{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FRS6GJAYF2FBZDUNRR2HSVFWYH","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":"ddeb489c13153dd68698764831a564cff657314568b69810c9bf7c41cab2da8d","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-22T17:26:36Z","title_canon_sha256":"27fd8ca5385856b40c7ec3f156169484789ae07db6da35c60ab37162980ddc82"},"schema_version":"1.0","source":{"id":"2109.10852","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.10852","created_at":"2026-07-05T04:08:40Z"},{"alias_kind":"arxiv_version","alias_value":"2109.10852v2","created_at":"2026-07-05T04:08:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.10852","created_at":"2026-07-05T04:08:40Z"},{"alias_kind":"pith_short_12","alias_value":"FRS6GJAYF2FB","created_at":"2026-07-05T04:08:40Z"},{"alias_kind":"pith_short_16","alias_value":"FRS6GJAYF2FBZDUN","created_at":"2026-07-05T04:08:40Z"},{"alias_kind":"pith_short_8","alias_value":"FRS6GJAY","created_at":"2026-07-05T04:08:40Z"}],"graph_snapshots":[{"event_id":"sha256:8141bf4e7b731c252eda858a8512a59800f77560c5b687cf4ec3c0b65e355c81","target":"graph","created_at":"2026-07-05T04:08:40Z","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/2109.10852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Pix2Seq, a simple and generic framework for object detection. Unlike existing approaches that explicitly integrate prior knowledge about the task, we cast object detection as a language modeling task conditioned on the observed pixel inputs. Object descriptions (e.g., bounding boxes and class labels) are expressed as sequences of discrete tokens, and we train a neural network to perceive the image and generate the desired sequence. Our approach is based mainly on the intuition that if a neural network knows about where and what the objects are, we just need to teach it how to read t","authors_text":"David J. Fleet, Geoffrey Hinton, Lala Li, Saurabh Saxena, Ting Chen","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-22T17:26:36Z","title":"Pix2seq: A Language Modeling Framework for Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.10852","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:cb59cb3decb7452f9fcd14025948ee84be0a82a4deed652bfbb63338e611e921","target":"record","created_at":"2026-07-05T04:08:40Z","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":"ddeb489c13153dd68698764831a564cff657314568b69810c9bf7c41cab2da8d","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-22T17:26:36Z","title_canon_sha256":"27fd8ca5385856b40c7ec3f156169484789ae07db6da35c60ab37162980ddc82"},"schema_version":"1.0","source":{"id":"2109.10852","kind":"arxiv","version":2}},"canonical_sha256":"2c65e324182e8a1c8e8d8c747954b6c1cc83654369b0f57ef2de6e065d55f1f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c65e324182e8a1c8e8d8c747954b6c1cc83654369b0f57ef2de6e065d55f1f6","first_computed_at":"2026-07-05T04:08:40.314950Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:08:40.314950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ImzdRyR/5YL5xgObGweJnJee70uaY0Dhg3rMb/TdCMZJLrm31rgk2JcYBdbUWylrGzi4fYLcCT+Ab1E9OE9KCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:08:40.315418Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.10852","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb59cb3decb7452f9fcd14025948ee84be0a82a4deed652bfbb63338e611e921","sha256:8141bf4e7b731c252eda858a8512a59800f77560c5b687cf4ec3c0b65e355c81"],"state_sha256":"514dc12403471f668a3df11c520954647b5753dfd72a7607227d6d7d208a0fc8"}