{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FRS6GJAYF2FBZDUNRR2HSVFWYH","short_pith_number":"pith:FRS6GJAY","schema_version":"1.0","canonical_sha256":"2c65e324182e8a1c8e8d8c747954b6c1cc83654369b0f57ef2de6e065d55f1f6","source":{"kind":"arxiv","id":"2109.10852","version":2},"attestation_state":"computed","paper":{"title":"Pix2seq: A Language Modeling Framework for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"David J. Fleet, Geoffrey Hinton, Lala Li, Saurabh Saxena, Ting Chen","submitted_at":"2021-09-22T17:26:36Z","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"},"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":"2109.10852","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-22T17:26:36Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"27fd8ca5385856b40c7ec3f156169484789ae07db6da35c60ab37162980ddc82","abstract_canon_sha256":"ddeb489c13153dd68698764831a564cff657314568b69810c9bf7c41cab2da8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:40.315418Z","signature_b64":"ImzdRyR/5YL5xgObGweJnJee70uaY0Dhg3rMb/TdCMZJLrm31rgk2JcYBdbUWylrGzi4fYLcCT+Ab1E9OE9KCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c65e324182e8a1c8e8d8c747954b6c1cc83654369b0f57ef2de6e065d55f1f6","last_reissued_at":"2026-07-05T04:08:40.314950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:40.314950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pix2seq: A Language Modeling Framework for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"David J. Fleet, Geoffrey Hinton, Lala Li, Saurabh Saxena, Ting Chen","submitted_at":"2021-09-22T17:26:36Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.10852","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/2109.10852/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":"2109.10852","created_at":"2026-07-05T04:08:40.315007+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.10852v2","created_at":"2026-07-05T04:08:40.315007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.10852","created_at":"2026-07-05T04:08:40.315007+00:00"},{"alias_kind":"pith_short_12","alias_value":"FRS6GJAYF2FB","created_at":"2026-07-05T04:08:40.315007+00:00"},{"alias_kind":"pith_short_16","alias_value":"FRS6GJAYF2FBZDUN","created_at":"2026-07-05T04:08:40.315007+00:00"},{"alias_kind":"pith_short_8","alias_value":"FRS6GJAY","created_at":"2026-07-05T04:08:40.315007+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24564","citing_title":"PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24564","citing_title":"PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02083","citing_title":"DeepGaze3.5-VL: Modeling Scanpaths via Autoregressive Token Prediction","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08420","citing_title":"CheXanatomy: Anatomy-Aware Vision-Language Modeling for Chest Radiographs","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24564","citing_title":"PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24564","citing_title":"PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14923","citing_title":"SceneParser: Hierarchical Scene Parsing for Visual Semantics Understanding","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25427","citing_title":"Binding Visual Features Point by Point","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30126","citing_title":"PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2510.18822","citing_title":"SAM 2++: Tracking Anything at Any Granularity","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2409.12514","citing_title":"TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2401.10935","citing_title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2209.06794","citing_title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","ref_index":126,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09016","citing_title":"Raster2Seq: Polygon Sequence Generation for Floorplan Reconstruction","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2310.01415","citing_title":"GPT-Driver: Learning to Drive with GPT","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02593","citing_title":"Moondream Segmentation: From Words to Masks","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2306.14824","citing_title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08921","citing_title":"TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2401.14159","citing_title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FRS6GJAYF2FBZDUNRR2HSVFWYH","json":"https://pith.science/pith/FRS6GJAYF2FBZDUNRR2HSVFWYH.json","graph_json":"https://pith.science/api/pith-number/FRS6GJAYF2FBZDUNRR2HSVFWYH/graph.json","events_json":"https://pith.science/api/pith-number/FRS6GJAYF2FBZDUNRR2HSVFWYH/events.json","paper":"https://pith.science/paper/FRS6GJAY"},"agent_actions":{"view_html":"https://pith.science/pith/FRS6GJAYF2FBZDUNRR2HSVFWYH","download_json":"https://pith.science/pith/FRS6GJAYF2FBZDUNRR2HSVFWYH.json","view_paper":"https://pith.science/paper/FRS6GJAY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.10852&json=true","fetch_graph":"https://pith.science/api/pith-number/FRS6GJAYF2FBZDUNRR2HSVFWYH/graph.json","fetch_events":"https://pith.science/api/pith-number/FRS6GJAYF2FBZDUNRR2HSVFWYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FRS6GJAYF2FBZDUNRR2HSVFWYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FRS6GJAYF2FBZDUNRR2HSVFWYH/action/storage_attestation","attest_author":"https://pith.science/pith/FRS6GJAYF2FBZDUNRR2HSVFWYH/action/author_attestation","sign_citation":"https://pith.science/pith/FRS6GJAYF2FBZDUNRR2HSVFWYH/action/citation_signature","submit_replication":"https://pith.science/pith/FRS6GJAYF2FBZDUNRR2HSVFWYH/action/replication_record"}},"created_at":"2026-07-05T04:08:40.315007+00:00","updated_at":"2026-07-05T04:08:40.315007+00:00"}