{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2XGIQN5M4YBI5VLC2XPO4CFXQ3","short_pith_number":"pith:2XGIQN5M","canonical_record":{"source":{"id":"2210.15110","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-27T01:44:08Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"41aef1bf7e230f4733e9149cbcf20c79ce75513313f1bab636a1209daf161d91","abstract_canon_sha256":"15846bb55f942ee0ccfc9935f172894c300b3fcb67bb2d669aee22f9759d6439"},"schema_version":"1.0"},"canonical_sha256":"d5cc8837ace6028ed562d5deee08b786f490dce4989f4e9b47e621f51ddb0090","source":{"kind":"arxiv","id":"2210.15110","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.15110","created_at":"2026-07-05T06:17:26Z"},{"alias_kind":"arxiv_version","alias_value":"2210.15110v1","created_at":"2026-07-05T06:17:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15110","created_at":"2026-07-05T06:17:26Z"},{"alias_kind":"pith_short_12","alias_value":"2XGIQN5M4YBI","created_at":"2026-07-05T06:17:26Z"},{"alias_kind":"pith_short_16","alias_value":"2XGIQN5M4YBI5VLC","created_at":"2026-07-05T06:17:26Z"},{"alias_kind":"pith_short_8","alias_value":"2XGIQN5M","created_at":"2026-07-05T06:17:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2XGIQN5M4YBI5VLC2XPO4CFXQ3","target":"record","payload":{"canonical_record":{"source":{"id":"2210.15110","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-27T01:44:08Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"41aef1bf7e230f4733e9149cbcf20c79ce75513313f1bab636a1209daf161d91","abstract_canon_sha256":"15846bb55f942ee0ccfc9935f172894c300b3fcb67bb2d669aee22f9759d6439"},"schema_version":"1.0"},"canonical_sha256":"d5cc8837ace6028ed562d5deee08b786f490dce4989f4e9b47e621f51ddb0090","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:26.724584Z","signature_b64":"jgi1VzN71noyC8mRtIKkDArITK2H5gLe3tgrBLMRUB6X1DMROAB5F3s8pO8orBfbWaLYOwy1Q+IS7UiIev/bAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5cc8837ace6028ed562d5deee08b786f490dce4989f4e9b47e621f51ddb0090","last_reissued_at":"2026-07-05T06:17:26.724022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:26.724022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.15110","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:17:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CGra8Mv7RllTsg4PzvKG+ujXSFCjrHyIz5PV2oksdeJwEcEqtRGNYy0v28aaeCAlsBVQ7nRwiSIq48IlnsO4Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:45:38.508294Z"},"content_sha256":"c6ad8181455e92b22f4172fc1d1500384f3dbb1e95e19273438d17362e997cbb","schema_version":"1.0","event_id":"sha256:c6ad8181455e92b22f4172fc1d1500384f3dbb1e95e19273438d17362e997cbb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2XGIQN5M4YBI5VLC2XPO4CFXQ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Masked Vision-Language Transformer in Fashion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Christos Sakaridis, Dehong Gao, Deng-Ping Fan, Ge-Peng Ji, Luc Van Gool, Mingcheng Zhuge","submitted_at":"2022-10-27T01:44:08Z","abstract_excerpt":"We present a masked vision-language transformer (MVLT) for fashion-specific multi-modal representation. Technically, we simply utilize vision transformer architecture for replacing the BERT in the pre-training model, making MVLT the first end-to-end framework for the fashion domain. Besides, we designed masked image reconstruction (MIR) for a fine-grained understanding of fashion. MVLT is an extensible and convenient architecture that admits raw multi-modal inputs without extra pre-processing models (e.g., ResNet), implicitly modeling the vision-language alignments. More importantly, MVLT can "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15110","kind":"arxiv","version":1},"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/2210.15110/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":"2026-07-05T06:17:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vY1rQ81mbkOyynpDUhSGZ8e6YBN9Z+rdt5j9LsFQPXq+atalmAhHE4SkjppTDKwug6NMjBlBcj0y9+sqGBIACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:45:38.508691Z"},"content_sha256":"9c9f49b17cbc70567d6d825467677629065fd9cf21f307647f54b946ae703d8a","schema_version":"1.0","event_id":"sha256:9c9f49b17cbc70567d6d825467677629065fd9cf21f307647f54b946ae703d8a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2XGIQN5M4YBI5VLC2XPO4CFXQ3/bundle.json","state_url":"https://pith.science/pith/2XGIQN5M4YBI5VLC2XPO4CFXQ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2XGIQN5M4YBI5VLC2XPO4CFXQ3/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":"2026-07-07T09:45:38Z","links":{"resolver":"https://pith.science/pith/2XGIQN5M4YBI5VLC2XPO4CFXQ3","bundle":"https://pith.science/pith/2XGIQN5M4YBI5VLC2XPO4CFXQ3/bundle.json","state":"https://pith.science/pith/2XGIQN5M4YBI5VLC2XPO4CFXQ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2XGIQN5M4YBI5VLC2XPO4CFXQ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2XGIQN5M4YBI5VLC2XPO4CFXQ3","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":"15846bb55f942ee0ccfc9935f172894c300b3fcb67bb2d669aee22f9759d6439","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-27T01:44:08Z","title_canon_sha256":"41aef1bf7e230f4733e9149cbcf20c79ce75513313f1bab636a1209daf161d91"},"schema_version":"1.0","source":{"id":"2210.15110","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.15110","created_at":"2026-07-05T06:17:26Z"},{"alias_kind":"arxiv_version","alias_value":"2210.15110v1","created_at":"2026-07-05T06:17:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15110","created_at":"2026-07-05T06:17:26Z"},{"alias_kind":"pith_short_12","alias_value":"2XGIQN5M4YBI","created_at":"2026-07-05T06:17:26Z"},{"alias_kind":"pith_short_16","alias_value":"2XGIQN5M4YBI5VLC","created_at":"2026-07-05T06:17:26Z"},{"alias_kind":"pith_short_8","alias_value":"2XGIQN5M","created_at":"2026-07-05T06:17:26Z"}],"graph_snapshots":[{"event_id":"sha256:9c9f49b17cbc70567d6d825467677629065fd9cf21f307647f54b946ae703d8a","target":"graph","created_at":"2026-07-05T06:17:26Z","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/2210.15110/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a masked vision-language transformer (MVLT) for fashion-specific multi-modal representation. Technically, we simply utilize vision transformer architecture for replacing the BERT in the pre-training model, making MVLT the first end-to-end framework for the fashion domain. Besides, we designed masked image reconstruction (MIR) for a fine-grained understanding of fashion. MVLT is an extensible and convenient architecture that admits raw multi-modal inputs without extra pre-processing models (e.g., ResNet), implicitly modeling the vision-language alignments. More importantly, MVLT can ","authors_text":"Christos Sakaridis, Dehong Gao, Deng-Ping Fan, Ge-Peng Ji, Luc Van Gool, Mingcheng Zhuge","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-27T01:44:08Z","title":"Masked Vision-Language Transformer in Fashion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15110","kind":"arxiv","version":1},"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:c6ad8181455e92b22f4172fc1d1500384f3dbb1e95e19273438d17362e997cbb","target":"record","created_at":"2026-07-05T06:17:26Z","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":"15846bb55f942ee0ccfc9935f172894c300b3fcb67bb2d669aee22f9759d6439","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-27T01:44:08Z","title_canon_sha256":"41aef1bf7e230f4733e9149cbcf20c79ce75513313f1bab636a1209daf161d91"},"schema_version":"1.0","source":{"id":"2210.15110","kind":"arxiv","version":1}},"canonical_sha256":"d5cc8837ace6028ed562d5deee08b786f490dce4989f4e9b47e621f51ddb0090","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5cc8837ace6028ed562d5deee08b786f490dce4989f4e9b47e621f51ddb0090","first_computed_at":"2026-07-05T06:17:26.724022Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:26.724022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jgi1VzN71noyC8mRtIKkDArITK2H5gLe3tgrBLMRUB6X1DMROAB5F3s8pO8orBfbWaLYOwy1Q+IS7UiIev/bAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:26.724584Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.15110","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6ad8181455e92b22f4172fc1d1500384f3dbb1e95e19273438d17362e997cbb","sha256:9c9f49b17cbc70567d6d825467677629065fd9cf21f307647f54b946ae703d8a"],"state_sha256":"8e9dc025eb2f434fa47ef22393e08c01aa195d72addbc12e7f736c61195a017b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qdr0Kk3dvJ8pHAtxPTEOLmJYxviGScQaEIqZZTfDLJvk88OqJDAZUL/JSrm5NABRFSpkBpHPAF71jviux9hlBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:45:38.510661Z","bundle_sha256":"6e2160665bc411a24c48810caf0212e6d1bbbac811e7d39e3f5677d5e3db2b9c"}}