{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VG32VVS5G274RD7E5DNWTTNDFG","short_pith_number":"pith:VG32VVS5","schema_version":"1.0","canonical_sha256":"a9b7aad65d36bfc88fe4e8db69cda3299310529fbdfe719dc14724e01adfb722","source":{"kind":"arxiv","id":"2206.07669","version":2},"attestation_state":"computed","paper":{"title":"A Unified Sequence Interface for Vision Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"David J. Fleet, Geoffrey Hinton, Lala Li, Saurabh Saxena, Ting Chen, Tsung-Yi Lin","submitted_at":"2022-06-15T17:08:53Z","abstract_excerpt":"While language tasks are naturally expressed in a single, unified, modeling framework, i.e., generating sequences of tokens, this has not been the case in computer vision. As a result, there is a proliferation of distinct architectures and loss functions for different vision tasks. In this work we show that a diverse set of \"core\" computer vision tasks can also be unified if formulated in terms of a shared pixel-to-sequence interface. We focus on four tasks, namely, object detection, instance segmentation, keypoint detection, and image captioning, all with diverse types of outputs, e.g., bound"},"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":"2206.07669","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-15T17:08:53Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"ecfd9495b17522137e8ddbfadc85a17058ee7d95ac88503f441a725fa2956fb4","abstract_canon_sha256":"b246ea78e6eec6a9b0d8d8bf9553a0af9f7e0c4e0ac3caca159abd788edc2620"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:00.411335Z","signature_b64":"phcBtlFUg0YUN/YCU8eXFka3UPjSquG0toQhG0zYOee93ocuN4YykdHOSk8eLPX9QhIHK7FfZ47mbPSGKu2iAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9b7aad65d36bfc88fe4e8db69cda3299310529fbdfe719dc14724e01adfb722","last_reissued_at":"2026-07-05T05:07:00.410889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:00.410889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified Sequence Interface for Vision Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"David J. Fleet, Geoffrey Hinton, Lala Li, Saurabh Saxena, Ting Chen, Tsung-Yi Lin","submitted_at":"2022-06-15T17:08:53Z","abstract_excerpt":"While language tasks are naturally expressed in a single, unified, modeling framework, i.e., generating sequences of tokens, this has not been the case in computer vision. As a result, there is a proliferation of distinct architectures and loss functions for different vision tasks. In this work we show that a diverse set of \"core\" computer vision tasks can also be unified if formulated in terms of a shared pixel-to-sequence interface. We focus on four tasks, namely, object detection, instance segmentation, keypoint detection, and image captioning, all with diverse types of outputs, e.g., bound"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07669","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/2206.07669/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":"2206.07669","created_at":"2026-07-05T05:07:00.410946+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.07669v2","created_at":"2026-07-05T05:07:00.410946+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07669","created_at":"2026-07-05T05:07:00.410946+00:00"},{"alias_kind":"pith_short_12","alias_value":"VG32VVS5G274","created_at":"2026-07-05T05:07:00.410946+00:00"},{"alias_kind":"pith_short_16","alias_value":"VG32VVS5G274RD7E","created_at":"2026-07-05T05:07:00.410946+00:00"},{"alias_kind":"pith_short_8","alias_value":"VG32VVS5","created_at":"2026-07-05T05:07:00.410946+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2209.06794","citing_title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","ref_index":197,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VG32VVS5G274RD7E5DNWTTNDFG","json":"https://pith.science/pith/VG32VVS5G274RD7E5DNWTTNDFG.json","graph_json":"https://pith.science/api/pith-number/VG32VVS5G274RD7E5DNWTTNDFG/graph.json","events_json":"https://pith.science/api/pith-number/VG32VVS5G274RD7E5DNWTTNDFG/events.json","paper":"https://pith.science/paper/VG32VVS5"},"agent_actions":{"view_html":"https://pith.science/pith/VG32VVS5G274RD7E5DNWTTNDFG","download_json":"https://pith.science/pith/VG32VVS5G274RD7E5DNWTTNDFG.json","view_paper":"https://pith.science/paper/VG32VVS5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.07669&json=true","fetch_graph":"https://pith.science/api/pith-number/VG32VVS5G274RD7E5DNWTTNDFG/graph.json","fetch_events":"https://pith.science/api/pith-number/VG32VVS5G274RD7E5DNWTTNDFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VG32VVS5G274RD7E5DNWTTNDFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VG32VVS5G274RD7E5DNWTTNDFG/action/storage_attestation","attest_author":"https://pith.science/pith/VG32VVS5G274RD7E5DNWTTNDFG/action/author_attestation","sign_citation":"https://pith.science/pith/VG32VVS5G274RD7E5DNWTTNDFG/action/citation_signature","submit_replication":"https://pith.science/pith/VG32VVS5G274RD7E5DNWTTNDFG/action/replication_record"}},"created_at":"2026-07-05T05:07:00.410946+00:00","updated_at":"2026-07-05T05:07:00.410946+00:00"}