{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2YXYLPCCYBMJXO4XMSZDHJ7JT4","short_pith_number":"pith:2YXYLPCC","canonical_record":{"source":{"id":"2206.01127","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-02T16:14:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9ef19ff3a59679e11e5ea56400679745af3449d1c3eec34790136761409476de","abstract_canon_sha256":"5246154307357154a71adf795f573162fb62427f06f8fec6948294372acdf26e"},"schema_version":"1.0"},"canonical_sha256":"d62f85bc42c0589bbb9764b233a7e99f0ae50b89e2c6d8cb3a3df33eec64035c","source":{"kind":"arxiv","id":"2206.01127","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.01127","created_at":"2026-07-05T04:54:21Z"},{"alias_kind":"arxiv_version","alias_value":"2206.01127v2","created_at":"2026-07-05T04:54:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01127","created_at":"2026-07-05T04:54:21Z"},{"alias_kind":"pith_short_12","alias_value":"2YXYLPCCYBMJ","created_at":"2026-07-05T04:54:21Z"},{"alias_kind":"pith_short_16","alias_value":"2YXYLPCCYBMJXO4X","created_at":"2026-07-05T04:54:21Z"},{"alias_kind":"pith_short_8","alias_value":"2YXYLPCC","created_at":"2026-07-05T04:54:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2YXYLPCCYBMJXO4XMSZDHJ7JT4","target":"record","payload":{"canonical_record":{"source":{"id":"2206.01127","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-02T16:14:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9ef19ff3a59679e11e5ea56400679745af3449d1c3eec34790136761409476de","abstract_canon_sha256":"5246154307357154a71adf795f573162fb62427f06f8fec6948294372acdf26e"},"schema_version":"1.0"},"canonical_sha256":"d62f85bc42c0589bbb9764b233a7e99f0ae50b89e2c6d8cb3a3df33eec64035c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:54:21.303570Z","signature_b64":"wIr6snQR+QTNPUiy+asVyf0z6TqhE1JmJ8mARtLPiWpYD6xIPUpFjsx1iDo8WNlDE8Q72Qn82HNFNrd4SSY5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d62f85bc42c0589bbb9764b233a7e99f0ae50b89e2c6d8cb3a3df33eec64035c","last_reissued_at":"2026-07-05T04:54:21.303130Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:54:21.303130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.01127","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":"2026-07-05T04:54:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AQeoEHbLBl44aUs4X+LXlB2thSxV+TC39gWN2upPxvQGeH/wJdO/4srB+Pc2AM4zei8JSZAt0cg2iXAMjevNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:25:19.437886Z"},"content_sha256":"19ff7f4381a72620b263fb94dfb4385dd2868e40e4105d0225901777ca65d809","schema_version":"1.0","event_id":"sha256:19ff7f4381a72620b263fb94dfb4385dd2868e40e4105d0225901777ca65d809"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2YXYLPCCYBMJXO4XMSZDHJ7JT4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VL-BEiT: Generative Vision-Language Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Furu Wei, Hangbo Bao, Li Dong, Wenhui Wang","submitted_at":"2022-06-02T16:14:19Z","abstract_excerpt":"We introduce a vision-language foundation model called VL-BEiT, which is a bidirectional multimodal Transformer learned by generative pretraining. Our minimalist solution conducts masked prediction on both monomodal and multimodal data with a shared Transformer. Specifically, we perform masked vision-language modeling on image-text pairs, masked language modeling on texts, and masked image modeling on images. VL-BEiT is learned from scratch with one unified pretraining task, one shared backbone, and one-stage training. Our method is conceptually simple and empirically effective. Experimental r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01127","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/2206.01127/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":"2026-07-05T04:54:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nxKSY/00ajbSlRFJzwCWXK+PaY/odUyGyOnEja9YDNV6acvDGDWzejEGHAg33W8YGMGYUbuLriwWWNlMa1hCCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:25:19.438273Z"},"content_sha256":"810dbd82bd3e2bb3d12f1a0fc6b7b5b747ecae713c0a077c349b736b882a1f6e","schema_version":"1.0","event_id":"sha256:810dbd82bd3e2bb3d12f1a0fc6b7b5b747ecae713c0a077c349b736b882a1f6e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2YXYLPCCYBMJXO4XMSZDHJ7JT4/bundle.json","state_url":"https://pith.science/pith/2YXYLPCCYBMJXO4XMSZDHJ7JT4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2YXYLPCCYBMJXO4XMSZDHJ7JT4/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":"2026-07-06T20:25:19Z","links":{"resolver":"https://pith.science/pith/2YXYLPCCYBMJXO4XMSZDHJ7JT4","bundle":"https://pith.science/pith/2YXYLPCCYBMJXO4XMSZDHJ7JT4/bundle.json","state":"https://pith.science/pith/2YXYLPCCYBMJXO4XMSZDHJ7JT4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2YXYLPCCYBMJXO4XMSZDHJ7JT4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2YXYLPCCYBMJXO4XMSZDHJ7JT4","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":"5246154307357154a71adf795f573162fb62427f06f8fec6948294372acdf26e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-02T16:14:19Z","title_canon_sha256":"9ef19ff3a59679e11e5ea56400679745af3449d1c3eec34790136761409476de"},"schema_version":"1.0","source":{"id":"2206.01127","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.01127","created_at":"2026-07-05T04:54:21Z"},{"alias_kind":"arxiv_version","alias_value":"2206.01127v2","created_at":"2026-07-05T04:54:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01127","created_at":"2026-07-05T04:54:21Z"},{"alias_kind":"pith_short_12","alias_value":"2YXYLPCCYBMJ","created_at":"2026-07-05T04:54:21Z"},{"alias_kind":"pith_short_16","alias_value":"2YXYLPCCYBMJXO4X","created_at":"2026-07-05T04:54:21Z"},{"alias_kind":"pith_short_8","alias_value":"2YXYLPCC","created_at":"2026-07-05T04:54:21Z"}],"graph_snapshots":[{"event_id":"sha256:810dbd82bd3e2bb3d12f1a0fc6b7b5b747ecae713c0a077c349b736b882a1f6e","target":"graph","created_at":"2026-07-05T04:54:21Z","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/2206.01127/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a vision-language foundation model called VL-BEiT, which is a bidirectional multimodal Transformer learned by generative pretraining. Our minimalist solution conducts masked prediction on both monomodal and multimodal data with a shared Transformer. Specifically, we perform masked vision-language modeling on image-text pairs, masked language modeling on texts, and masked image modeling on images. VL-BEiT is learned from scratch with one unified pretraining task, one shared backbone, and one-stage training. Our method is conceptually simple and empirically effective. Experimental r","authors_text":"Furu Wei, Hangbo Bao, Li Dong, Wenhui Wang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-02T16:14:19Z","title":"VL-BEiT: Generative Vision-Language Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01127","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":"sha256:19ff7f4381a72620b263fb94dfb4385dd2868e40e4105d0225901777ca65d809","target":"record","created_at":"2026-07-05T04:54:21Z","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":"5246154307357154a71adf795f573162fb62427f06f8fec6948294372acdf26e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-02T16:14:19Z","title_canon_sha256":"9ef19ff3a59679e11e5ea56400679745af3449d1c3eec34790136761409476de"},"schema_version":"1.0","source":{"id":"2206.01127","kind":"arxiv","version":2}},"canonical_sha256":"d62f85bc42c0589bbb9764b233a7e99f0ae50b89e2c6d8cb3a3df33eec64035c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d62f85bc42c0589bbb9764b233a7e99f0ae50b89e2c6d8cb3a3df33eec64035c","first_computed_at":"2026-07-05T04:54:21.303130Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:54:21.303130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wIr6snQR+QTNPUiy+asVyf0z6TqhE1JmJ8mARtLPiWpYD6xIPUpFjsx1iDo8WNlDE8Q72Qn82HNFNrd4SSY5AA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:54:21.303570Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.01127","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19ff7f4381a72620b263fb94dfb4385dd2868e40e4105d0225901777ca65d809","sha256:810dbd82bd3e2bb3d12f1a0fc6b7b5b747ecae713c0a077c349b736b882a1f6e"],"state_sha256":"2d24e5c2ec62f806433a7387edb84556ada708ec2c1bac7f970d172021af45b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DREwUpYLeEwqsbHQIL3B/C+mrygEC5p6XTGVuzqo7XkP4AJPZY4yJ3tRTGN4iWtNy754jPB05raUtg8b86axCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:25:19.440262Z","bundle_sha256":"0ed759adbf596a0bce1b7062b077afd09be7be623db0791138771a276e525af3"}}