{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:HAAHC77EXKZRA2AB2MXI5XO5XQ","short_pith_number":"pith:HAAHC77E","canonical_record":{"source":{"id":"2203.00242","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-01T05:34:01Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"70ed288465bd36d1b35b423ba4c6da079fe2d65c82927d8acbf30df5623d7ead","abstract_canon_sha256":"52fd1634491ec0b9e38d1972a048ba62572cae90f572e65f00c89ca054d14750"},"schema_version":"1.0"},"canonical_sha256":"3800717fe4bab3106801d32e8eddddbc181f09a17723429032003a6bf4039900","source":{"kind":"arxiv","id":"2203.00242","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.00242","created_at":"2026-07-05T04:01:15Z"},{"alias_kind":"arxiv_version","alias_value":"2203.00242v1","created_at":"2026-07-05T04:01:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.00242","created_at":"2026-07-05T04:01:15Z"},{"alias_kind":"pith_short_12","alias_value":"HAAHC77EXKZR","created_at":"2026-07-05T04:01:15Z"},{"alias_kind":"pith_short_16","alias_value":"HAAHC77EXKZRA2AB","created_at":"2026-07-05T04:01:15Z"},{"alias_kind":"pith_short_8","alias_value":"HAAHC77E","created_at":"2026-07-05T04:01:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:HAAHC77EXKZRA2AB2MXI5XO5XQ","target":"record","payload":{"canonical_record":{"source":{"id":"2203.00242","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-01T05:34:01Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"70ed288465bd36d1b35b423ba4c6da079fe2d65c82927d8acbf30df5623d7ead","abstract_canon_sha256":"52fd1634491ec0b9e38d1972a048ba62572cae90f572e65f00c89ca054d14750"},"schema_version":"1.0"},"canonical_sha256":"3800717fe4bab3106801d32e8eddddbc181f09a17723429032003a6bf4039900","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:15.452155Z","signature_b64":"qAn1UC4RlPGm68Cjv7DgSb6SM+N5wI4nLDsGFy23iOxnymVmzYWoOGAK95sK0/mQi85E7/5wNvTma44eCRqmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3800717fe4bab3106801d32e8eddddbc181f09a17723429032003a6bf4039900","last_reissued_at":"2026-07-05T04:01:15.451738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:15.451738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.00242","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":"2026-07-05T04:01:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UDKlnjd0+FfOmouPsmjYx8p1rvnxX5AnkRn+eBYoXRhrh5qwtA8amfPdyQe+Crp9/Ul0phQibwkaYBGWdAj6Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:21:58.070054Z"},"content_sha256":"10dc633d348f53f72bb366476bbe3a510061fda0d8c11c9b4505ce984babc30a","schema_version":"1.0","event_id":"sha256:10dc633d348f53f72bb366476bbe3a510061fda0d8c11c9b4505ce984babc30a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:HAAHC77EXKZRA2AB2MXI5XO5XQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Amanpreet Singh, Licheng Yu, Mengjiao Wang, Mingyang Zhou, Ning Zhang, Zhou Yu","submitted_at":"2022-03-01T05:34:01Z","abstract_excerpt":"Vision-and-Language (V+L) pre-training models have achieved tremendous success in recent years on various multi-modal benchmarks. However, the majority of existing models require pre-training on a large set of parallel image-text data, which is costly to collect, compared to image-only or text-only data. In this paper, we explore unsupervised Vision-and-Language pre-training (UVLP) to learn the cross-modal representation from non-parallel image and text datasets. We found two key factors that lead to good unsupervised V+L pre-training without parallel data: (i) joint image-and-text input (ii) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.00242","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/2203.00242/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":"2026-07-05T04:01:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cJ1jL3BuNcAb1LNYOjS/DRO63wpC+Vnoe2YlhdVuHzSepqmz734R4P5xHLxIICamtYJWDTnux0RAzmAc2s9gBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:21:58.070440Z"},"content_sha256":"ccc8c672c2bba62a85a3060dec35140844420e009b5eac53a59ebd392c22a712","schema_version":"1.0","event_id":"sha256:ccc8c672c2bba62a85a3060dec35140844420e009b5eac53a59ebd392c22a712"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HAAHC77EXKZRA2AB2MXI5XO5XQ/bundle.json","state_url":"https://pith.science/pith/HAAHC77EXKZRA2AB2MXI5XO5XQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HAAHC77EXKZRA2AB2MXI5XO5XQ/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":"2026-07-07T13:21:58Z","links":{"resolver":"https://pith.science/pith/HAAHC77EXKZRA2AB2MXI5XO5XQ","bundle":"https://pith.science/pith/HAAHC77EXKZRA2AB2MXI5XO5XQ/bundle.json","state":"https://pith.science/pith/HAAHC77EXKZRA2AB2MXI5XO5XQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HAAHC77EXKZRA2AB2MXI5XO5XQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HAAHC77EXKZRA2AB2MXI5XO5XQ","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":"52fd1634491ec0b9e38d1972a048ba62572cae90f572e65f00c89ca054d14750","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-01T05:34:01Z","title_canon_sha256":"70ed288465bd36d1b35b423ba4c6da079fe2d65c82927d8acbf30df5623d7ead"},"schema_version":"1.0","source":{"id":"2203.00242","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.00242","created_at":"2026-07-05T04:01:15Z"},{"alias_kind":"arxiv_version","alias_value":"2203.00242v1","created_at":"2026-07-05T04:01:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.00242","created_at":"2026-07-05T04:01:15Z"},{"alias_kind":"pith_short_12","alias_value":"HAAHC77EXKZR","created_at":"2026-07-05T04:01:15Z"},{"alias_kind":"pith_short_16","alias_value":"HAAHC77EXKZRA2AB","created_at":"2026-07-05T04:01:15Z"},{"alias_kind":"pith_short_8","alias_value":"HAAHC77E","created_at":"2026-07-05T04:01:15Z"}],"graph_snapshots":[{"event_id":"sha256:ccc8c672c2bba62a85a3060dec35140844420e009b5eac53a59ebd392c22a712","target":"graph","created_at":"2026-07-05T04:01:15Z","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/2203.00242/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-and-Language (V+L) pre-training models have achieved tremendous success in recent years on various multi-modal benchmarks. However, the majority of existing models require pre-training on a large set of parallel image-text data, which is costly to collect, compared to image-only or text-only data. In this paper, we explore unsupervised Vision-and-Language pre-training (UVLP) to learn the cross-modal representation from non-parallel image and text datasets. We found two key factors that lead to good unsupervised V+L pre-training without parallel data: (i) joint image-and-text input (ii) ","authors_text":"Amanpreet Singh, Licheng Yu, Mengjiao Wang, Mingyang Zhou, Ning Zhang, Zhou Yu","cross_cats":["cs.AI","cs.CL","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-01T05:34:01Z","title":"Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.00242","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":"sha256:10dc633d348f53f72bb366476bbe3a510061fda0d8c11c9b4505ce984babc30a","target":"record","created_at":"2026-07-05T04:01:15Z","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":"52fd1634491ec0b9e38d1972a048ba62572cae90f572e65f00c89ca054d14750","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-01T05:34:01Z","title_canon_sha256":"70ed288465bd36d1b35b423ba4c6da079fe2d65c82927d8acbf30df5623d7ead"},"schema_version":"1.0","source":{"id":"2203.00242","kind":"arxiv","version":1}},"canonical_sha256":"3800717fe4bab3106801d32e8eddddbc181f09a17723429032003a6bf4039900","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3800717fe4bab3106801d32e8eddddbc181f09a17723429032003a6bf4039900","first_computed_at":"2026-07-05T04:01:15.451738Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:01:15.451738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qAn1UC4RlPGm68Cjv7DgSb6SM+N5wI4nLDsGFy23iOxnymVmzYWoOGAK95sK0/mQi85E7/5wNvTma44eCRqmDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:01:15.452155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.00242","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10dc633d348f53f72bb366476bbe3a510061fda0d8c11c9b4505ce984babc30a","sha256:ccc8c672c2bba62a85a3060dec35140844420e009b5eac53a59ebd392c22a712"],"state_sha256":"336b75fbddfb4ff0b39478fa1956972d74c399a76f7422363d01e0195ecdf297"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Unzxj9fdDQvpXNpLnH19oAOCoVK2tyGlkbkU11JM0m7FINy99i46r+JhUW+FD2ULGLBEgLZUCtMwpVgii49jCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:21:58.072585Z","bundle_sha256":"10cec314062098705df5b0cf3fa672da3010161f2072e36154fece5801eca4d8"}}