{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VG32VVS5G274RD7E5DNWTTNDFG","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":"b246ea78e6eec6a9b0d8d8bf9553a0af9f7e0c4e0ac3caca159abd788edc2620","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-15T17:08:53Z","title_canon_sha256":"ecfd9495b17522137e8ddbfadc85a17058ee7d95ac88503f441a725fa2956fb4"},"schema_version":"1.0","source":{"id":"2206.07669","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.07669","created_at":"2026-07-05T05:07:00Z"},{"alias_kind":"arxiv_version","alias_value":"2206.07669v2","created_at":"2026-07-05T05:07:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07669","created_at":"2026-07-05T05:07:00Z"},{"alias_kind":"pith_short_12","alias_value":"VG32VVS5G274","created_at":"2026-07-05T05:07:00Z"},{"alias_kind":"pith_short_16","alias_value":"VG32VVS5G274RD7E","created_at":"2026-07-05T05:07:00Z"},{"alias_kind":"pith_short_8","alias_value":"VG32VVS5","created_at":"2026-07-05T05:07:00Z"}],"graph_snapshots":[{"event_id":"sha256:ab3283302156f2e022b82a83dad4005323519bfd7f39773198973159e4363159","target":"graph","created_at":"2026-07-05T05:07:00Z","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/2206.07669/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"David J. Fleet, Geoffrey Hinton, Lala Li, Saurabh Saxena, Ting Chen, Tsung-Yi Lin","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-15T17:08:53Z","title":"A Unified Sequence Interface for Vision Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07669","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:bcd7ecf7544086a28956af514c218996ce9b41708436831e4dc903cc7a886f8e","target":"record","created_at":"2026-07-05T05:07:00Z","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":"b246ea78e6eec6a9b0d8d8bf9553a0af9f7e0c4e0ac3caca159abd788edc2620","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-15T17:08:53Z","title_canon_sha256":"ecfd9495b17522137e8ddbfadc85a17058ee7d95ac88503f441a725fa2956fb4"},"schema_version":"1.0","source":{"id":"2206.07669","kind":"arxiv","version":2}},"canonical_sha256":"a9b7aad65d36bfc88fe4e8db69cda3299310529fbdfe719dc14724e01adfb722","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9b7aad65d36bfc88fe4e8db69cda3299310529fbdfe719dc14724e01adfb722","first_computed_at":"2026-07-05T05:07:00.410889Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:07:00.410889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"phcBtlFUg0YUN/YCU8eXFka3UPjSquG0toQhG0zYOee93ocuN4YykdHOSk8eLPX9QhIHK7FfZ47mbPSGKu2iAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:07:00.411335Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.07669","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcd7ecf7544086a28956af514c218996ce9b41708436831e4dc903cc7a886f8e","sha256:ab3283302156f2e022b82a83dad4005323519bfd7f39773198973159e4363159"],"state_sha256":"512d7ba93b5a666e439f06f7e3760463f3b0e83b8538fccecb0c84163e96fa38"}