{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M757D4R273AEYWSVPYH2YFQEMD","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":"b73b71a3121652d86ca9dc0f47fe141cb49b4729f1eb9217eda4a9a8831bec33","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T13:30:51Z","title_canon_sha256":"b82906534617cd8450de967bbdaee3633e71c43bc4fe1c1245478d1099a44ee8"},"schema_version":"1.0","source":{"id":"2403.00522","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00522","created_at":"2026-07-05T08:41:00Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00522v2","created_at":"2026-07-05T08:41:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00522","created_at":"2026-07-05T08:41:00Z"},{"alias_kind":"pith_short_12","alias_value":"M757D4R273AE","created_at":"2026-07-05T08:41:00Z"},{"alias_kind":"pith_short_16","alias_value":"M757D4R273AEYWSV","created_at":"2026-07-05T08:41:00Z"},{"alias_kind":"pith_short_8","alias_value":"M757D4R2","created_at":"2026-07-05T08:41:00Z"}],"graph_snapshots":[{"event_id":"sha256:27b55ca5b22a276b7531c47365c11ca8d66ec47eac607ae2c505cec18b750ee8","target":"graph","created_at":"2026-07-05T08:41:00Z","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/2403.00522/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models are built on top of a transformer-based architecture to process textual inputs. For example, the LLaMA stands out among many open-source implementations. Can the same transformer be used to process 2D images? In this paper, we answer this question by unveiling a LLaMA-like vision transformer in plain and pyramid forms, termed VisionLLaMA, which is tailored for this purpose. VisionLLaMA is a unified and generic modelling framework for solving most vision tasks. We extensively evaluate its effectiveness using typical pre-training paradigms in a good portion of downstream ta","authors_text":"Bo Zhang, Chunhua Shen, Jianlin Su, Xiangxiang Chu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T13:30:51Z","title":"VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00522","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:c655dc0abc2b44709a7f0f97da396e055cda35bae5b5750f23542d8aea53dc60","target":"record","created_at":"2026-07-05T08:41:00Z","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":"b73b71a3121652d86ca9dc0f47fe141cb49b4729f1eb9217eda4a9a8831bec33","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T13:30:51Z","title_canon_sha256":"b82906534617cd8450de967bbdaee3633e71c43bc4fe1c1245478d1099a44ee8"},"schema_version":"1.0","source":{"id":"2403.00522","kind":"arxiv","version":2}},"canonical_sha256":"67fbf1f23afec04c5a557e0fac160460c2e3e54afbbf16e29f4a5f986985af24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67fbf1f23afec04c5a557e0fac160460c2e3e54afbbf16e29f4a5f986985af24","first_computed_at":"2026-07-05T08:41:00.197280Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:41:00.197280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jMLNRYnUtQnQaVo+1mPHSWi+VkwmARRnBzHQCfsPJXwDjRwYgvDIGg0qgK8u6Vufdlxl0URdiiP/CeZNHLQxAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:41:00.197707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.00522","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c655dc0abc2b44709a7f0f97da396e055cda35bae5b5750f23542d8aea53dc60","sha256:27b55ca5b22a276b7531c47365c11ca8d66ec47eac607ae2c505cec18b750ee8"],"state_sha256":"86c1235607de086c6188e75b113a4d49b6fb11342e8caf45a479cbb4550df040"}