{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:26TC7SLMNH23LAZUKTXGWZAYTL","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":"c83148b9082f21073cec0eb41d48aa98fc2f23f4b9a32b6c73b51f21e8c83579","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:59:34Z","title_canon_sha256":"8a54a3910ffc3174da4ffc9cc790250c4faa93f9e5f8beff7ce2f080b9f6b4a1"},"schema_version":"1.0","source":{"id":"2406.04334","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04334","created_at":"2026-07-05T08:28:29Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04334v1","created_at":"2026-07-05T08:28:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04334","created_at":"2026-07-05T08:28:29Z"},{"alias_kind":"pith_short_12","alias_value":"26TC7SLMNH23","created_at":"2026-07-05T08:28:29Z"},{"alias_kind":"pith_short_16","alias_value":"26TC7SLMNH23LAZU","created_at":"2026-07-05T08:28:29Z"},{"alias_kind":"pith_short_8","alias_value":"26TC7SLM","created_at":"2026-07-05T08:28:29Z"}],"graph_snapshots":[{"event_id":"sha256:7fe9038fc1d3621fc4354518c1aeb5c0d18d4a446db4a9b093c8ba1d5b90a2e4","target":"graph","created_at":"2026-07-05T08:28:29Z","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/2406.04334/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most large multimodal models (LMMs) are implemented by feeding visual tokens as a sequence into the first layer of a large language model (LLM). The resulting architecture is simple but significantly increases computation and memory costs, as it has to handle a large number of additional tokens in its input layer. This paper presents a new architecture DeepStack for LMMs. Considering $N$ layers in the language and vision transformer of LMMs, we stack the visual tokens into $N$ groups and feed each group to its aligned transformer layer \\textit{from bottom to top}. Surprisingly, this simple met","authors_text":"Jianfeng Gao, Jianwei Yang, Lingchen Meng, Rui Tian, Xiyang Dai, Yu-Gang Jiang, Zuxuan Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:59:34Z","title":"DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04334","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:e75c5dfc3e95aa6d735c193409f45793534aa62f4322c65e222661e2d1384853","target":"record","created_at":"2026-07-05T08:28:29Z","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":"c83148b9082f21073cec0eb41d48aa98fc2f23f4b9a32b6c73b51f21e8c83579","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:59:34Z","title_canon_sha256":"8a54a3910ffc3174da4ffc9cc790250c4faa93f9e5f8beff7ce2f080b9f6b4a1"},"schema_version":"1.0","source":{"id":"2406.04334","kind":"arxiv","version":1}},"canonical_sha256":"d7a62fc96c69f5b5833454ee6b64189ada02a46b3dfc36eca19d692bbc6ef717","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7a62fc96c69f5b5833454ee6b64189ada02a46b3dfc36eca19d692bbc6ef717","first_computed_at":"2026-07-05T08:28:29.564334Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:29.564334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qs5lJ6omm0rlROdg5jvt28MX86PFiD6sFDw6yBSSqe225CtDwqV7CIkLFh/ekcZq5Q/r5yjI+UxtN6VpotYmAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:29.564813Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04334","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e75c5dfc3e95aa6d735c193409f45793534aa62f4322c65e222661e2d1384853","sha256:7fe9038fc1d3621fc4354518c1aeb5c0d18d4a446db4a9b093c8ba1d5b90a2e4"],"state_sha256":"9d1ac4b5adf2bb065cf78724df5e96f0dac694afb44f04f5649351f89ddab6e8"}