{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VZGF4A2KGHJ64A2QZJTJY3MFZD","short_pith_number":"pith:VZGF4A2K","canonical_record":{"source":{"id":"2409.03206","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-05T02:54:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a4371f26ddf38055ab9d1365d7f56ee604106764cb8f8dfbd93809ededce2bc4","abstract_canon_sha256":"2a179eca22b3e45a7f61e2032fb59e9de3860ab4d7d749ef2dd1c420c49b1663"},"schema_version":"1.0"},"canonical_sha256":"ae4c5e034a31d3ee0350ca669c6d85c8e76dcbf2adf30c64b3ab3d237249d13e","source":{"kind":"arxiv","id":"2409.03206","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.03206","created_at":"2026-07-05T09:03:27Z"},{"alias_kind":"arxiv_version","alias_value":"2409.03206v1","created_at":"2026-07-05T09:03:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03206","created_at":"2026-07-05T09:03:27Z"},{"alias_kind":"pith_short_12","alias_value":"VZGF4A2KGHJ6","created_at":"2026-07-05T09:03:27Z"},{"alias_kind":"pith_short_16","alias_value":"VZGF4A2KGHJ64A2Q","created_at":"2026-07-05T09:03:27Z"},{"alias_kind":"pith_short_8","alias_value":"VZGF4A2K","created_at":"2026-07-05T09:03:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VZGF4A2KGHJ64A2QZJTJY3MFZD","target":"record","payload":{"canonical_record":{"source":{"id":"2409.03206","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-05T02:54:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a4371f26ddf38055ab9d1365d7f56ee604106764cb8f8dfbd93809ededce2bc4","abstract_canon_sha256":"2a179eca22b3e45a7f61e2032fb59e9de3860ab4d7d749ef2dd1c420c49b1663"},"schema_version":"1.0"},"canonical_sha256":"ae4c5e034a31d3ee0350ca669c6d85c8e76dcbf2adf30c64b3ab3d237249d13e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:27.564015Z","signature_b64":"xZpW5Wusy2qNr10Cw9m2NJAI7pxCG6Rhd7pM2YqgklnCS5+xLuJ09qBvNxJozEeYo1YJjSzBf/vQQvgosYZhDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae4c5e034a31d3ee0350ca669c6d85c8e76dcbf2adf30c64b3ab3d237249d13e","last_reissued_at":"2026-07-05T09:03:27.563587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:27.563587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.03206","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":"2026-07-05T09:03:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gGL48ddXNMKmlKt9rUQmKKegGDJgD3h7T4HAacrJ5UyLO1ffXu5/xfcG16a+nvcSp2EN/iwxQ8X49G+vP0U1Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:15:01.305285Z"},"content_sha256":"9dc191f0264decdff84826ccf97921bb25dcedbf15d9246bf04a2c094c797622","schema_version":"1.0","event_id":"sha256:9dc191f0264decdff84826ccf97921bb25dcedbf15d9246bf04a2c094c797622"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VZGF4A2KGHJ64A2QZJTJY3MFZD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TC-LLaVA: Rethinking the Transfer from Image to Video Understanding with Temporal Considerations","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Zhao, Hui Xiong, Jiangtao Xie, Jingyu Liu, Mingda Li, Mingze Gao, Qingbin Liu, Xi Chen","submitted_at":"2024-09-05T02:54:17Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have significantly improved performance across various image-language applications. Recently, there has been a growing interest in adapting image pre-trained MLLMs for video-related tasks. However, most efforts concentrate on enhancing the vision encoder and projector components, while the core part, Large Language Models (LLMs), remains comparatively under-explored. In this paper, we propose two strategies to enhance the model's capability in video understanding tasks by improving inter-layer attention computation in LLMs. Specifically, the first appro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03206","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/2409.03206/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":"2026-07-05T09:03:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A8UUe4NX/K7q+DlrxFaZ0amjOqhh9jSWpNbkxe5BPN8+BHc/LZj0iqMajMD29hxFoKzHbdMHZjpWC2c/XMyRBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:15:01.305845Z"},"content_sha256":"798a724439681e22195499fe9e40350b8d3d70b237989be7e2d24f14c8259551","schema_version":"1.0","event_id":"sha256:798a724439681e22195499fe9e40350b8d3d70b237989be7e2d24f14c8259551"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VZGF4A2KGHJ64A2QZJTJY3MFZD/bundle.json","state_url":"https://pith.science/pith/VZGF4A2KGHJ64A2QZJTJY3MFZD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VZGF4A2KGHJ64A2QZJTJY3MFZD/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":"2026-08-10T05:15:01Z","links":{"resolver":"https://pith.science/pith/VZGF4A2KGHJ64A2QZJTJY3MFZD","bundle":"https://pith.science/pith/VZGF4A2KGHJ64A2QZJTJY3MFZD/bundle.json","state":"https://pith.science/pith/VZGF4A2KGHJ64A2QZJTJY3MFZD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VZGF4A2KGHJ64A2QZJTJY3MFZD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VZGF4A2KGHJ64A2QZJTJY3MFZD","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":"2a179eca22b3e45a7f61e2032fb59e9de3860ab4d7d749ef2dd1c420c49b1663","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-05T02:54:17Z","title_canon_sha256":"a4371f26ddf38055ab9d1365d7f56ee604106764cb8f8dfbd93809ededce2bc4"},"schema_version":"1.0","source":{"id":"2409.03206","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.03206","created_at":"2026-07-05T09:03:27Z"},{"alias_kind":"arxiv_version","alias_value":"2409.03206v1","created_at":"2026-07-05T09:03:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03206","created_at":"2026-07-05T09:03:27Z"},{"alias_kind":"pith_short_12","alias_value":"VZGF4A2KGHJ6","created_at":"2026-07-05T09:03:27Z"},{"alias_kind":"pith_short_16","alias_value":"VZGF4A2KGHJ64A2Q","created_at":"2026-07-05T09:03:27Z"},{"alias_kind":"pith_short_8","alias_value":"VZGF4A2K","created_at":"2026-07-05T09:03:27Z"}],"graph_snapshots":[{"event_id":"sha256:798a724439681e22195499fe9e40350b8d3d70b237989be7e2d24f14c8259551","target":"graph","created_at":"2026-07-05T09:03:27Z","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/2409.03206/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have significantly improved performance across various image-language applications. Recently, there has been a growing interest in adapting image pre-trained MLLMs for video-related tasks. However, most efforts concentrate on enhancing the vision encoder and projector components, while the core part, Large Language Models (LLMs), remains comparatively under-explored. In this paper, we propose two strategies to enhance the model's capability in video understanding tasks by improving inter-layer attention computation in LLMs. Specifically, the first appro","authors_text":"Bo Zhao, Hui Xiong, Jiangtao Xie, Jingyu Liu, Mingda Li, Mingze Gao, Qingbin Liu, Xi Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-05T02:54:17Z","title":"TC-LLaVA: Rethinking the Transfer from Image to Video Understanding with Temporal Considerations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03206","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":"sha256:9dc191f0264decdff84826ccf97921bb25dcedbf15d9246bf04a2c094c797622","target":"record","created_at":"2026-07-05T09:03:27Z","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":"2a179eca22b3e45a7f61e2032fb59e9de3860ab4d7d749ef2dd1c420c49b1663","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-05T02:54:17Z","title_canon_sha256":"a4371f26ddf38055ab9d1365d7f56ee604106764cb8f8dfbd93809ededce2bc4"},"schema_version":"1.0","source":{"id":"2409.03206","kind":"arxiv","version":1}},"canonical_sha256":"ae4c5e034a31d3ee0350ca669c6d85c8e76dcbf2adf30c64b3ab3d237249d13e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae4c5e034a31d3ee0350ca669c6d85c8e76dcbf2adf30c64b3ab3d237249d13e","first_computed_at":"2026-07-05T09:03:27.563587Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:03:27.563587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xZpW5Wusy2qNr10Cw9m2NJAI7pxCG6Rhd7pM2YqgklnCS5+xLuJ09qBvNxJozEeYo1YJjSzBf/vQQvgosYZhDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:03:27.564015Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.03206","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9dc191f0264decdff84826ccf97921bb25dcedbf15d9246bf04a2c094c797622","sha256:798a724439681e22195499fe9e40350b8d3d70b237989be7e2d24f14c8259551"],"state_sha256":"80999627d62ef63b79b74cce51b5a2158f590e3d4e2f112b0b0fc02b78061998"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o8vOKUtDsHTbQP//Tp9TGWDlSaY7VUW8P8yhw3tPTnNbm9Lb+ZdBx1FVsAHjEq9iEsQY9hXcRl4XVYbhsPeXDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T05:15:01.311033Z","bundle_sha256":"8dc90e601b6a1fc311a5da4f8ae3cb0ac31c91c32ae5b75c6f8d93e79e5be7e2"}}