{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JCMH23DTKT5O4YY6DFUOJOW526","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":"6b30ac4ab06f9adfd44ecf4e630541d932dd4301e8cc2b92a9a1252fbd2a86ee","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T17:59:11Z","title_canon_sha256":"0b34f367eb156eb813dfd086ff02df3e73d28fc74ed5b0e48ac25bff9030979c"},"schema_version":"1.0","source":{"id":"2410.16267","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16267","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16267v2","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16267","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"pith_short_12","alias_value":"JCMH23DTKT5O","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"pith_short_16","alias_value":"JCMH23DTKT5O4YY6","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"pith_short_8","alias_value":"JCMH23DT","created_at":"2026-07-05T11:18:39Z"}],"graph_snapshots":[{"event_id":"sha256:db3d56eb1a3a8de197e16fe0b6c3b17b479d2861371aadeea5fd8ab44df20d1c","target":"graph","created_at":"2026-07-05T11:18:39Z","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/2410.16267/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present xGen-MM-Vid (BLIP-3-Video): a multimodal language model for videos, particularly designed to efficiently capture temporal information over multiple frames. BLIP-3-Video takes advantage of the 'temporal encoder' in addition to the conventional visual tokenizer, which maps a sequence of tokens over multiple frames into a compact set of visual tokens. This enables BLIP3-Video to use much fewer visual tokens than its competing models (e.g., 32 vs. 4608 tokens). We explore different types of temporal encoders, including learnable spatio-temporal pooling as well as sequential models like ","authors_text":"Caiming Xiong, Can Qin, Honglu Zhou, Jongwoo Park, Juan Carlos Niebles, Kanchana Ranasinghe, Le Xue, Manli Shu, Michael S. Ryoo, Ran Xu, Shrikant Kendre, Silvio Savarese","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T17:59:11Z","title":"xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16267","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":"sha256:4fd94e0e732d452d31535d7f35520588424bfb1382e1d87534e5e52a8c85a736","target":"record","created_at":"2026-07-05T11:18:39Z","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":"6b30ac4ab06f9adfd44ecf4e630541d932dd4301e8cc2b92a9a1252fbd2a86ee","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T17:59:11Z","title_canon_sha256":"0b34f367eb156eb813dfd086ff02df3e73d28fc74ed5b0e48ac25bff9030979c"},"schema_version":"1.0","source":{"id":"2410.16267","kind":"arxiv","version":2}},"canonical_sha256":"48987d6c7354faee631e1968e4baddd7a541a5ae3bdbf944febef51fa9d750ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48987d6c7354faee631e1968e4baddd7a541a5ae3bdbf944febef51fa9d750ee","first_computed_at":"2026-07-05T11:18:39.887633Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:39.887633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ba8bO++IwdHl9uc9fVuM8SP8TRA8H7FdHHl00+DwaFuuPc6ypqdrNL6qeGVr6Oe6Jfq8I9nbNhsCfgzfu+4xDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:39.888123Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16267","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fd94e0e732d452d31535d7f35520588424bfb1382e1d87534e5e52a8c85a736","sha256:db3d56eb1a3a8de197e16fe0b6c3b17b479d2861371aadeea5fd8ab44df20d1c"],"state_sha256":"edfb9d2dc8739d3ff6d1ef1d24880688225949af7c73f7e574f6769f8388db66"}