{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:IGY5WSB3X3DLH242AI4E2KRWQD","short_pith_number":"pith:IGY5WSB3","canonical_record":{"source":{"id":"2205.06230","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-12T17:20:36Z","cross_cats_sorted":[],"title_canon_sha256":"3434a61164d9733b082f7598190befce1e234d099fb82337b50bef42883d0b8e","abstract_canon_sha256":"0dd54383247bfbd1d4334e396de02656b22d610f60d0326f712a902cf4b19e5f"},"schema_version":"1.0"},"canonical_sha256":"41b1db483bbec6b3eb9a02384d2a3680d3c49346cd76cb7e2190a0278855de2d","source":{"kind":"arxiv","id":"2205.06230","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.06230","created_at":"2026-07-05T04:41:55Z"},{"alias_kind":"arxiv_version","alias_value":"2205.06230v2","created_at":"2026-07-05T04:41:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.06230","created_at":"2026-07-05T04:41:55Z"},{"alias_kind":"pith_short_12","alias_value":"IGY5WSB3X3DL","created_at":"2026-07-05T04:41:55Z"},{"alias_kind":"pith_short_16","alias_value":"IGY5WSB3X3DLH242","created_at":"2026-07-05T04:41:55Z"},{"alias_kind":"pith_short_8","alias_value":"IGY5WSB3","created_at":"2026-07-05T04:41:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:IGY5WSB3X3DLH242AI4E2KRWQD","target":"record","payload":{"canonical_record":{"source":{"id":"2205.06230","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-12T17:20:36Z","cross_cats_sorted":[],"title_canon_sha256":"3434a61164d9733b082f7598190befce1e234d099fb82337b50bef42883d0b8e","abstract_canon_sha256":"0dd54383247bfbd1d4334e396de02656b22d610f60d0326f712a902cf4b19e5f"},"schema_version":"1.0"},"canonical_sha256":"41b1db483bbec6b3eb9a02384d2a3680d3c49346cd76cb7e2190a0278855de2d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:41:55.891385Z","signature_b64":"YxBFnDYKSP5d55jZ4ur5/xAt5IkJFtstyzK4gy4fe4IVLxKQKRSilGeItpFxf5sSVo319VxpyrTu5V9ScISFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41b1db483bbec6b3eb9a02384d2a3680d3c49346cd76cb7e2190a0278855de2d","last_reissued_at":"2026-07-05T04:41:55.890929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:41:55.890929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.06230","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:41:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9qL9J+b+U/RIrvUGs2h2cA0tg3FNJW4vMAanC5fGy6ElC/HcRhLI78rsRGUmAjyXTejT94mv2ARGt2pol9i6AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:41:38.146809Z"},"content_sha256":"39d56bc84786274f45be607102bd469cd684a5885f060f7624569bfea175aac9","schema_version":"1.0","event_id":"sha256:39d56bc84786274f45be607102bd469cd684a5885f060f7624569bfea175aac9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:IGY5WSB3X3DLH242AI4E2KRWQD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Simple Open-Vocabulary Object Detection with Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexey Dosovitskiy, Alexey Gritsenko, Anurag Arnab, Aravindh Mahendran, Austin Stone, Dirk Weissenborn, Matthias Minderer, Maxim Neumann, Mostafa Dehghani, Neil Houlsby, Thomas Kipf, Xiaohua Zhai, Xiao Wang, Zhuoran Shen","submitted_at":"2022-05-12T17:20:36Z","abstract_excerpt":"Combining simple architectures with large-scale pre-training has led to massive improvements in image classification. For object detection, pre-training and scaling approaches are less well established, especially in the long-tailed and open-vocabulary setting, where training data is relatively scarce. In this paper, we propose a strong recipe for transferring image-text models to open-vocabulary object detection. We use a standard Vision Transformer architecture with minimal modifications, contrastive image-text pre-training, and end-to-end detection fine-tuning. Our analysis of the scaling p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.06230","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/2205.06230/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":"2026-07-05T04:41:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VuGCR1KF3Q241Vxy5cTghChg9hOKgcp4X04i4yIfvKFdus4qSPsTRPLGKPgGANOycFR66ij6wzGAeY7Oz0vLBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:41:38.147322Z"},"content_sha256":"8c18391ad6a2e34b5f19cacad6fbcb8461ae80f8702a0d53b0da7efb34b791f8","schema_version":"1.0","event_id":"sha256:8c18391ad6a2e34b5f19cacad6fbcb8461ae80f8702a0d53b0da7efb34b791f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IGY5WSB3X3DLH242AI4E2KRWQD/bundle.json","state_url":"https://pith.science/pith/IGY5WSB3X3DLH242AI4E2KRWQD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IGY5WSB3X3DLH242AI4E2KRWQD/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":"2026-08-03T18:41:38Z","links":{"resolver":"https://pith.science/pith/IGY5WSB3X3DLH242AI4E2KRWQD","bundle":"https://pith.science/pith/IGY5WSB3X3DLH242AI4E2KRWQD/bundle.json","state":"https://pith.science/pith/IGY5WSB3X3DLH242AI4E2KRWQD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IGY5WSB3X3DLH242AI4E2KRWQD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IGY5WSB3X3DLH242AI4E2KRWQD","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":"0dd54383247bfbd1d4334e396de02656b22d610f60d0326f712a902cf4b19e5f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-12T17:20:36Z","title_canon_sha256":"3434a61164d9733b082f7598190befce1e234d099fb82337b50bef42883d0b8e"},"schema_version":"1.0","source":{"id":"2205.06230","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.06230","created_at":"2026-07-05T04:41:55Z"},{"alias_kind":"arxiv_version","alias_value":"2205.06230v2","created_at":"2026-07-05T04:41:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.06230","created_at":"2026-07-05T04:41:55Z"},{"alias_kind":"pith_short_12","alias_value":"IGY5WSB3X3DL","created_at":"2026-07-05T04:41:55Z"},{"alias_kind":"pith_short_16","alias_value":"IGY5WSB3X3DLH242","created_at":"2026-07-05T04:41:55Z"},{"alias_kind":"pith_short_8","alias_value":"IGY5WSB3","created_at":"2026-07-05T04:41:55Z"}],"graph_snapshots":[{"event_id":"sha256:8c18391ad6a2e34b5f19cacad6fbcb8461ae80f8702a0d53b0da7efb34b791f8","target":"graph","created_at":"2026-07-05T04:41:55Z","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/2205.06230/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Combining simple architectures with large-scale pre-training has led to massive improvements in image classification. For object detection, pre-training and scaling approaches are less well established, especially in the long-tailed and open-vocabulary setting, where training data is relatively scarce. In this paper, we propose a strong recipe for transferring image-text models to open-vocabulary object detection. We use a standard Vision Transformer architecture with minimal modifications, contrastive image-text pre-training, and end-to-end detection fine-tuning. Our analysis of the scaling p","authors_text":"Alexey Dosovitskiy, Alexey Gritsenko, Anurag Arnab, Aravindh Mahendran, Austin Stone, Dirk Weissenborn, Matthias Minderer, Maxim Neumann, Mostafa Dehghani, Neil Houlsby, Thomas Kipf, Xiaohua Zhai, Xiao Wang, Zhuoran Shen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-12T17:20:36Z","title":"Simple Open-Vocabulary Object Detection with Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.06230","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":"sha256:39d56bc84786274f45be607102bd469cd684a5885f060f7624569bfea175aac9","target":"record","created_at":"2026-07-05T04:41:55Z","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":"0dd54383247bfbd1d4334e396de02656b22d610f60d0326f712a902cf4b19e5f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-12T17:20:36Z","title_canon_sha256":"3434a61164d9733b082f7598190befce1e234d099fb82337b50bef42883d0b8e"},"schema_version":"1.0","source":{"id":"2205.06230","kind":"arxiv","version":2}},"canonical_sha256":"41b1db483bbec6b3eb9a02384d2a3680d3c49346cd76cb7e2190a0278855de2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41b1db483bbec6b3eb9a02384d2a3680d3c49346cd76cb7e2190a0278855de2d","first_computed_at":"2026-07-05T04:41:55.890929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:41:55.890929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YxBFnDYKSP5d55jZ4ur5/xAt5IkJFtstyzK4gy4fe4IVLxKQKRSilGeItpFxf5sSVo319VxpyrTu5V9ScISFAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:41:55.891385Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.06230","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39d56bc84786274f45be607102bd469cd684a5885f060f7624569bfea175aac9","sha256:8c18391ad6a2e34b5f19cacad6fbcb8461ae80f8702a0d53b0da7efb34b791f8"],"state_sha256":"bb3568d494875264e85d0cffbd4088754850579b33c9bc7744d91c6ee4dba208"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"utROI0HJZ4N4+Dj8W/6msppPGriNlpze8r8BMwpcB9ru4Dxg08/0xUDR+9thGV6j0WlaUmWUjVmzQMrZtsMsCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:41:38.151158Z","bundle_sha256":"1eee34ff333b53d254b4770ae0ba67e8951e0f478b79938d4defa4b99cf089a4"}}