{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CELOFLDBOGVGBOBYOIEHCXCBJ2","short_pith_number":"pith:CELOFLDB","canonical_record":{"source":{"id":"2406.09418","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"2f5cb84cdbc868eec653424053bfba04b44aa9d288760761f458928d3612566d","abstract_canon_sha256":"7b97242fd2cd501664d0b4ea61e8937278824f92a0bd6bb7781605d0245a74b8"},"schema_version":"1.0"},"canonical_sha256":"1116e2ac6171aa60b8387208715c414ea48b0f9c21516feda79c8f947fa6e88a","source":{"kind":"arxiv","id":"2406.09418","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09418","created_at":"2026-07-05T08:31:37Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09418v1","created_at":"2026-07-05T08:31:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09418","created_at":"2026-07-05T08:31:37Z"},{"alias_kind":"pith_short_12","alias_value":"CELOFLDBOGVG","created_at":"2026-07-05T08:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"CELOFLDBOGVGBOBY","created_at":"2026-07-05T08:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"CELOFLDB","created_at":"2026-07-05T08:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CELOFLDBOGVGBOBYOIEHCXCBJ2","target":"record","payload":{"canonical_record":{"source":{"id":"2406.09418","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"2f5cb84cdbc868eec653424053bfba04b44aa9d288760761f458928d3612566d","abstract_canon_sha256":"7b97242fd2cd501664d0b4ea61e8937278824f92a0bd6bb7781605d0245a74b8"},"schema_version":"1.0"},"canonical_sha256":"1116e2ac6171aa60b8387208715c414ea48b0f9c21516feda79c8f947fa6e88a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:37.208643Z","signature_b64":"i0o5NEJvD4t4NgDucl1lABpUq1Tu/ovLaK0umhyo+49qGcWs6ddceCkOP2tDXlIegmBwUoGb6ZpvWf7b0xIBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1116e2ac6171aa60b8387208715c414ea48b0f9c21516feda79c8f947fa6e88a","last_reissued_at":"2026-07-05T08:31:37.208154Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:37.208154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.09418","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":"2026-07-05T08:31:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sqkC5MrCOBydkMeOtbnEyfdzf/TozspbINUsGdCJEHdzWue6G92Oecg2PMUrg3ksV2gL1G2rVbxkmqAT2LzfDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:51:10.833506Z"},"content_sha256":"6c12bf9fb4ec21cc07d1c3e24521d4656758f205eb1b38ea60bddcd86306b9c1","schema_version":"1.0","event_id":"sha256:6c12bf9fb4ec21cc07d1c3e24521d4656758f205eb1b38ea60bddcd86306b9c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CELOFLDBOGVGBOBYOIEHCXCBJ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fahad Khan, Hanoona Rasheed, Muhammad Maaz, Salman Khan","submitted_at":"2024-06-13T17:59:59Z","abstract_excerpt":"Building on the advances of language models, Large Multimodal Models (LMMs) have contributed significant improvements in video understanding. While the current video LMMs utilize advanced Large Language Models (LLMs), they rely on either image or video encoders to process visual inputs, each of which has its own limitations. Image encoders excel at capturing rich spatial details from frame sequences but lack explicit temporal context, which can be important in videos with intricate action sequences. On the other hand, video encoders provide temporal context but are often limited by computation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09418","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/2406.09418/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":"2026-07-05T08:31:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x95B8KyMsTgs5tfkEZQOocXpaCxB0Jb487lOjcm38h85L0/U0bNU6zWLmlLSPQIh0hsh4GlUYCYznZsGY1DOBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:51:10.833881Z"},"content_sha256":"7f97057cebc0680a3f1014e57ef687ef0ea586cec4a98cae079bf2bf1edce9c0","schema_version":"1.0","event_id":"sha256:7f97057cebc0680a3f1014e57ef687ef0ea586cec4a98cae079bf2bf1edce9c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CELOFLDBOGVGBOBYOIEHCXCBJ2/bundle.json","state_url":"https://pith.science/pith/CELOFLDBOGVGBOBYOIEHCXCBJ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CELOFLDBOGVGBOBYOIEHCXCBJ2/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":"2026-07-06T08:51:10Z","links":{"resolver":"https://pith.science/pith/CELOFLDBOGVGBOBYOIEHCXCBJ2","bundle":"https://pith.science/pith/CELOFLDBOGVGBOBYOIEHCXCBJ2/bundle.json","state":"https://pith.science/pith/CELOFLDBOGVGBOBYOIEHCXCBJ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CELOFLDBOGVGBOBYOIEHCXCBJ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CELOFLDBOGVGBOBYOIEHCXCBJ2","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":"7b97242fd2cd501664d0b4ea61e8937278824f92a0bd6bb7781605d0245a74b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:59Z","title_canon_sha256":"2f5cb84cdbc868eec653424053bfba04b44aa9d288760761f458928d3612566d"},"schema_version":"1.0","source":{"id":"2406.09418","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09418","created_at":"2026-07-05T08:31:37Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09418v1","created_at":"2026-07-05T08:31:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09418","created_at":"2026-07-05T08:31:37Z"},{"alias_kind":"pith_short_12","alias_value":"CELOFLDBOGVG","created_at":"2026-07-05T08:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"CELOFLDBOGVGBOBY","created_at":"2026-07-05T08:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"CELOFLDB","created_at":"2026-07-05T08:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:7f97057cebc0680a3f1014e57ef687ef0ea586cec4a98cae079bf2bf1edce9c0","target":"graph","created_at":"2026-07-05T08:31:37Z","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/2406.09418/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building on the advances of language models, Large Multimodal Models (LMMs) have contributed significant improvements in video understanding. While the current video LMMs utilize advanced Large Language Models (LLMs), they rely on either image or video encoders to process visual inputs, each of which has its own limitations. Image encoders excel at capturing rich spatial details from frame sequences but lack explicit temporal context, which can be important in videos with intricate action sequences. On the other hand, video encoders provide temporal context but are often limited by computation","authors_text":"Fahad Khan, Hanoona Rasheed, Muhammad Maaz, Salman Khan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:59Z","title":"VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09418","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":"sha256:6c12bf9fb4ec21cc07d1c3e24521d4656758f205eb1b38ea60bddcd86306b9c1","target":"record","created_at":"2026-07-05T08:31:37Z","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":"7b97242fd2cd501664d0b4ea61e8937278824f92a0bd6bb7781605d0245a74b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:59Z","title_canon_sha256":"2f5cb84cdbc868eec653424053bfba04b44aa9d288760761f458928d3612566d"},"schema_version":"1.0","source":{"id":"2406.09418","kind":"arxiv","version":1}},"canonical_sha256":"1116e2ac6171aa60b8387208715c414ea48b0f9c21516feda79c8f947fa6e88a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1116e2ac6171aa60b8387208715c414ea48b0f9c21516feda79c8f947fa6e88a","first_computed_at":"2026-07-05T08:31:37.208154Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:37.208154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i0o5NEJvD4t4NgDucl1lABpUq1Tu/ovLaK0umhyo+49qGcWs6ddceCkOP2tDXlIegmBwUoGb6ZpvWf7b0xIBCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:37.208643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09418","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c12bf9fb4ec21cc07d1c3e24521d4656758f205eb1b38ea60bddcd86306b9c1","sha256:7f97057cebc0680a3f1014e57ef687ef0ea586cec4a98cae079bf2bf1edce9c0"],"state_sha256":"e2c69a1a1ba8417d3383c9a12a0c19340ec64335a4341d85a65275dc4a6993a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6WTPTiT5pF0/2++BZEuR9xqEl320mfQrhAsJQQQC6g6CIPnufupeSjyz6sI0aXOCP+WKWm+aHIf47cC/2IaiBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:51:10.835966Z","bundle_sha256":"ae674a264b681b48d9d4fcde22cee59186f576203349e306dd521108c7f1353e"}}