfa33e986e9c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x0h+SnZTSs4rJUlzc9fhL55imVuxr1Cy6rp5FhDaeA4WO0fNAkA2OycuBKlGgw5U9copJK1KThbQoarjRRLQAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:29:12.856371Z","bundle_sha256":"0bfbe5aba2f7003fe87f7b698ad950e1ef4945e0ed3338829eecfa1057851d89"}}