{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GFNRU7NU55HNVQCWGACH24IYQL","short_pith_number":"pith:GFNRU7NU","canonical_record":{"source":{"id":"2210.03347","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-07T06:42:06Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"bda90542f851113088efdf4a45d93addd49a2741770fd5a13210431c5e97ad7d","abstract_canon_sha256":"758a21e1d584d64a8b33b605f046b4e2b9f5abb9a5d9823b74e03150822ab7fe"},"schema_version":"1.0"},"canonical_sha256":"315b1a7db4ef4edac05630047d711882ca269b6bbf20143886427f5b914e3f8f","source":{"kind":"arxiv","id":"2210.03347","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03347","created_at":"2026-07-05T06:21:13Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03347v2","created_at":"2026-07-05T06:21:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03347","created_at":"2026-07-05T06:21:13Z"},{"alias_kind":"pith_short_12","alias_value":"GFNRU7NU55HN","created_at":"2026-07-05T06:21:13Z"},{"alias_kind":"pith_short_16","alias_value":"GFNRU7NU55HNVQCW","created_at":"2026-07-05T06:21:13Z"},{"alias_kind":"pith_short_8","alias_value":"GFNRU7NU","created_at":"2026-07-05T06:21:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GFNRU7NU55HNVQCWGACH24IYQL","target":"record","payload":{"canonical_record":{"source":{"id":"2210.03347","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-07T06:42:06Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"bda90542f851113088efdf4a45d93addd49a2741770fd5a13210431c5e97ad7d","abstract_canon_sha256":"758a21e1d584d64a8b33b605f046b4e2b9f5abb9a5d9823b74e03150822ab7fe"},"schema_version":"1.0"},"canonical_sha256":"315b1a7db4ef4edac05630047d711882ca269b6bbf20143886427f5b914e3f8f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:13.785973Z","signature_b64":"F7N9JH/9ZSLbs6M9gp0Rj/cebT8q3nvG2KhP/n9c4I+QsdWfxwssdy5k5Rk2yUtYBpOVmwdU2VdQWdnp7G8XBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"315b1a7db4ef4edac05630047d711882ca269b6bbf20143886427f5b914e3f8f","last_reissued_at":"2026-07-05T06:21:13.785555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:13.785555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.03347","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":"2026-07-05T06:21:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"suyhrgf5WpJjgtg6UeeUx/znOe8KZ8zICWoEcS/P3hizpPgUXyu7Czkx1eKZPj0cTpYygjxMAHzUXdnFcflqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T01:23:58.576448Z"},"content_sha256":"f4d9d8688987bc850f3a5501ca8d36d30ec980ae9c43b29ab5cc460a43a5e66d","schema_version":"1.0","event_id":"sha256:f4d9d8688987bc850f3a5501ca8d36d30ec980ae9c43b29ab5cc460a43a5e66d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GFNRU7NU55HNVQCWGACH24IYQL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Fangyu Liu, Hexiang Hu, Iulia Turc, Julian Eisenschlos, Kenton Lee, Kristina Toutanova, Mandar Joshi, Ming-Wei Chang, Peter Shaw, Urvashi Khandelwal","submitted_at":"2022-10-07T06:42:06Z","abstract_excerpt":"Visually-situated language is ubiquitous -- sources range from textbooks with diagrams to web pages with images and tables, to mobile apps with buttons and forms. Perhaps due to this diversity, previous work has typically relied on domain-specific recipes with limited sharing of the underlying data, model architectures, and objectives. We present Pix2Struct, a pretrained image-to-text model for purely visual language understanding, which can be finetuned on tasks containing visually-situated language. Pix2Struct is pretrained by learning to parse masked screenshots of web pages into simplified"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03347","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/2210.03347/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":"2026-07-05T06:21:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0mCDGzmqhdtrHaWA7YZKbrisdcr4ohV3MhW/twLuXCWthSzf8XPX4c4xFHkJrVuj6o/hQ66kuYyUlaTukL8nAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T01:23:58.576963Z"},"content_sha256":"d5f4da1dcb4c1cc37cce7fa3ea4bd7be270b9b34611c80236b85502189858b37","schema_version":"1.0","event_id":"sha256:d5f4da1dcb4c1cc37cce7fa3ea4bd7be270b9b34611c80236b85502189858b37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GFNRU7NU55HNVQCWGACH24IYQL/bundle.json","state_url":"https://pith.science/pith/GFNRU7NU55HNVQCWGACH24IYQL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GFNRU7NU55HNVQCWGACH24IYQL/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":"2026-08-14T01:23:58Z","links":{"resolver":"https://pith.science/pith/GFNRU7NU55HNVQCWGACH24IYQL","bundle":"https://pith.science/pith/GFNRU7NU55HNVQCWGACH24IYQL/bundle.json","state":"https://pith.science/pith/GFNRU7NU55HNVQCWGACH24IYQL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GFNRU7NU55HNVQCWGACH24IYQL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GFNRU7NU55HNVQCWGACH24IYQL","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":"758a21e1d584d64a8b33b605f046b4e2b9f5abb9a5d9823b74e03150822ab7fe","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-07T06:42:06Z","title_canon_sha256":"bda90542f851113088efdf4a45d93addd49a2741770fd5a13210431c5e97ad7d"},"schema_version":"1.0","source":{"id":"2210.03347","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03347","created_at":"2026-07-05T06:21:13Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03347v2","created_at":"2026-07-05T06:21:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03347","created_at":"2026-07-05T06:21:13Z"},{"alias_kind":"pith_short_12","alias_value":"GFNRU7NU55HN","created_at":"2026-07-05T06:21:13Z"},{"alias_kind":"pith_short_16","alias_value":"GFNRU7NU55HNVQCW","created_at":"2026-07-05T06:21:13Z"},{"alias_kind":"pith_short_8","alias_value":"GFNRU7NU","created_at":"2026-07-05T06:21:13Z"}],"graph_snapshots":[{"event_id":"sha256:d5f4da1dcb4c1cc37cce7fa3ea4bd7be270b9b34611c80236b85502189858b37","target":"graph","created_at":"2026-07-05T06:21:13Z","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/2210.03347/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visually-situated language is ubiquitous -- sources range from textbooks with diagrams to web pages with images and tables, to mobile apps with buttons and forms. Perhaps due to this diversity, previous work has typically relied on domain-specific recipes with limited sharing of the underlying data, model architectures, and objectives. We present Pix2Struct, a pretrained image-to-text model for purely visual language understanding, which can be finetuned on tasks containing visually-situated language. Pix2Struct is pretrained by learning to parse masked screenshots of web pages into simplified","authors_text":"Fangyu Liu, Hexiang Hu, Iulia Turc, Julian Eisenschlos, Kenton Lee, Kristina Toutanova, Mandar Joshi, Ming-Wei Chang, Peter Shaw, Urvashi Khandelwal","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-07T06:42:06Z","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03347","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:f4d9d8688987bc850f3a5501ca8d36d30ec980ae9c43b29ab5cc460a43a5e66d","target":"record","created_at":"2026-07-05T06:21:13Z","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":"758a21e1d584d64a8b33b605f046b4e2b9f5abb9a5d9823b74e03150822ab7fe","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-07T06:42:06Z","title_canon_sha256":"bda90542f851113088efdf4a45d93addd49a2741770fd5a13210431c5e97ad7d"},"schema_version":"1.0","source":{"id":"2210.03347","kind":"arxiv","version":2}},"canonical_sha256":"315b1a7db4ef4edac05630047d711882ca269b6bbf20143886427f5b914e3f8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"315b1a7db4ef4edac05630047d711882ca269b6bbf20143886427f5b914e3f8f","first_computed_at":"2026-07-05T06:21:13.785555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:21:13.785555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F7N9JH/9ZSLbs6M9gp0Rj/cebT8q3nvG2KhP/n9c4I+QsdWfxwssdy5k5Rk2yUtYBpOVmwdU2VdQWdnp7G8XBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:21:13.785973Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.03347","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4d9d8688987bc850f3a5501ca8d36d30ec980ae9c43b29ab5cc460a43a5e66d","sha256:d5f4da1dcb4c1cc37cce7fa3ea4bd7be270b9b34611c80236b85502189858b37"],"state_sha256":"9e513ecfc9d7c5cbc57c19503770d0370d6b7a808eef9220e2ed9d81405f00a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eRwdZaLfZNLc4bLm3F+GCW4AYSgQNfssXa/iMp/z0jb/o0VYdmmq5M2tWcM40Dz4biGv9eH6JUz0XQnRk3CHAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T01:23:58.582156Z","bundle_sha256":"13c89eeb18f15f0e2c803b881a798d4174308b3ed2294092bd565f4bd67c5a7e"}}