{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q6GKIIRK33HP3W2E7B2CJFVKFM","short_pith_number":"pith:Q6GKIIRK","canonical_record":{"source":{"id":"2404.06773","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-10T06:30:08Z","cross_cats_sorted":[],"title_canon_sha256":"8d536ec5417308ebebc2e36df5ffa9323ec2b70e219c52ebf59490ffe2d4afef","abstract_canon_sha256":"519203fc6107043f49b454c683cbc61988d3d84623f4cfe3f4abc892d765ab4f"},"schema_version":"1.0"},"canonical_sha256":"878ca4222adecefddb44f8742496aa2b380ed481430a0da1314d10e26f79c676","source":{"kind":"arxiv","id":"2404.06773","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06773","created_at":"2026-07-05T08:23:21Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06773v4","created_at":"2026-07-05T08:23:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06773","created_at":"2026-07-05T08:23:21Z"},{"alias_kind":"pith_short_12","alias_value":"Q6GKIIRK33HP","created_at":"2026-07-05T08:23:21Z"},{"alias_kind":"pith_short_16","alias_value":"Q6GKIIRK33HP3W2E","created_at":"2026-07-05T08:23:21Z"},{"alias_kind":"pith_short_8","alias_value":"Q6GKIIRK","created_at":"2026-07-05T08:23:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q6GKIIRK33HP3W2E7B2CJFVKFM","target":"record","payload":{"canonical_record":{"source":{"id":"2404.06773","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-10T06:30:08Z","cross_cats_sorted":[],"title_canon_sha256":"8d536ec5417308ebebc2e36df5ffa9323ec2b70e219c52ebf59490ffe2d4afef","abstract_canon_sha256":"519203fc6107043f49b454c683cbc61988d3d84623f4cfe3f4abc892d765ab4f"},"schema_version":"1.0"},"canonical_sha256":"878ca4222adecefddb44f8742496aa2b380ed481430a0da1314d10e26f79c676","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:21.120117Z","signature_b64":"yNevecrHTPykzKrEGH07OcvSH3ZJdO45u25IYKXWP6SYGvzSDAzr/rtxsi63PLDea73XPEMw0SQwiTsHG/79Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"878ca4222adecefddb44f8742496aa2b380ed481430a0da1314d10e26f79c676","last_reissued_at":"2026-07-05T08:23:21.119643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:21.119643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.06773","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:23:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rcLCK5MoENNOi7I8GQ+WLjxTRxlTxvP8B+e4S5k1cQekdwHw3eSsi0IJcPxrr6Ajh8UK3wL2YvzKzHMIr05mBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:25:40.465244Z"},"content_sha256":"30f9f7df3060d8e7cdd288ee724d70acba89b855ab37d1e279f54d14048bb7f2","schema_version":"1.0","event_id":"sha256:30f9f7df3060d8e7cdd288ee724d70acba89b855ab37d1e279f54d14048bb7f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q6GKIIRK33HP3W2E7B2CJFVKFM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adapting LLaMA Decoder to Vision Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengyue Wu, Jiahao Wang, Kai Chen, Kaipeng Zhang, Mengzhao Chen, Ping Luo, Songyang Zhang, Taiqiang Wu, Wenqi Shao, Yong Liu","submitted_at":"2024-04-10T06:30:08Z","abstract_excerpt":"This work examines whether decoder-only Transformers such as LLaMA, which were originally designed for large language models (LLMs), can be adapted to the computer vision field. We first \"LLaMAfy\" a standard ViT step-by-step to align with LLaMA's architecture, and find that directly applying a causal mask to the self-attention brings an attention collapse issue, resulting in the failure to the network training. We suggest to reposition the class token behind the image tokens with a post-sequence class token technique to overcome this challenge, enabling causal self-attention to efficiently cap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06773","kind":"arxiv","version":4},"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/2404.06773/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:23:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"siCZLzoLp/a1IzG8jmk/LHRY+l2w4WKptZ59pHMAfIR0CmkNyrOtM6QXD6wdO1K9PX2Hojiqprm/rThAQ2fRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:25:40.465634Z"},"content_sha256":"833d69a0e02548871985d76aff3fa6eeb183e04dc0dd068ca02e5d99b4767678","schema_version":"1.0","event_id":"sha256:833d69a0e02548871985d76aff3fa6eeb183e04dc0dd068ca02e5d99b4767678"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q6GKIIRK33HP3W2E7B2CJFVKFM/bundle.json","state_url":"https://pith.science/pith/Q6GKIIRK33HP3W2E7B2CJFVKFM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q6GKIIRK33HP3W2E7B2CJFVKFM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T12:25:40Z","links":{"resolver":"https://pith.science/pith/Q6GKIIRK33HP3W2E7B2CJFVKFM","bundle":"https://pith.science/pith/Q6GKIIRK33HP3W2E7B2CJFVKFM/bundle.json","state":"https://pith.science/pith/Q6GKIIRK33HP3W2E7B2CJFVKFM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q6GKIIRK33HP3W2E7B2CJFVKFM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q6GKIIRK33HP3W2E7B2CJFVKFM","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":"519203fc6107043f49b454c683cbc61988d3d84623f4cfe3f4abc892d765ab4f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-10T06:30:08Z","title_canon_sha256":"8d536ec5417308ebebc2e36df5ffa9323ec2b70e219c52ebf59490ffe2d4afef"},"schema_version":"1.0","source":{"id":"2404.06773","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06773","created_at":"2026-07-05T08:23:21Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06773v4","created_at":"2026-07-05T08:23:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06773","created_at":"2026-07-05T08:23:21Z"},{"alias_kind":"pith_short_12","alias_value":"Q6GKIIRK33HP","created_at":"2026-07-05T08:23:21Z"},{"alias_kind":"pith_short_16","alias_value":"Q6GKIIRK33HP3W2E","created_at":"2026-07-05T08:23:21Z"},{"alias_kind":"pith_short_8","alias_value":"Q6GKIIRK","created_at":"2026-07-05T08:23:21Z"}],"graph_snapshots":[{"event_id":"sha256:833d69a0e02548871985d76aff3fa6eeb183e04dc0dd068ca02e5d99b4767678","target":"graph","created_at":"2026-07-05T08:23:21Z","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/2404.06773/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work examines whether decoder-only Transformers such as LLaMA, which were originally designed for large language models (LLMs), can be adapted to the computer vision field. We first \"LLaMAfy\" a standard ViT step-by-step to align with LLaMA's architecture, and find that directly applying a causal mask to the self-attention brings an attention collapse issue, resulting in the failure to the network training. We suggest to reposition the class token behind the image tokens with a post-sequence class token technique to overcome this challenge, enabling causal self-attention to efficiently cap","authors_text":"Chengyue Wu, Jiahao Wang, Kai Chen, Kaipeng Zhang, Mengzhao Chen, Ping Luo, Songyang Zhang, Taiqiang Wu, Wenqi Shao, Yong Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-10T06:30:08Z","title":"Adapting LLaMA Decoder to Vision Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06773","kind":"arxiv","version":4},"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":"sha256:30f9f7df3060d8e7cdd288ee724d70acba89b855ab37d1e279f54d14048bb7f2","target":"record","created_at":"2026-07-05T08:23:21Z","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":"519203fc6107043f49b454c683cbc61988d3d84623f4cfe3f4abc892d765ab4f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-10T06:30:08Z","title_canon_sha256":"8d536ec5417308ebebc2e36df5ffa9323ec2b70e219c52ebf59490ffe2d4afef"},"schema_version":"1.0","source":{"id":"2404.06773","kind":"arxiv","version":4}},"canonical_sha256":"878ca4222adecefddb44f8742496aa2b380ed481430a0da1314d10e26f79c676","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"878ca4222adecefddb44f8742496aa2b380ed481430a0da1314d10e26f79c676","first_computed_at":"2026-07-05T08:23:21.119643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:21.119643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yNevecrHTPykzKrEGH07OcvSH3ZJdO45u25IYKXWP6SYGvzSDAzr/rtxsi63PLDea73XPEMw0SQwiTsHG/79Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:21.120117Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.06773","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30f9f7df3060d8e7cdd288ee724d70acba89b855ab37d1e279f54d14048bb7f2","sha256:833d69a0e02548871985d76aff3fa6eeb183e04dc0dd068ca02e5d99b4767678"],"state_sha256":"e946edd3d8bb662c7d0dd052d0f27721a3befe7ee8b77e535712173ac3ccc4ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A6Ru3mXh1N21I25I+k6kmANujZjW7KUUyuNlzpOS3Ek5MMRPzWAZSxWb1DyxmTNrVaEgwWvfmNBZDO8gDra9DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:25:40.467561Z","bundle_sha256":"a580c7181e24debc4ea9cb72fb666b6da6c769aaf881629c45386e8006bd062d"}}