{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2WNSQ6VI5SKRYX2MVNI46BJF64","short_pith_number":"pith:2WNSQ6VI","schema_version":"1.0","canonical_sha256":"d59b287aa8ec951c5f4cab51cf0525f70aa1f363fa14f24cafbc3041a8a905a3","source":{"kind":"arxiv","id":"2111.12710","version":3},"attestation_state":"computed","paper":{"title":"PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Baining Guo, Dong Chen, Dongdong Chen, Fang Wen, Jianmin Bao, Lu Yuan, Nenghai Yu, Ting Zhang, Weiming Zhang, Xiaoyi Dong","submitted_at":"2021-11-24T18:59:58Z","abstract_excerpt":"This paper explores a better prediction target for BERT pre-training of vision transformers. We observe that current prediction targets disagree with human perception judgment.This contradiction motivates us to learn a perceptual prediction target. We argue that perceptually similar images should stay close to each other in the prediction target space. We surprisingly find one simple yet effective idea: enforcing perceptual similarity during the dVAE training. Moreover, we adopt a self-supervised transformer model for deep feature extraction and show that it works well for calculating perceptu"},"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":"2111.12710","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-24T18:59:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2e0e2ee3c66f35059993d3e4efcc0a96e55f9fcee10c0477ab1225170c17fb74","abstract_canon_sha256":"93f6a0e6c4d97c04250a6da5b0049c61025e12cdc18fd7f3982bf232fbcc33c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:47.446931Z","signature_b64":"/17hAkQloaysxsWwC5BVaWDrujuAQgUjs1goE6YaQk/WEI9rv8FOhXsKyOF9Pcltm5TLapMXTZmFzG5WFxHLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d59b287aa8ec951c5f4cab51cf0525f70aa1f363fa14f24cafbc3041a8a905a3","last_reissued_at":"2026-07-05T05:25:47.446424Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:47.446424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Baining Guo, Dong Chen, Dongdong Chen, Fang Wen, Jianmin Bao, Lu Yuan, Nenghai Yu, Ting Zhang, Weiming Zhang, Xiaoyi Dong","submitted_at":"2021-11-24T18:59:58Z","abstract_excerpt":"This paper explores a better prediction target for BERT pre-training of vision transformers. We observe that current prediction targets disagree with human perception judgment.This contradiction motivates us to learn a perceptual prediction target. We argue that perceptually similar images should stay close to each other in the prediction target space. We surprisingly find one simple yet effective idea: enforcing perceptual similarity during the dVAE training. Moreover, we adopt a self-supervised transformer model for deep feature extraction and show that it works well for calculating perceptu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12710","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/2111.12710/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":"2111.12710","created_at":"2026-07-05T05:25:47.446489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.12710v3","created_at":"2026-07-05T05:25:47.446489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12710","created_at":"2026-07-05T05:25:47.446489+00:00"},{"alias_kind":"pith_short_12","alias_value":"2WNSQ6VI5SKR","created_at":"2026-07-05T05:25:47.446489+00:00"},{"alias_kind":"pith_short_16","alias_value":"2WNSQ6VI5SKRYX2M","created_at":"2026-07-05T05:25:47.446489+00:00"},{"alias_kind":"pith_short_8","alias_value":"2WNSQ6VI","created_at":"2026-07-05T05:25:47.446489+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2309.16588","citing_title":"Vision Transformers Need Registers","ref_index":79,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2WNSQ6VI5SKRYX2MVNI46BJF64","json":"https://pith.science/pith/2WNSQ6VI5SKRYX2MVNI46BJF64.json","graph_json":"https://pith.science/api/pith-number/2WNSQ6VI5SKRYX2MVNI46BJF64/graph.json","events_json":"https://pith.science/api/pith-number/2WNSQ6VI5SKRYX2MVNI46BJF64/events.json","paper":"https://pith.science/paper/2WNSQ6VI"},"agent_actions":{"view_html":"https://pith.science/pith/2WNSQ6VI5SKRYX2MVNI46BJF64","download_json":"https://pith.science/pith/2WNSQ6VI5SKRYX2MVNI46BJF64.json","view_paper":"https://pith.science/paper/2WNSQ6VI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.12710&json=true","fetch_graph":"https://pith.science/api/pith-number/2WNSQ6VI5SKRYX2MVNI46BJF64/graph.json","fetch_events":"https://pith.science/api/pith-number/2WNSQ6VI5SKRYX2MVNI46BJF64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2WNSQ6VI5SKRYX2MVNI46BJF64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2WNSQ6VI5SKRYX2MVNI46BJF64/action/storage_attestation","attest_author":"https://pith.science/pith/2WNSQ6VI5SKRYX2MVNI46BJF64/action/author_attestation","sign_citation":"https://pith.science/pith/2WNSQ6VI5SKRYX2MVNI46BJF64/action/citation_signature","submit_replication":"https://pith.science/pith/2WNSQ6VI5SKRYX2MVNI46BJF64/action/replication_record"}},"created_at":"2026-07-05T05:25:47.446489+00:00","updated_at":"2026-07-05T05:25:47.446489+00:00"}