{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:OUCHK6BDFGP4DMJVHHCF7JSIAI","short_pith_number":"pith:OUCHK6BD","canonical_record":{"source":{"id":"2205.09256","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-19T00:19:48Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"8220197114d5f3fe6b3ae4e0b853bb0ab7414f7a84a37a85c20191b4ec8f0d48","abstract_canon_sha256":"bd6a9976a2edba66245e71a5754653db25d59373250e99762cebc646a9067b76"},"schema_version":"1.0"},"canonical_sha256":"7504757823299fc1b13539c45fa64802351d8203553824cfcf10d725c1765961","source":{"kind":"arxiv","id":"2205.09256","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.09256","created_at":"2026-07-05T06:20:35Z"},{"alias_kind":"arxiv_version","alias_value":"2205.09256v3","created_at":"2026-07-05T06:20:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.09256","created_at":"2026-07-05T06:20:35Z"},{"alias_kind":"pith_short_12","alias_value":"OUCHK6BDFGP4","created_at":"2026-07-05T06:20:35Z"},{"alias_kind":"pith_short_16","alias_value":"OUCHK6BDFGP4DMJV","created_at":"2026-07-05T06:20:35Z"},{"alias_kind":"pith_short_8","alias_value":"OUCHK6BD","created_at":"2026-07-05T06:20:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:OUCHK6BDFGP4DMJVHHCF7JSIAI","target":"record","payload":{"canonical_record":{"source":{"id":"2205.09256","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-19T00:19:48Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"8220197114d5f3fe6b3ae4e0b853bb0ab7414f7a84a37a85c20191b4ec8f0d48","abstract_canon_sha256":"bd6a9976a2edba66245e71a5754653db25d59373250e99762cebc646a9067b76"},"schema_version":"1.0"},"canonical_sha256":"7504757823299fc1b13539c45fa64802351d8203553824cfcf10d725c1765961","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:35.333155Z","signature_b64":"AcdjezUSNoo4AYSvA3vXzR1rG7QBVl6kCuhBKC8HIWPszbTDK2jc+Px/Y8RuiIfMSKkJzqYiY3xmO5oZGAhNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7504757823299fc1b13539c45fa64802351d8203553824cfcf10d725c1765961","last_reissued_at":"2026-07-05T06:20:35.332593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:35.332593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.09256","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:20:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m6VjK+fnStEKCRvQrh+2Aw+Nmv1/ECtjAVsl/ZlePjgptGdNdLbQxVsDjDrovlE3zRZIZ4/CPrqLT3XzZdD+Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:19:10.922035Z"},"content_sha256":"a096db55e25014fe286d3fd6e67236fa4731665acd30df9a322648c6acc00654","schema_version":"1.0","event_id":"sha256:a096db55e25014fe286d3fd6e67236fa4731665acd30df9a322648c6acc00654"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:OUCHK6BDFGP4DMJVHHCF7JSIAI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Vision-Language Transformers from Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Alex Hauptmann, Jianfeng Gao, Liangke Gui, Qiuyuan Huang, Subhojit Som, Yingshan Chang, Yonatan Bisk","submitted_at":"2022-05-19T00:19:48Z","abstract_excerpt":"Vision-Language Transformers can be learned without low-level human labels (e.g. class labels, bounding boxes, etc). Existing work, whether explicitly utilizing bounding boxes or patches, assumes that the visual backbone must first be trained on ImageNet class prediction before being integrated into a multimodal linguistic pipeline. We show that this is not necessary and introduce a new model Vision-Language from Captions (VLC) built on top of Masked Auto-Encoders that does not require this supervision. In fact, in a head-to-head comparison between ViLT, the current state-of-the-art patch-base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.09256","kind":"arxiv","version":3},"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/2205.09256/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":"2026-07-05T06:20:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yHO3SpNtlx5szbTYRUkmATLWzhtqgjW9nX4WT9WxARG+MWkTRjbxuMDtKpbKnOMPPbQW+NBZH09jWDhlC+mBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:19:10.922427Z"},"content_sha256":"eebafcdc5371c2a06c5520601490ddb765e28385f31521a2af4be17567d3af19","schema_version":"1.0","event_id":"sha256:eebafcdc5371c2a06c5520601490ddb765e28385f31521a2af4be17567d3af19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OUCHK6BDFGP4DMJVHHCF7JSIAI/bundle.json","state_url":"https://pith.science/pith/OUCHK6BDFGP4DMJVHHCF7JSIAI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OUCHK6BDFGP4DMJVHHCF7JSIAI/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":"2026-07-06T13:19:10Z","links":{"resolver":"https://pith.science/pith/OUCHK6BDFGP4DMJVHHCF7JSIAI","bundle":"https://pith.science/pith/OUCHK6BDFGP4DMJVHHCF7JSIAI/bundle.json","state":"https://pith.science/pith/OUCHK6BDFGP4DMJVHHCF7JSIAI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OUCHK6BDFGP4DMJVHHCF7JSIAI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OUCHK6BDFGP4DMJVHHCF7JSIAI","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":"bd6a9976a2edba66245e71a5754653db25d59373250e99762cebc646a9067b76","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-19T00:19:48Z","title_canon_sha256":"8220197114d5f3fe6b3ae4e0b853bb0ab7414f7a84a37a85c20191b4ec8f0d48"},"schema_version":"1.0","source":{"id":"2205.09256","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.09256","created_at":"2026-07-05T06:20:35Z"},{"alias_kind":"arxiv_version","alias_value":"2205.09256v3","created_at":"2026-07-05T06:20:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.09256","created_at":"2026-07-05T06:20:35Z"},{"alias_kind":"pith_short_12","alias_value":"OUCHK6BDFGP4","created_at":"2026-07-05T06:20:35Z"},{"alias_kind":"pith_short_16","alias_value":"OUCHK6BDFGP4DMJV","created_at":"2026-07-05T06:20:35Z"},{"alias_kind":"pith_short_8","alias_value":"OUCHK6BD","created_at":"2026-07-05T06:20:35Z"}],"graph_snapshots":[{"event_id":"sha256:eebafcdc5371c2a06c5520601490ddb765e28385f31521a2af4be17567d3af19","target":"graph","created_at":"2026-07-05T06:20:35Z","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/2205.09256/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Transformers can be learned without low-level human labels (e.g. class labels, bounding boxes, etc). Existing work, whether explicitly utilizing bounding boxes or patches, assumes that the visual backbone must first be trained on ImageNet class prediction before being integrated into a multimodal linguistic pipeline. We show that this is not necessary and introduce a new model Vision-Language from Captions (VLC) built on top of Masked Auto-Encoders that does not require this supervision. In fact, in a head-to-head comparison between ViLT, the current state-of-the-art patch-base","authors_text":"Alex Hauptmann, Jianfeng Gao, Liangke Gui, Qiuyuan Huang, Subhojit Som, Yingshan Chang, Yonatan Bisk","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-19T00:19:48Z","title":"Training Vision-Language Transformers from Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.09256","kind":"arxiv","version":3},"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:a096db55e25014fe286d3fd6e67236fa4731665acd30df9a322648c6acc00654","target":"record","created_at":"2026-07-05T06:20:35Z","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":"bd6a9976a2edba66245e71a5754653db25d59373250e99762cebc646a9067b76","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-19T00:19:48Z","title_canon_sha256":"8220197114d5f3fe6b3ae4e0b853bb0ab7414f7a84a37a85c20191b4ec8f0d48"},"schema_version":"1.0","source":{"id":"2205.09256","kind":"arxiv","version":3}},"canonical_sha256":"7504757823299fc1b13539c45fa64802351d8203553824cfcf10d725c1765961","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7504757823299fc1b13539c45fa64802351d8203553824cfcf10d725c1765961","first_computed_at":"2026-07-05T06:20:35.332593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:20:35.332593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AcdjezUSNoo4AYSvA3vXzR1rG7QBVl6kCuhBKC8HIWPszbTDK2jc+Px/Y8RuiIfMSKkJzqYiY3xmO5oZGAhNCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:20:35.333155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.09256","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a096db55e25014fe286d3fd6e67236fa4731665acd30df9a322648c6acc00654","sha256:eebafcdc5371c2a06c5520601490ddb765e28385f31521a2af4be17567d3af19"],"state_sha256":"ca777ac7a25e069e76ff9b52d2a853dda464c44ec3607406f0adad5d02a6af93"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FkPlHHwPOjh8ElUh/Y1bZGNaaw3a3v/zgqZ8FH72lo046xMKUC4BvfyYxL/kqfPAvboTYgMgxP7W+Y1/ESVaDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T13:19:10.924410Z","bundle_sha256":"01820cf1e5f96f7a9440227dfc970853f6d2452789670f4628f09a30aee097a6"}}