{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:6SKSA4RMNG2NXUR5EEASPR5VHR","short_pith_number":"pith:6SKSA4RM","canonical_record":{"source":{"id":"2106.00666","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-01T17:54:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"690be607601c9f8f5d422e73c80b1b0d666a229dfd06048b74eed5b49ba8da94","abstract_canon_sha256":"87de38bbe6cacc8234892604788abb72f9e06508d427666d96d908a22ffcef39"},"schema_version":"1.0"},"canonical_sha256":"f49520722c69b4dbd23d210127c7b53c79ec1a6436784ad036de0a85d4ed04c3","source":{"kind":"arxiv","id":"2106.00666","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.00666","created_at":"2026-07-05T03:26:17Z"},{"alias_kind":"arxiv_version","alias_value":"2106.00666v3","created_at":"2026-07-05T03:26:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00666","created_at":"2026-07-05T03:26:17Z"},{"alias_kind":"pith_short_12","alias_value":"6SKSA4RMNG2N","created_at":"2026-07-05T03:26:17Z"},{"alias_kind":"pith_short_16","alias_value":"6SKSA4RMNG2NXUR5","created_at":"2026-07-05T03:26:17Z"},{"alias_kind":"pith_short_8","alias_value":"6SKSA4RM","created_at":"2026-07-05T03:26:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:6SKSA4RMNG2NXUR5EEASPR5VHR","target":"record","payload":{"canonical_record":{"source":{"id":"2106.00666","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-01T17:54:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"690be607601c9f8f5d422e73c80b1b0d666a229dfd06048b74eed5b49ba8da94","abstract_canon_sha256":"87de38bbe6cacc8234892604788abb72f9e06508d427666d96d908a22ffcef39"},"schema_version":"1.0"},"canonical_sha256":"f49520722c69b4dbd23d210127c7b53c79ec1a6436784ad036de0a85d4ed04c3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:17.372343Z","signature_b64":"ylx3EGyXPrzrZ0kYrgRgNKYHY8x04OH2aiWtjyOkOiBqw8ZBN93rgf7Dnj1kWt+SyWdTmx6q5scssY8nYPkXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f49520722c69b4dbd23d210127c7b53c79ec1a6436784ad036de0a85d4ed04c3","last_reissued_at":"2026-07-05T03:26:17.371840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:17.371840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.00666","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:26:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a3kMxqV6P5atmikMf5rzi9b6LiqnWmOaxYuIKvpOJ24RkIhQX3tXzWfxwfdct+K+0yHVoZD8lrD7YcUx3mUeBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T05:22:56.414947Z"},"content_sha256":"67bf5b4adc333fd7885db188c80e04fad4ffd2157f05d750870eb226646ec81b","schema_version":"1.0","event_id":"sha256:67bf5b4adc333fd7885db188c80e04fad4ffd2157f05d750870eb226646ec81b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:6SKSA4RMNG2NXUR5EEASPR5VHR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bencheng Liao, Jianwei Niu, Jiemin Fang, Jiyang Qi, Rui Wu, Wenyu Liu, Xinggang Wang, Yuxin Fang","submitted_at":"2021-06-01T17:54:09Z","abstract_excerpt":"Can Transformer perform 2D object- and region-level recognition from a pure sequence-to-sequence perspective with minimal knowledge about the 2D spatial structure? To answer this question, we present You Only Look at One Sequence (YOLOS), a series of object detection models based on the vanilla Vision Transformer with the fewest possible modifications, region priors, as well as inductive biases of the target task. We find that YOLOS pre-trained on the mid-sized ImageNet-1k dataset only can already achieve quite competitive performance on the challenging COCO object detection benchmark, e.g., Y"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00666","kind":"arxiv","version":3},"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/2106.00666/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":"2026-07-05T03:26:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xYnxFbrtaLA+lf2Yo7ByodYEx7dhoHVRgC08Vjy4sCkowafNeVCeLqK7aT/yVFeRdwtLTZHgEUCX4BgqpanMBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T05:22:56.415354Z"},"content_sha256":"c8735f45d13d020d2fb1423a874eace407d6e3b028dd5f948c354a3d0340fdfb","schema_version":"1.0","event_id":"sha256:c8735f45d13d020d2fb1423a874eace407d6e3b028dd5f948c354a3d0340fdfb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6SKSA4RMNG2NXUR5EEASPR5VHR/bundle.json","state_url":"https://pith.science/pith/6SKSA4RMNG2NXUR5EEASPR5VHR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6SKSA4RMNG2NXUR5EEASPR5VHR/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":"2026-07-22T05:22:56Z","links":{"resolver":"https://pith.science/pith/6SKSA4RMNG2NXUR5EEASPR5VHR","bundle":"https://pith.science/pith/6SKSA4RMNG2NXUR5EEASPR5VHR/bundle.json","state":"https://pith.science/pith/6SKSA4RMNG2NXUR5EEASPR5VHR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6SKSA4RMNG2NXUR5EEASPR5VHR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6SKSA4RMNG2NXUR5EEASPR5VHR","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":"87de38bbe6cacc8234892604788abb72f9e06508d427666d96d908a22ffcef39","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-01T17:54:09Z","title_canon_sha256":"690be607601c9f8f5d422e73c80b1b0d666a229dfd06048b74eed5b49ba8da94"},"schema_version":"1.0","source":{"id":"2106.00666","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.00666","created_at":"2026-07-05T03:26:17Z"},{"alias_kind":"arxiv_version","alias_value":"2106.00666v3","created_at":"2026-07-05T03:26:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00666","created_at":"2026-07-05T03:26:17Z"},{"alias_kind":"pith_short_12","alias_value":"6SKSA4RMNG2N","created_at":"2026-07-05T03:26:17Z"},{"alias_kind":"pith_short_16","alias_value":"6SKSA4RMNG2NXUR5","created_at":"2026-07-05T03:26:17Z"},{"alias_kind":"pith_short_8","alias_value":"6SKSA4RM","created_at":"2026-07-05T03:26:17Z"}],"graph_snapshots":[{"event_id":"sha256:c8735f45d13d020d2fb1423a874eace407d6e3b028dd5f948c354a3d0340fdfb","target":"graph","created_at":"2026-07-05T03:26:17Z","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/2106.00666/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Can Transformer perform 2D object- and region-level recognition from a pure sequence-to-sequence perspective with minimal knowledge about the 2D spatial structure? To answer this question, we present You Only Look at One Sequence (YOLOS), a series of object detection models based on the vanilla Vision Transformer with the fewest possible modifications, region priors, as well as inductive biases of the target task. We find that YOLOS pre-trained on the mid-sized ImageNet-1k dataset only can already achieve quite competitive performance on the challenging COCO object detection benchmark, e.g., Y","authors_text":"Bencheng Liao, Jianwei Niu, Jiemin Fang, Jiyang Qi, Rui Wu, Wenyu Liu, Xinggang Wang, Yuxin Fang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-01T17:54:09Z","title":"You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00666","kind":"arxiv","version":3},"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":"sha256:67bf5b4adc333fd7885db188c80e04fad4ffd2157f05d750870eb226646ec81b","target":"record","created_at":"2026-07-05T03:26:17Z","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":"87de38bbe6cacc8234892604788abb72f9e06508d427666d96d908a22ffcef39","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-01T17:54:09Z","title_canon_sha256":"690be607601c9f8f5d422e73c80b1b0d666a229dfd06048b74eed5b49ba8da94"},"schema_version":"1.0","source":{"id":"2106.00666","kind":"arxiv","version":3}},"canonical_sha256":"f49520722c69b4dbd23d210127c7b53c79ec1a6436784ad036de0a85d4ed04c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f49520722c69b4dbd23d210127c7b53c79ec1a6436784ad036de0a85d4ed04c3","first_computed_at":"2026-07-05T03:26:17.371840Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:26:17.371840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ylx3EGyXPrzrZ0kYrgRgNKYHY8x04OH2aiWtjyOkOiBqw8ZBN93rgf7Dnj1kWt+SyWdTmx6q5scssY8nYPkXCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:26:17.372343Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.00666","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67bf5b4adc333fd7885db188c80e04fad4ffd2157f05d750870eb226646ec81b","sha256:c8735f45d13d020d2fb1423a874eace407d6e3b028dd5f948c354a3d0340fdfb"],"state_sha256":"a054847d371c4eaaf4038799858047ac7af2bacecfbf939ab1ecd5c52740d85b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"553TqjTdpVbiW62E6sG6IKHL1H4r5P+VERbwlhUf1D2qjvdBsW77eSqnh7XtOG8BpuskY1GDB9U0wS0tenPZAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-22T05:22:56.417516Z","bundle_sha256":"33a888762524e14b5e15b5e3e3b218f131f2a9a2b287acab81b45de11873c029"}}