{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:VLAKP62BQYZ6X3WOZK6IWKWIKH","short_pith_number":"pith:VLAKP62B","canonical_record":{"source":{"id":"2204.12408","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-26T16:06:31Z","cross_cats_sorted":[],"title_canon_sha256":"ef12fac3c7fe7b513fd8092416fbd44ed3ad16760417b92e00ca7a454841feba","abstract_canon_sha256":"0889d374b7f6ba2cd28a738833802833f7303fbc62b8c5cb05da1068db303833"},"schema_version":"1.0"},"canonical_sha256":"aac0a7fb418633ebeececabc8b2ac851c669ab937d23e7f70f937573810a888a","source":{"kind":"arxiv","id":"2204.12408","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.12408","created_at":"2026-07-05T04:17:47Z"},{"alias_kind":"arxiv_version","alias_value":"2204.12408v1","created_at":"2026-07-05T04:17:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12408","created_at":"2026-07-05T04:17:47Z"},{"alias_kind":"pith_short_12","alias_value":"VLAKP62BQYZ6","created_at":"2026-07-05T04:17:47Z"},{"alias_kind":"pith_short_16","alias_value":"VLAKP62BQYZ6X3WO","created_at":"2026-07-05T04:17:47Z"},{"alias_kind":"pith_short_8","alias_value":"VLAKP62B","created_at":"2026-07-05T04:17:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:VLAKP62BQYZ6X3WOZK6IWKWIKH","target":"record","payload":{"canonical_record":{"source":{"id":"2204.12408","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-26T16:06:31Z","cross_cats_sorted":[],"title_canon_sha256":"ef12fac3c7fe7b513fd8092416fbd44ed3ad16760417b92e00ca7a454841feba","abstract_canon_sha256":"0889d374b7f6ba2cd28a738833802833f7303fbc62b8c5cb05da1068db303833"},"schema_version":"1.0"},"canonical_sha256":"aac0a7fb418633ebeececabc8b2ac851c669ab937d23e7f70f937573810a888a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:47.941574Z","signature_b64":"k88l3Jir39RtL6+LHyUMplzK9AG4f7zglFrVC3bByrrVWj1aIHioZFpYgdQCa4jRt5OkcLhV+pFOgq5kCrm9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aac0a7fb418633ebeececabc8b2ac851c669ab937d23e7f70f937573810a888a","last_reissued_at":"2026-07-05T04:17:47.941134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:47.941134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.12408","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":"2026-07-05T04:17:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UBRr5v4CjF76sUwkLiwQIOk2fZgK9NFRVRE05diYezOvbYRzGyxvDL2/MohY7GOFGXLSUg8osekau542WE+sDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T02:08:08.714653Z"},"content_sha256":"65103f9d65075e2168de35fe6080db44cb07a707393100b498c2dda576d9e213","schema_version":"1.0","event_id":"sha256:65103f9d65075e2168de35fe6080db44cb07a707393100b498c2dda576d9e213"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:VLAKP62BQYZ6X3WOZK6IWKWIKH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Jinpeng Wang, Jianping Wu, Ping Luo, Xiaohu Qie, Xihui Liu, Ying Shan, Yixiao Ge, Yuying Ge","submitted_at":"2022-04-26T16:06:31Z","abstract_excerpt":"Dominant pre-training work for video-text retrieval mainly adopt the \"dual-encoder\" architectures to enable efficient retrieval, where two separate encoders are used to contrast global video and text representations, but ignore detailed local semantics. The recent success of image BERT pre-training with masked visual modeling that promotes the learning of local visual context, motivates a possible solution to address the above limitation. In this work, we for the first time investigate masked visual modeling in video-text pre-training with the \"dual-encoder\" architecture. We perform Masked vis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12408","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/2204.12408/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":"2026-07-05T04:17:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oqfQpbHzPTzeHh8q6LMcbzocJg/DCbmg2GYWQlnYwjg7YmKSPQp3g75SP+DQ2ErHb7SfuwK8FVpvJAzBlkKLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T02:08:08.715116Z"},"content_sha256":"1c40c0b66e31836e3b7dd7a1252160e722b5220d463d463a1716a14eb18da75e","schema_version":"1.0","event_id":"sha256:1c40c0b66e31836e3b7dd7a1252160e722b5220d463d463a1716a14eb18da75e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VLAKP62BQYZ6X3WOZK6IWKWIKH/bundle.json","state_url":"https://pith.science/pith/VLAKP62BQYZ6X3WOZK6IWKWIKH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VLAKP62BQYZ6X3WOZK6IWKWIKH/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":"2026-08-23T02:08:08Z","links":{"resolver":"https://pith.science/pith/VLAKP62BQYZ6X3WOZK6IWKWIKH","bundle":"https://pith.science/pith/VLAKP62BQYZ6X3WOZK6IWKWIKH/bundle.json","state":"https://pith.science/pith/VLAKP62BQYZ6X3WOZK6IWKWIKH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VLAKP62BQYZ6X3WOZK6IWKWIKH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VLAKP62BQYZ6X3WOZK6IWKWIKH","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":"0889d374b7f6ba2cd28a738833802833f7303fbc62b8c5cb05da1068db303833","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-26T16:06:31Z","title_canon_sha256":"ef12fac3c7fe7b513fd8092416fbd44ed3ad16760417b92e00ca7a454841feba"},"schema_version":"1.0","source":{"id":"2204.12408","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.12408","created_at":"2026-07-05T04:17:47Z"},{"alias_kind":"arxiv_version","alias_value":"2204.12408v1","created_at":"2026-07-05T04:17:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12408","created_at":"2026-07-05T04:17:47Z"},{"alias_kind":"pith_short_12","alias_value":"VLAKP62BQYZ6","created_at":"2026-07-05T04:17:47Z"},{"alias_kind":"pith_short_16","alias_value":"VLAKP62BQYZ6X3WO","created_at":"2026-07-05T04:17:47Z"},{"alias_kind":"pith_short_8","alias_value":"VLAKP62B","created_at":"2026-07-05T04:17:47Z"}],"graph_snapshots":[{"event_id":"sha256:1c40c0b66e31836e3b7dd7a1252160e722b5220d463d463a1716a14eb18da75e","target":"graph","created_at":"2026-07-05T04:17:47Z","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/2204.12408/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dominant pre-training work for video-text retrieval mainly adopt the \"dual-encoder\" architectures to enable efficient retrieval, where two separate encoders are used to contrast global video and text representations, but ignore detailed local semantics. The recent success of image BERT pre-training with masked visual modeling that promotes the learning of local visual context, motivates a possible solution to address the above limitation. In this work, we for the first time investigate masked visual modeling in video-text pre-training with the \"dual-encoder\" architecture. We perform Masked vis","authors_text":"Alex Jinpeng Wang, Jianping Wu, Ping Luo, Xiaohu Qie, Xihui Liu, Ying Shan, Yixiao Ge, Yuying Ge","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-26T16:06:31Z","title":"MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12408","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":"sha256:65103f9d65075e2168de35fe6080db44cb07a707393100b498c2dda576d9e213","target":"record","created_at":"2026-07-05T04:17:47Z","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":"0889d374b7f6ba2cd28a738833802833f7303fbc62b8c5cb05da1068db303833","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-26T16:06:31Z","title_canon_sha256":"ef12fac3c7fe7b513fd8092416fbd44ed3ad16760417b92e00ca7a454841feba"},"schema_version":"1.0","source":{"id":"2204.12408","kind":"arxiv","version":1}},"canonical_sha256":"aac0a7fb418633ebeececabc8b2ac851c669ab937d23e7f70f937573810a888a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aac0a7fb418633ebeececabc8b2ac851c669ab937d23e7f70f937573810a888a","first_computed_at":"2026-07-05T04:17:47.941134Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:47.941134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k88l3Jir39RtL6+LHyUMplzK9AG4f7zglFrVC3bByrrVWj1aIHioZFpYgdQCa4jRt5OkcLhV+pFOgq5kCrm9Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:47.941574Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.12408","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65103f9d65075e2168de35fe6080db44cb07a707393100b498c2dda576d9e213","sha256:1c40c0b66e31836e3b7dd7a1252160e722b5220d463d463a1716a14eb18da75e"],"state_sha256":"565c23b8b9277c48336a41de9c16ee88ff3c6df44f219a0f1eacd0bf0e6fbcbe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a+h2gJgUAB6ZALUmybsnHxsZY5QAX0nnM3eNbZ20NBI8mWFsMpVucfs5FtDJQ9JXApc3a9Fy+vqcctcCwqrbAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T02:08:08.718580Z","bundle_sha256":"db5b16093f7a5f59106a1b3ee0bb90b5ef745cef3b4626172f8dc7a907ac8bcf"}}