{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M757D4R273AEYWSVPYH2YFQEMD","short_pith_number":"pith:M757D4R2","schema_version":"1.0","canonical_sha256":"67fbf1f23afec04c5a557e0fac160460c2e3e54afbbf16e29f4a5f986985af24","source":{"kind":"arxiv","id":"2403.00522","version":2},"attestation_state":"computed","paper":{"title":"VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zhang, Chunhua Shen, Jianlin Su, Xiangxiang Chu","submitted_at":"2024-03-01T13:30:51Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.00522","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T13:30:51Z","cross_cats_sorted":[],"title_canon_sha256":"b82906534617cd8450de967bbdaee3633e71c43bc4fe1c1245478d1099a44ee8","abstract_canon_sha256":"b73b71a3121652d86ca9dc0f47fe141cb49b4729f1eb9217eda4a9a8831bec33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:00.197707Z","signature_b64":"jMLNRYnUtQnQaVo+1mPHSWi+VkwmARRnBzHQCfsPJXwDjRwYgvDIGg0qgK8u6Vufdlxl0URdiiP/CeZNHLQxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67fbf1f23afec04c5a557e0fac160460c2e3e54afbbf16e29f4a5f986985af24","last_reissued_at":"2026-07-05T08:41:00.197280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:00.197280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zhang, Chunhua Shen, Jianlin Su, Xiangxiang Chu","submitted_at":"2024-03-01T13:30:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00522","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.00522/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.00522","created_at":"2026-07-05T08:41:00.197339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.00522v2","created_at":"2026-07-05T08:41:00.197339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00522","created_at":"2026-07-05T08:41:00.197339+00:00"},{"alias_kind":"pith_short_12","alias_value":"M757D4R273AE","created_at":"2026-07-05T08:41:00.197339+00:00"},{"alias_kind":"pith_short_16","alias_value":"M757D4R273AEYWSV","created_at":"2026-07-05T08:41:00.197339+00:00"},{"alias_kind":"pith_short_8","alias_value":"M757D4R2","created_at":"2026-07-05T08:41:00.197339+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.23268","citing_title":"PixNerd: Pixel Neural Field Diffusion","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M757D4R273AEYWSVPYH2YFQEMD","json":"https://pith.science/pith/M757D4R273AEYWSVPYH2YFQEMD.json","graph_json":"https://pith.science/api/pith-number/M757D4R273AEYWSVPYH2YFQEMD/graph.json","events_json":"https://pith.science/api/pith-number/M757D4R273AEYWSVPYH2YFQEMD/events.json","paper":"https://pith.science/paper/M757D4R2"},"agent_actions":{"view_html":"https://pith.science/pith/M757D4R273AEYWSVPYH2YFQEMD","download_json":"https://pith.science/pith/M757D4R273AEYWSVPYH2YFQEMD.json","view_paper":"https://pith.science/paper/M757D4R2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.00522&json=true","fetch_graph":"https://pith.science/api/pith-number/M757D4R273AEYWSVPYH2YFQEMD/graph.json","fetch_events":"https://pith.science/api/pith-number/M757D4R273AEYWSVPYH2YFQEMD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M757D4R273AEYWSVPYH2YFQEMD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M757D4R273AEYWSVPYH2YFQEMD/action/storage_attestation","attest_author":"https://pith.science/pith/M757D4R273AEYWSVPYH2YFQEMD/action/author_attestation","sign_citation":"https://pith.science/pith/M757D4R273AEYWSVPYH2YFQEMD/action/citation_signature","submit_replication":"https://pith.science/pith/M757D4R273AEYWSVPYH2YFQEMD/action/replication_record"}},"created_at":"2026-07-05T08:41:00.197339+00:00","updated_at":"2026-07-05T08:41:00.197339+00:00"}