{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:NMJZOMG5VSPYCH7RG466IBYJTL","short_pith_number":"pith:NMJZOMG5","canonical_record":{"source":{"id":"2010.12831","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T08:17:54Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"073271b293c2ae178f4c6763fc7bea539c783c7cb4424cf1e699ca7f8facc250","abstract_canon_sha256":"0638d898755583000823d4bfffbd3df711de54be44c66a48760be974e8c649e3"},"schema_version":"1.0"},"canonical_sha256":"6b139730ddac9f811ff1373de407099ad4fb8cc24b2830287a8c04e779adae22","source":{"kind":"arxiv","id":"2010.12831","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12831","created_at":"2026-07-05T02:31:00Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12831v2","created_at":"2026-07-05T02:31:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12831","created_at":"2026-07-05T02:31:00Z"},{"alias_kind":"pith_short_12","alias_value":"NMJZOMG5VSPY","created_at":"2026-07-05T02:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"NMJZOMG5VSPYCH7R","created_at":"2026-07-05T02:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"NMJZOMG5","created_at":"2026-07-05T02:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:NMJZOMG5VSPYCH7RG466IBYJTL","target":"record","payload":{"canonical_record":{"source":{"id":"2010.12831","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T08:17:54Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"073271b293c2ae178f4c6763fc7bea539c783c7cb4424cf1e699ca7f8facc250","abstract_canon_sha256":"0638d898755583000823d4bfffbd3df711de54be44c66a48760be974e8c649e3"},"schema_version":"1.0"},"canonical_sha256":"6b139730ddac9f811ff1373de407099ad4fb8cc24b2830287a8c04e779adae22","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:00.801710Z","signature_b64":"WX8u6b4MJb5otDHJQLkHypTPalH2XOwYlmZAWfo8QA/pPIyQOZpTo45iiaAuOpZ7+vpAKGHF10G+OgraYE/pDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b139730ddac9f811ff1373de407099ad4fb8cc24b2830287a8c04e779adae22","last_reissued_at":"2026-07-05T02:31:00.801209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:00.801209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.12831","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:31:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FPR0vGNDF/+XDskiGKwE+ugj18n97bAfMTS4NTFrVD5FX2LivljhnUbGyhNznWXeqco6bM2sMQe1ieeUkZZDAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:40:43.412682Z"},"content_sha256":"7db69197ccb0b1f370293070e10747b0ac732a05ed830ece2c220116f7b73fa2","schema_version":"1.0","event_id":"sha256:7db69197ccb0b1f370293070e10747b0ac732a05ed830ece2c220116f7b73fa2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:NMJZOMG5VSPYCH7RG466IBYJTL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alireza Zareian, Haoxuan You, Kai-Wei Chang, Liunian Harold Li, Shih-Fu Chang, Zhecan Wang","submitted_at":"2020-10-24T08:17:54Z","abstract_excerpt":"Pre-trained contextual vision-and-language (V&L) models have achieved impressive performance on various benchmarks. However, existing models require a large amount of parallel image-caption data for pre-training. Such data are costly to collect and require cumbersome curation. Inspired by unsupervised machine translation, we investigate if a strong V&L representation model can be learned through unsupervised pre-training without image-caption corpora. In particular, we propose to conduct ``mask-and-predict'' pre-training on text-only and image-only corpora and introduce the object tags detecte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12831","kind":"arxiv","version":2},"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/2010.12831/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":"2026-07-05T02:31:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"joALEhMyAS5OW4V6PGaLWbckpurAolsPENW0Voxv4VgFPUBZfg7biDFJwjVINuH8vItqmcixu8Hk43pVWj7zAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:40:43.413337Z"},"content_sha256":"25b0b15cef78b7eb75af79b1ff6ed28a93f7e77165991195358aade00f8a1cb5","schema_version":"1.0","event_id":"sha256:25b0b15cef78b7eb75af79b1ff6ed28a93f7e77165991195358aade00f8a1cb5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NMJZOMG5VSPYCH7RG466IBYJTL/bundle.json","state_url":"https://pith.science/pith/NMJZOMG5VSPYCH7RG466IBYJTL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NMJZOMG5VSPYCH7RG466IBYJTL/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":"2026-07-07T02:40:43Z","links":{"resolver":"https://pith.science/pith/NMJZOMG5VSPYCH7RG466IBYJTL","bundle":"https://pith.science/pith/NMJZOMG5VSPYCH7RG466IBYJTL/bundle.json","state":"https://pith.science/pith/NMJZOMG5VSPYCH7RG466IBYJTL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NMJZOMG5VSPYCH7RG466IBYJTL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:NMJZOMG5VSPYCH7RG466IBYJTL","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":"0638d898755583000823d4bfffbd3df711de54be44c66a48760be974e8c649e3","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T08:17:54Z","title_canon_sha256":"073271b293c2ae178f4c6763fc7bea539c783c7cb4424cf1e699ca7f8facc250"},"schema_version":"1.0","source":{"id":"2010.12831","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12831","created_at":"2026-07-05T02:31:00Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12831v2","created_at":"2026-07-05T02:31:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12831","created_at":"2026-07-05T02:31:00Z"},{"alias_kind":"pith_short_12","alias_value":"NMJZOMG5VSPY","created_at":"2026-07-05T02:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"NMJZOMG5VSPYCH7R","created_at":"2026-07-05T02:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"NMJZOMG5","created_at":"2026-07-05T02:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:25b0b15cef78b7eb75af79b1ff6ed28a93f7e77165991195358aade00f8a1cb5","target":"graph","created_at":"2026-07-05T02:31:00Z","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/2010.12831/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained contextual vision-and-language (V&L) models have achieved impressive performance on various benchmarks. However, existing models require a large amount of parallel image-caption data for pre-training. Such data are costly to collect and require cumbersome curation. Inspired by unsupervised machine translation, we investigate if a strong V&L representation model can be learned through unsupervised pre-training without image-caption corpora. In particular, we propose to conduct ``mask-and-predict'' pre-training on text-only and image-only corpora and introduce the object tags detecte","authors_text":"Alireza Zareian, Haoxuan You, Kai-Wei Chang, Liunian Harold Li, Shih-Fu Chang, Zhecan Wang","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T08:17:54Z","title":"Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12831","kind":"arxiv","version":2},"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":"sha256:7db69197ccb0b1f370293070e10747b0ac732a05ed830ece2c220116f7b73fa2","target":"record","created_at":"2026-07-05T02:31:00Z","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":"0638d898755583000823d4bfffbd3df711de54be44c66a48760be974e8c649e3","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T08:17:54Z","title_canon_sha256":"073271b293c2ae178f4c6763fc7bea539c783c7cb4424cf1e699ca7f8facc250"},"schema_version":"1.0","source":{"id":"2010.12831","kind":"arxiv","version":2}},"canonical_sha256":"6b139730ddac9f811ff1373de407099ad4fb8cc24b2830287a8c04e779adae22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b139730ddac9f811ff1373de407099ad4fb8cc24b2830287a8c04e779adae22","first_computed_at":"2026-07-05T02:31:00.801209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:31:00.801209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WX8u6b4MJb5otDHJQLkHypTPalH2XOwYlmZAWfo8QA/pPIyQOZpTo45iiaAuOpZ7+vpAKGHF10G+OgraYE/pDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:31:00.801710Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.12831","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7db69197ccb0b1f370293070e10747b0ac732a05ed830ece2c220116f7b73fa2","sha256:25b0b15cef78b7eb75af79b1ff6ed28a93f7e77165991195358aade00f8a1cb5"],"state_sha256":"ff9366cea568f96f8d41a1226aea52159ccaeb756774ec5bbc85c4e42c23908a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KjxRxkirENLLbk1MvMevEp+c9mjGT3hVBMSj0J9YrAa2HyVScZH3FEWZhuZIBRPJyRBXj3tuRbuQ1HINnZrmBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T02:40:43.417271Z","bundle_sha256":"294c506bb82c00f80b67fe58e17a2250d67867523b570b8c4fca2968bbe56db6"}}