{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FMVCTWAM7O2WDNJBZIBV5R7F47","short_pith_number":"pith:FMVCTWAM","canonical_record":{"source":{"id":"2404.11865","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T02:43:37Z","cross_cats_sorted":[],"title_canon_sha256":"0a6bd07fa31d1f3f52279fa860fd6b884af8eb5833a69e2a418ab03e013c492a","abstract_canon_sha256":"882675027f2b04bf5f234d32793140007089ad2ca2d30ec5a0fc22f84a1b1691"},"schema_version":"1.0"},"canonical_sha256":"2b2a29d80cfbb561b521ca035ec7e5e7c766ecd4dcc07a5e7a661bb8b0f2842e","source":{"kind":"arxiv","id":"2404.11865","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.11865","created_at":"2026-07-05T11:03:49Z"},{"alias_kind":"arxiv_version","alias_value":"2404.11865v2","created_at":"2026-07-05T11:03:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11865","created_at":"2026-07-05T11:03:49Z"},{"alias_kind":"pith_short_12","alias_value":"FMVCTWAM7O2W","created_at":"2026-07-05T11:03:49Z"},{"alias_kind":"pith_short_16","alias_value":"FMVCTWAM7O2WDNJB","created_at":"2026-07-05T11:03:49Z"},{"alias_kind":"pith_short_8","alias_value":"FMVCTWAM","created_at":"2026-07-05T11:03:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FMVCTWAM7O2WDNJBZIBV5R7F47","target":"record","payload":{"canonical_record":{"source":{"id":"2404.11865","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T02:43:37Z","cross_cats_sorted":[],"title_canon_sha256":"0a6bd07fa31d1f3f52279fa860fd6b884af8eb5833a69e2a418ab03e013c492a","abstract_canon_sha256":"882675027f2b04bf5f234d32793140007089ad2ca2d30ec5a0fc22f84a1b1691"},"schema_version":"1.0"},"canonical_sha256":"2b2a29d80cfbb561b521ca035ec7e5e7c766ecd4dcc07a5e7a661bb8b0f2842e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:49.705892Z","signature_b64":"/XbxYScCtgibJkNV8Ld5zjoBg7DXDJ4qmuUwY+//4fPcrAZv1+jYQdl8i1owciePk/EestcOEvCmFbD/E4DtCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b2a29d80cfbb561b521ca035ec7e5e7c766ecd4dcc07a5e7a661bb8b0f2842e","last_reissued_at":"2026-07-05T11:03:49.705464Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:49.705464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.11865","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:03:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"45lbTo6rC72CN1++vcER/LYd1c2eQ+9urLX/RfVNIAT4TtbbcbessVGaQXIn0f2tZ4zjvJed4LvFtSdcTswOCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:06:45.958759Z"},"content_sha256":"02559de3617d98f75540e7dab4cf436f6b9d37f8c1fc362feca849dfaafc4c62","schema_version":"1.0","event_id":"sha256:02559de3617d98f75540e7dab4cf436f6b9d37f8c1fc362feca849dfaafc4c62"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FMVCTWAM7O2WDNJBZIBV5R7F47","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Image to Video, what do we need in multimodal LLMs?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoxin Zhang, Honggu Chen, Linqing Zhong, Suyuan Huang, Yan Gao, Yao Hu, Zengchang Qin","submitted_at":"2024-04-18T02:43:37Z","abstract_excerpt":"Covering from Image LLMs to the more complex Video LLMs, the Multimodal Large Language Models (MLLMs) have demonstrated profound capabilities in comprehending cross-modal information as numerous studies have illustrated. Previous methods delve into designing comprehensive Video LLMs through integrating video foundation models with primitive LLMs. Despite its effectiveness, such paradigm renders Video LLM's structure verbose and typically requires substantial video data for pre-training. Crucially, it neglects leveraging the foundational contributions of ready-made Image LLMs. In this paper, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11865","kind":"arxiv","version":2},"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/2404.11865/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":"2026-07-05T11:03:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vM/mvWgTbEPuLGmHTaNp9vwFFk7wo6MKosB8dmaV6GmEKVpf+85S/Nbvbh4iw17fUNbX/KCdkvUpJTm6dliJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:06:45.959255Z"},"content_sha256":"b39bb7eb1f055fe13ebf6e1550ae836caaa778f1b99f687b8b7b926ffb8d9768","schema_version":"1.0","event_id":"sha256:b39bb7eb1f055fe13ebf6e1550ae836caaa778f1b99f687b8b7b926ffb8d9768"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FMVCTWAM7O2WDNJBZIBV5R7F47/bundle.json","state_url":"https://pith.science/pith/FMVCTWAM7O2WDNJBZIBV5R7F47/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FMVCTWAM7O2WDNJBZIBV5R7F47/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":"2026-08-07T16:06:45Z","links":{"resolver":"https://pith.science/pith/FMVCTWAM7O2WDNJBZIBV5R7F47","bundle":"https://pith.science/pith/FMVCTWAM7O2WDNJBZIBV5R7F47/bundle.json","state":"https://pith.science/pith/FMVCTWAM7O2WDNJBZIBV5R7F47/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FMVCTWAM7O2WDNJBZIBV5R7F47/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FMVCTWAM7O2WDNJBZIBV5R7F47","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":"882675027f2b04bf5f234d32793140007089ad2ca2d30ec5a0fc22f84a1b1691","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T02:43:37Z","title_canon_sha256":"0a6bd07fa31d1f3f52279fa860fd6b884af8eb5833a69e2a418ab03e013c492a"},"schema_version":"1.0","source":{"id":"2404.11865","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.11865","created_at":"2026-07-05T11:03:49Z"},{"alias_kind":"arxiv_version","alias_value":"2404.11865v2","created_at":"2026-07-05T11:03:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11865","created_at":"2026-07-05T11:03:49Z"},{"alias_kind":"pith_short_12","alias_value":"FMVCTWAM7O2W","created_at":"2026-07-05T11:03:49Z"},{"alias_kind":"pith_short_16","alias_value":"FMVCTWAM7O2WDNJB","created_at":"2026-07-05T11:03:49Z"},{"alias_kind":"pith_short_8","alias_value":"FMVCTWAM","created_at":"2026-07-05T11:03:49Z"}],"graph_snapshots":[{"event_id":"sha256:b39bb7eb1f055fe13ebf6e1550ae836caaa778f1b99f687b8b7b926ffb8d9768","target":"graph","created_at":"2026-07-05T11:03:49Z","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/2404.11865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Covering from Image LLMs to the more complex Video LLMs, the Multimodal Large Language Models (MLLMs) have demonstrated profound capabilities in comprehending cross-modal information as numerous studies have illustrated. Previous methods delve into designing comprehensive Video LLMs through integrating video foundation models with primitive LLMs. Despite its effectiveness, such paradigm renders Video LLM's structure verbose and typically requires substantial video data for pre-training. Crucially, it neglects leveraging the foundational contributions of ready-made Image LLMs. In this paper, we","authors_text":"Haoxin Zhang, Honggu Chen, Linqing Zhong, Suyuan Huang, Yan Gao, Yao Hu, Zengchang Qin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T02:43:37Z","title":"From Image to Video, what do we need in multimodal LLMs?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11865","kind":"arxiv","version":2},"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":"sha256:02559de3617d98f75540e7dab4cf436f6b9d37f8c1fc362feca849dfaafc4c62","target":"record","created_at":"2026-07-05T11:03:49Z","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":"882675027f2b04bf5f234d32793140007089ad2ca2d30ec5a0fc22f84a1b1691","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T02:43:37Z","title_canon_sha256":"0a6bd07fa31d1f3f52279fa860fd6b884af8eb5833a69e2a418ab03e013c492a"},"schema_version":"1.0","source":{"id":"2404.11865","kind":"arxiv","version":2}},"canonical_sha256":"2b2a29d80cfbb561b521ca035ec7e5e7c766ecd4dcc07a5e7a661bb8b0f2842e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b2a29d80cfbb561b521ca035ec7e5e7c766ecd4dcc07a5e7a661bb8b0f2842e","first_computed_at":"2026-07-05T11:03:49.705464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:49.705464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/XbxYScCtgibJkNV8Ld5zjoBg7DXDJ4qmuUwY+//4fPcrAZv1+jYQdl8i1owciePk/EestcOEvCmFbD/E4DtCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:49.705892Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.11865","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02559de3617d98f75540e7dab4cf436f6b9d37f8c1fc362feca849dfaafc4c62","sha256:b39bb7eb1f055fe13ebf6e1550ae836caaa778f1b99f687b8b7b926ffb8d9768"],"state_sha256":"51b124c7365f010a2c46f200ac22555f19af4739a49c373465b1186ab18dc556"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q57t7R+tgKMYi/g68ydCELwoEpqy28VRdde/GEyVmesj7PRF4hpiDHO1oNIQfNjM9BQMqxMEz8g1ZnvVOjm4Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:06:45.988032Z","bundle_sha256":"91d7f62b6bb66b8eb7f9f3cb804d0851b45528bfe595d9b31a7622816ee10f3a"}}