{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:INYRK5U66U2NYQOUBJVMSLAFTX","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":"e7f062b7ab18c6dd8eae9d89755175c32e48e488de11afebe6a61070caab9963","cross_cats_sorted":["cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T17:04:42Z","title_canon_sha256":"da5c277768807f719a47cc19c1c87c518ad1ad93c9fb1f0b72ebd0781ad36513"},"schema_version":"1.0","source":{"id":"2412.05185","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05185","created_at":"2026-07-05T09:47:37Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05185v2","created_at":"2026-07-05T09:47:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05185","created_at":"2026-07-05T09:47:37Z"},{"alias_kind":"pith_short_12","alias_value":"INYRK5U66U2N","created_at":"2026-07-05T09:47:37Z"},{"alias_kind":"pith_short_16","alias_value":"INYRK5U66U2NYQOU","created_at":"2026-07-05T09:47:37Z"},{"alias_kind":"pith_short_8","alias_value":"INYRK5U6","created_at":"2026-07-05T09:47:37Z"}],"graph_snapshots":[{"event_id":"sha256:912695fb14533e1f9965b3fc340b2df1ec72df45d783941848f1b167a37bdc44","target":"graph","created_at":"2026-07-05T09:47:37Z","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/2412.05185/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have been widely used in various tasks, motivating us to develop an LLM-based assistant for videos. Instead of training from scratch, we propose a module to transform arbitrary well-trained image-based LLMs into video-LLMs (after being trained on video data). To better adapt image-LLMs for processing videos, we introduce two design principles: linear transformation to preserve the original visual-language alignment and representative information condensation from redundant video content. Guided by these principles, we propose a plug-and-play Linear Video Tokenizer(","authors_text":"Dengjie Li, Haoxian Tan, Lishuai Gao, Yingsen Zeng, Yujie Zhong, Zheng Zhao","cross_cats":["cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T17:04:42Z","title":"LinVT: Empower Your Image-level Large Language Model to Understand Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05185","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":"sha256:376b4a578f493fc5efa9c599d5eb6e412f8030c20684190347afb9113ade36a5","target":"record","created_at":"2026-07-05T09:47:37Z","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":"e7f062b7ab18c6dd8eae9d89755175c32e48e488de11afebe6a61070caab9963","cross_cats_sorted":["cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T17:04:42Z","title_canon_sha256":"da5c277768807f719a47cc19c1c87c518ad1ad93c9fb1f0b72ebd0781ad36513"},"schema_version":"1.0","source":{"id":"2412.05185","kind":"arxiv","version":2}},"canonical_sha256":"437115769ef534dc41d40a6ac92c059ddc3f20f7157f144b00b8078d30100e02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"437115769ef534dc41d40a6ac92c059ddc3f20f7157f144b00b8078d30100e02","first_computed_at":"2026-07-05T09:47:37.579506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:37.579506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k0V4ZhReY5cfks8AA400Vy7IbNQEk8xDskS0PIPWnEsGBop+SKtL+nlPHqfpCEuGLLxkpqjVlU9sEac9A8e6Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:37.579988Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.05185","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:376b4a578f493fc5efa9c599d5eb6e412f8030c20684190347afb9113ade36a5","sha256:912695fb14533e1f9965b3fc340b2df1ec72df45d783941848f1b167a37bdc44"],"state_sha256":"69ac17201970eca59c90ef0530e65f68db4e10a51285df3122aea7575917868f"}