{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WOGWWQYPBRLU5Z4QZL42WDOZAB","short_pith_number":"pith:WOGWWQYP","canonical_record":{"source":{"id":"2303.17376","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-30T13:42:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4c5030ca691bf5a45059542b978c3b5d7af6871b8e23158232c31a574679c166","abstract_canon_sha256":"da846752deb7e5579bc3678e47c9287c3e4e38aa2c3a1e2249b1fdd70cfc8580"},"schema_version":"1.0"},"canonical_sha256":"b38d6b430f0c574ee790caf9ab0dd9005a03fd79578f7d757d9752d4c7125b4e","source":{"kind":"arxiv","id":"2303.17376","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.17376","created_at":"2026-07-05T05:56:33Z"},{"alias_kind":"arxiv_version","alias_value":"2303.17376v1","created_at":"2026-07-05T05:56:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17376","created_at":"2026-07-05T05:56:33Z"},{"alias_kind":"pith_short_12","alias_value":"WOGWWQYPBRLU","created_at":"2026-07-05T05:56:33Z"},{"alias_kind":"pith_short_16","alias_value":"WOGWWQYPBRLU5Z4Q","created_at":"2026-07-05T05:56:33Z"},{"alias_kind":"pith_short_8","alias_value":"WOGWWQYP","created_at":"2026-07-05T05:56:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WOGWWQYPBRLU5Z4QZL42WDOZAB","target":"record","payload":{"canonical_record":{"source":{"id":"2303.17376","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-30T13:42:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4c5030ca691bf5a45059542b978c3b5d7af6871b8e23158232c31a574679c166","abstract_canon_sha256":"da846752deb7e5579bc3678e47c9287c3e4e38aa2c3a1e2249b1fdd70cfc8580"},"schema_version":"1.0"},"canonical_sha256":"b38d6b430f0c574ee790caf9ab0dd9005a03fd79578f7d757d9752d4c7125b4e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:33.367421Z","signature_b64":"HBV0axlKzN7OdxzcGVDY0zL69yQClO8k72PmXGcYUq0AdV4oXwrAR09VVTw94OkW8+wSEkYjH4h62az8hq0WAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b38d6b430f0c574ee790caf9ab0dd9005a03fd79578f7d757d9752d4c7125b4e","last_reissued_at":"2026-07-05T05:56:33.366912Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:33.366912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.17376","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:56:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SataLJZEwm2W3+93IdUn9PtSuL1eKp3Ixchyiitb/7DvNhZyUhWKuCS9cyPlrvTeThYLR0hyBAMKu5v3GbBeAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:02:56.206487Z"},"content_sha256":"c7bf492e861dee9837a1213a64d8d2bda2a48c86a0f7eb3468d7e10668f60273","schema_version":"1.0","event_id":"sha256:c7bf492e861dee9837a1213a64d8d2bda2a48c86a0f7eb3468d7e10668f60273"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WOGWWQYPBRLU5Z4QZL42WDOZAB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Kolesnikov, Andreas Steiner, Andr\\'e Susano Pinto, Bo Wan, Emanuele Bugliarello, Filip Pavetic, Gagan Madan, Liang-Chieh Chen, Lucas Beyer, Qihang Yu, Xiaohua Zhai, Xiao Wang","submitted_at":"2023-03-30T13:42:58Z","abstract_excerpt":"There has been a recent explosion of computer vision models which perform many tasks and are composed of an image encoder (usually a ViT) and an autoregressive decoder (usually a Transformer). However, most of this work simply presents one system and its results, leaving many questions regarding design decisions and trade-offs of such systems unanswered. In this work, we aim to provide such answers. We take a close look at autoregressive decoders for multi-task learning in multimodal computer vision, including classification, captioning, visual question answering, and optical character recogni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17376","kind":"arxiv","version":1},"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/2303.17376/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":"2026-07-05T05:56:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GAo9ipWW36P9ZZCDkiS7AGleRRpAj9vZnbmEVFmQhSN/svnCo3Y+U9j9xcYgJ3/0NMM4xaIZV4jVUhzeeeTBDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:02:56.206983Z"},"content_sha256":"007d03306277ce140018b75dd15ad84b5426c4b2ab894ceeb0a1748e106755a0","schema_version":"1.0","event_id":"sha256:007d03306277ce140018b75dd15ad84b5426c4b2ab894ceeb0a1748e106755a0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WOGWWQYPBRLU5Z4QZL42WDOZAB/bundle.json","state_url":"https://pith.science/pith/WOGWWQYPBRLU5Z4QZL42WDOZAB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WOGWWQYPBRLU5Z4QZL42WDOZAB/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":"2026-08-04T17:02:56Z","links":{"resolver":"https://pith.science/pith/WOGWWQYPBRLU5Z4QZL42WDOZAB","bundle":"https://pith.science/pith/WOGWWQYPBRLU5Z4QZL42WDOZAB/bundle.json","state":"https://pith.science/pith/WOGWWQYPBRLU5Z4QZL42WDOZAB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WOGWWQYPBRLU5Z4QZL42WDOZAB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WOGWWQYPBRLU5Z4QZL42WDOZAB","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":"da846752deb7e5579bc3678e47c9287c3e4e38aa2c3a1e2249b1fdd70cfc8580","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-30T13:42:58Z","title_canon_sha256":"4c5030ca691bf5a45059542b978c3b5d7af6871b8e23158232c31a574679c166"},"schema_version":"1.0","source":{"id":"2303.17376","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.17376","created_at":"2026-07-05T05:56:33Z"},{"alias_kind":"arxiv_version","alias_value":"2303.17376v1","created_at":"2026-07-05T05:56:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17376","created_at":"2026-07-05T05:56:33Z"},{"alias_kind":"pith_short_12","alias_value":"WOGWWQYPBRLU","created_at":"2026-07-05T05:56:33Z"},{"alias_kind":"pith_short_16","alias_value":"WOGWWQYPBRLU5Z4Q","created_at":"2026-07-05T05:56:33Z"},{"alias_kind":"pith_short_8","alias_value":"WOGWWQYP","created_at":"2026-07-05T05:56:33Z"}],"graph_snapshots":[{"event_id":"sha256:007d03306277ce140018b75dd15ad84b5426c4b2ab894ceeb0a1748e106755a0","target":"graph","created_at":"2026-07-05T05:56:33Z","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/2303.17376/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There has been a recent explosion of computer vision models which perform many tasks and are composed of an image encoder (usually a ViT) and an autoregressive decoder (usually a Transformer). However, most of this work simply presents one system and its results, leaving many questions regarding design decisions and trade-offs of such systems unanswered. In this work, we aim to provide such answers. We take a close look at autoregressive decoders for multi-task learning in multimodal computer vision, including classification, captioning, visual question answering, and optical character recogni","authors_text":"Alexander Kolesnikov, Andreas Steiner, Andr\\'e Susano Pinto, Bo Wan, Emanuele Bugliarello, Filip Pavetic, Gagan Madan, Liang-Chieh Chen, Lucas Beyer, Qihang Yu, Xiaohua Zhai, Xiao Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-30T13:42:58Z","title":"A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17376","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:c7bf492e861dee9837a1213a64d8d2bda2a48c86a0f7eb3468d7e10668f60273","target":"record","created_at":"2026-07-05T05:56:33Z","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":"da846752deb7e5579bc3678e47c9287c3e4e38aa2c3a1e2249b1fdd70cfc8580","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-30T13:42:58Z","title_canon_sha256":"4c5030ca691bf5a45059542b978c3b5d7af6871b8e23158232c31a574679c166"},"schema_version":"1.0","source":{"id":"2303.17376","kind":"arxiv","version":1}},"canonical_sha256":"b38d6b430f0c574ee790caf9ab0dd9005a03fd79578f7d757d9752d4c7125b4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b38d6b430f0c574ee790caf9ab0dd9005a03fd79578f7d757d9752d4c7125b4e","first_computed_at":"2026-07-05T05:56:33.366912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:56:33.366912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HBV0axlKzN7OdxzcGVDY0zL69yQClO8k72PmXGcYUq0AdV4oXwrAR09VVTw94OkW8+wSEkYjH4h62az8hq0WAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:56:33.367421Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.17376","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7bf492e861dee9837a1213a64d8d2bda2a48c86a0f7eb3468d7e10668f60273","sha256:007d03306277ce140018b75dd15ad84b5426c4b2ab894ceeb0a1748e106755a0"],"state_sha256":"e67bf1a9b3078731aa04f0d9f5449d3d6b9d0db7a7d006363ad901cb8e92957e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/7F7kVLeuJDEoOmDyAu7BpWVyV17tNRH4ZNvKvWyAGDA2bj4ym870/LGQLw5CbrW9V32ez8WsM8HWU9a/T6yDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:02:56.212924Z","bundle_sha256":"e9056d2f76151e823003a7aaca1ccc0962a8ad06456354c9e23241c38155656b"}}