{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UNLEZZ4ZTFR7MBF4FNAJO7VUJ2","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":"563e223c5d310e2d485b50e8f72174f895c6de21bd921798ea661c365a107f66","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T07:13:40Z","title_canon_sha256":"6fe6ecbd4a55e82a9f26a7be78955d2c1e8aaee0cee0b5e2259833e4097326dc"},"schema_version":"1.0","source":{"id":"2412.09919","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09919","created_at":"2026-07-05T11:52:00Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09919v2","created_at":"2026-07-05T11:52:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09919","created_at":"2026-07-05T11:52:00Z"},{"alias_kind":"pith_short_12","alias_value":"UNLEZZ4ZTFR7","created_at":"2026-07-05T11:52:00Z"},{"alias_kind":"pith_short_16","alias_value":"UNLEZZ4ZTFR7MBF4","created_at":"2026-07-05T11:52:00Z"},{"alias_kind":"pith_short_8","alias_value":"UNLEZZ4Z","created_at":"2026-07-05T11:52:00Z"}],"graph_snapshots":[{"event_id":"sha256:3e859865a16b13bc99754f5dfc1c5af2bd79bb82cc57be50716b16461b30f1fc","target":"graph","created_at":"2026-07-05T11:52:00Z","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/2412.09919/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, Vision Large Language Models (VLLMs) integrated with vision encoders have shown promising performance in vision understanding. The key of VLLMs is to encode visual content into sequences of visual tokens, enabling VLLMs to simultaneously process both visual and textual content. However, understanding videos, especially long videos, remain a challenge to VLLMs as the number of visual tokens grows rapidly when encoding videos, resulting in the risk of exceeding the context window of VLLMs and introducing heavy computation burden. To restrict the number of visual tokens, existing VLLMs ","authors_text":"Kun Hu, Mengwei He, Zhenfei Yin, Zhihui Wang, Zhiyong Wang, Zhuqiang Lu, Zicheng Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T07:13:40Z","title":"B-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09919","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":"sha256:3c0a36c03ae9f90e75172568e48bd99cc81ad1bc5fbb49a661aef1464158c16e","target":"record","created_at":"2026-07-05T11:52:00Z","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":"563e223c5d310e2d485b50e8f72174f895c6de21bd921798ea661c365a107f66","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T07:13:40Z","title_canon_sha256":"6fe6ecbd4a55e82a9f26a7be78955d2c1e8aaee0cee0b5e2259833e4097326dc"},"schema_version":"1.0","source":{"id":"2412.09919","kind":"arxiv","version":2}},"canonical_sha256":"a3564ce7999963f604bc2b40977eb44e85577857495c25767ce7e6269a4065e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3564ce7999963f604bc2b40977eb44e85577857495c25767ce7e6269a4065e6","first_computed_at":"2026-07-05T11:52:00.957290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:00.957290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fDy94jxzZJVCBiwUq0gfyBuhRcRPaTxiTAjPU02Tk2p0kTS87yO3uY9j+p1AbRzsWduCvBqBh2+2KHAxe7ZADg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:00.957771Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09919","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c0a36c03ae9f90e75172568e48bd99cc81ad1bc5fbb49a661aef1464158c16e","sha256:3e859865a16b13bc99754f5dfc1c5af2bd79bb82cc57be50716b16461b30f1fc"],"state_sha256":"34a387d8859e7d6fa1e5c073b2a48f6b8293d4f5745d98b5e5c732a81d9813b9"}