{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2WNSQ6VI5SKRYX2MVNI46BJF64","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":"93f6a0e6c4d97c04250a6da5b0049c61025e12cdc18fd7f3982bf232fbcc33c9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-24T18:59:58Z","title_canon_sha256":"2e0e2ee3c66f35059993d3e4efcc0a96e55f9fcee10c0477ab1225170c17fb74"},"schema_version":"1.0","source":{"id":"2111.12710","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.12710","created_at":"2026-07-05T05:25:47Z"},{"alias_kind":"arxiv_version","alias_value":"2111.12710v3","created_at":"2026-07-05T05:25:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12710","created_at":"2026-07-05T05:25:47Z"},{"alias_kind":"pith_short_12","alias_value":"2WNSQ6VI5SKR","created_at":"2026-07-05T05:25:47Z"},{"alias_kind":"pith_short_16","alias_value":"2WNSQ6VI5SKRYX2M","created_at":"2026-07-05T05:25:47Z"},{"alias_kind":"pith_short_8","alias_value":"2WNSQ6VI","created_at":"2026-07-05T05:25:47Z"}],"graph_snapshots":[{"event_id":"sha256:94fee4dea9adb692d0fc7f237fe26bcbf9452089769f5f5c000fef32e9542d78","target":"graph","created_at":"2026-07-05T05:25:47Z","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/2111.12710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Baining Guo, Dong Chen, Dongdong Chen, Fang Wen, Jianmin Bao, Lu Yuan, Nenghai Yu, Ting Zhang, Weiming Zhang, Xiaoyi Dong","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-24T18:59:58Z","title":"PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12710","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:fa9822ffae7e0559a63cebf53c082638fa2fc7a6d404169f896f9cb6a70417f5","target":"record","created_at":"2026-07-05T05:25:47Z","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":"93f6a0e6c4d97c04250a6da5b0049c61025e12cdc18fd7f3982bf232fbcc33c9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-24T18:59:58Z","title_canon_sha256":"2e0e2ee3c66f35059993d3e4efcc0a96e55f9fcee10c0477ab1225170c17fb74"},"schema_version":"1.0","source":{"id":"2111.12710","kind":"arxiv","version":3}},"canonical_sha256":"d59b287aa8ec951c5f4cab51cf0525f70aa1f363fa14f24cafbc3041a8a905a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d59b287aa8ec951c5f4cab51cf0525f70aa1f363fa14f24cafbc3041a8a905a3","first_computed_at":"2026-07-05T05:25:47.446424Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:25:47.446424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/17hAkQloaysxsWwC5BVaWDrujuAQgUjs1goE6YaQk/WEI9rv8FOhXsKyOF9Pcltm5TLapMXTZmFzG5WFxHLCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:25:47.446931Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.12710","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa9822ffae7e0559a63cebf53c082638fa2fc7a6d404169f896f9cb6a70417f5","sha256:94fee4dea9adb692d0fc7f237fe26bcbf9452089769f5f5c000fef32e9542d78"],"state_sha256":"7e82a27582f9847d82bba157b362482f4404df33aca968c0b6c47542a789a229"}