{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YPQL3SYIHV4HCRT2QRTOJNVAZQ","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":"819fd4e8442df1a1dae2ebe10ac27f0fa22cf3933735b75190b2bda80c7773c3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-30T06:53:00Z","title_canon_sha256":"bde37ebb0839402a1c30d3330c7fc0345b37e28e63870211fe6ace10673cfbf5"},"schema_version":"1.0","source":{"id":"2103.16110","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.16110","created_at":"2026-07-05T02:32:16Z"},{"alias_kind":"arxiv_version","alias_value":"2103.16110v3","created_at":"2026-07-05T02:32:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.16110","created_at":"2026-07-05T02:32:16Z"},{"alias_kind":"pith_short_12","alias_value":"YPQL3SYIHV4H","created_at":"2026-07-05T02:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"YPQL3SYIHV4HCRT2","created_at":"2026-07-05T02:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"YPQL3SYI","created_at":"2026-07-05T02:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:61cc3f0d1ea2cac39085e1513317aac51a1feae06893fae057805b9038180b78","target":"graph","created_at":"2026-07-05T02:32:16Z","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/2103.16110/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a new vision-language (VL) pre-training model dubbed Kaleido-BERT, which introduces a novel kaleido strategy for fashion cross-modality representations from transformers. In contrast to random masking strategy of recent VL models, we design alignment guided masking to jointly focus more on image-text semantic relations. To this end, we carry out five novel tasks, i.e., rotation, jigsaw, camouflage, grey-to-color, and blank-to-color for self-supervised VL pre-training at patches of different scale. Kaleido-BERT is conceptually simple and easy to extend to the existing BERT framework,","authors_text":"Ben Chen, Dehong Gao, Deng-Ping Fan, Haoming Zhou, Linbo Jin, Ling Shao, Mingchen Zhuge, Minghui Qiu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-30T06:53:00Z","title":"Kaleido-BERT: Vision-Language Pre-training on Fashion Domain"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.16110","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:f76afe97ceaab5fd87b0335198ec61b82a646df86fa2b7c63de2a6b8943081b8","target":"record","created_at":"2026-07-05T02:32:16Z","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":"819fd4e8442df1a1dae2ebe10ac27f0fa22cf3933735b75190b2bda80c7773c3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-30T06:53:00Z","title_canon_sha256":"bde37ebb0839402a1c30d3330c7fc0345b37e28e63870211fe6ace10673cfbf5"},"schema_version":"1.0","source":{"id":"2103.16110","kind":"arxiv","version":3}},"canonical_sha256":"c3e0bdcb083d7871467a8466e4b6a0cc219b8a53a7388ec62be28e7f487f558b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3e0bdcb083d7871467a8466e4b6a0cc219b8a53a7388ec62be28e7f487f558b","first_computed_at":"2026-07-05T02:32:16.798813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:32:16.798813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q6u70pUBJ+/YfOUfiiapguOfpKngPItdgJs5UIjux6BcfYQqQbvtzaPYWUnrgWNpRcadzoUbvNvk0bKrgOOsDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:32:16.799230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.16110","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f76afe97ceaab5fd87b0335198ec61b82a646df86fa2b7c63de2a6b8943081b8","sha256:61cc3f0d1ea2cac39085e1513317aac51a1feae06893fae057805b9038180b78"],"state_sha256":"d17277af074618a4cb381b13815249752cbae123edaf35df9a97afb7995f951c"}