{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AKYNDDC2JV5K5YZ3ICQLDAPEAY","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":"c0f65426a8d48eccbdc09120f8cd98c7f32c7e58693557f4ca1c6125a27905c6","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-24T09:09:37Z","title_canon_sha256":"cb2d1074271d6784ccaa53a8b9123c452181a860948376d2d601fbebef11d61a"},"schema_version":"1.0","source":{"id":"2401.13313","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.13313","created_at":"2026-07-05T07:37:03Z"},{"alias_kind":"arxiv_version","alias_value":"2401.13313v1","created_at":"2026-07-05T07:37:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13313","created_at":"2026-07-05T07:37:03Z"},{"alias_kind":"pith_short_12","alias_value":"AKYNDDC2JV5K","created_at":"2026-07-05T07:37:03Z"},{"alias_kind":"pith_short_16","alias_value":"AKYNDDC2JV5K5YZ3","created_at":"2026-07-05T07:37:03Z"},{"alias_kind":"pith_short_8","alias_value":"AKYNDDC2","created_at":"2026-07-05T07:37:03Z"}],"graph_snapshots":[{"event_id":"sha256:2f56cc9460b7774124560ae8056fc9fd87c23b484601ffe644284f2b3a3c0c5f","target":"graph","created_at":"2026-07-05T07:37:03Z","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/2401.13313/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of completing various visual document understanding (VDU) tasks, e.g., question answering and information extraction, on real-world documents through human-written instructions. To this end, we propose InstructDoc, the first large-scale collection of 30 publicly available VDU datasets, each with diverse instructions in a unified format, which covers a wide range of 12 tasks and includes open document types/formats. Furthermore, to enhance the generalization performance on VDU tasks, we design a new instruction-based document reading and understanding model, InstructDr, tha","authors_text":"Jun Suzuki, Kuniko Saito, Kyosuke Nishida, Ryota Tanaka, Taichi Iki","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-24T09:09:37Z","title":"InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13313","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:f0ff0d3cbc7ec2de706b718823744a4de4c4f86219cbcdf8c5d7f06797e12342","target":"record","created_at":"2026-07-05T07:37:03Z","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":"c0f65426a8d48eccbdc09120f8cd98c7f32c7e58693557f4ca1c6125a27905c6","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-24T09:09:37Z","title_canon_sha256":"cb2d1074271d6784ccaa53a8b9123c452181a860948376d2d601fbebef11d61a"},"schema_version":"1.0","source":{"id":"2401.13313","kind":"arxiv","version":1}},"canonical_sha256":"02b0d18c5a4d7aaee33b40a0b181e40623990a6b092ac2c96b5fba25cc082462","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02b0d18c5a4d7aaee33b40a0b181e40623990a6b092ac2c96b5fba25cc082462","first_computed_at":"2026-07-05T07:37:03.672866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:37:03.672866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J7jcqVBqzOPzUBE/ugqGf7TdxR/dsJBOy5zg9v0hmrolvEgoXiaUUMsJGQKOGLqm7Ge9DD/v6pStlkeSXy0mDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:37:03.673359Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.13313","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0ff0d3cbc7ec2de706b718823744a4de4c4f86219cbcdf8c5d7f06797e12342","sha256:2f56cc9460b7774124560ae8056fc9fd87c23b484601ffe644284f2b3a3c0c5f"],"state_sha256":"f51d15c5b27a836b5398cfc99297553650ff8eea76a6f6578902458d318cd949"}