{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:W75QZ2VHRGACCRAL6VHE6BRVBF","short_pith_number":"pith:W75QZ2VH","canonical_record":{"source":{"id":"2206.08916","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-17T17:53:47Z","cross_cats_sorted":[],"title_canon_sha256":"5ac584da3d7e066a87346000c779ed6abeda11556b7bff1ed2e1563faed83a3e","abstract_canon_sha256":"64c220e772d9cc1aa4ddb2d7db5f3983c9434ba7cf4c3cd07ff8c3de4f14c15a"},"schema_version":"1.0"},"canonical_sha256":"b7fb0ceaa7898021440bf54e4f06350959f6a2bc630a5c8f14861ffd455d8d33","source":{"kind":"arxiv","id":"2206.08916","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.08916","created_at":"2026-07-05T05:03:37Z"},{"alias_kind":"arxiv_version","alias_value":"2206.08916v2","created_at":"2026-07-05T05:03:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08916","created_at":"2026-07-05T05:03:37Z"},{"alias_kind":"pith_short_12","alias_value":"W75QZ2VHRGAC","created_at":"2026-07-05T05:03:37Z"},{"alias_kind":"pith_short_16","alias_value":"W75QZ2VHRGACCRAL","created_at":"2026-07-05T05:03:37Z"},{"alias_kind":"pith_short_8","alias_value":"W75QZ2VH","created_at":"2026-07-05T05:03:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:W75QZ2VHRGACCRAL6VHE6BRVBF","target":"record","payload":{"canonical_record":{"source":{"id":"2206.08916","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-17T17:53:47Z","cross_cats_sorted":[],"title_canon_sha256":"5ac584da3d7e066a87346000c779ed6abeda11556b7bff1ed2e1563faed83a3e","abstract_canon_sha256":"64c220e772d9cc1aa4ddb2d7db5f3983c9434ba7cf4c3cd07ff8c3de4f14c15a"},"schema_version":"1.0"},"canonical_sha256":"b7fb0ceaa7898021440bf54e4f06350959f6a2bc630a5c8f14861ffd455d8d33","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:37.936838Z","signature_b64":"2L+qQzUN0QhjzovrKQIKdkWrdFGaJF/C5WcNNzRFfWBwYNBq2is8e9guDNCXRREI7KOncug2X6a6EOdwgZoJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7fb0ceaa7898021440bf54e4f06350959f6a2bc630a5c8f14861ffd455d8d33","last_reissued_at":"2026-07-05T05:03:37.936357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:37.936357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.08916","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":"2026-07-05T05:03:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A+8mFzeeSNkcfGRDA2LoV2r4OjMOtAb2860ofF6TTLVphXXGJqMamuDoPOg9MF8uogAgcG3hDVvKGB702yFkAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T15:14:36.556213Z"},"content_sha256":"1650323ed3ec3df4eb6617d3a1722d2cf9957332a622a01b224d8cf85be7d752","schema_version":"1.0","event_id":"sha256:1650323ed3ec3df4eb6617d3a1722d2cf9957332a622a01b224d8cf85be7d752"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:W75QZ2VHRGACCRAL6VHE6BRVBF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aniruddha Kembhavi, Christopher Clark, Jiasen Lu, Roozbeh Mottaghi, Rowan Zellers","submitted_at":"2022-06-17T17:53:47Z","abstract_excerpt":"We propose Unified-IO, a model that performs a large variety of AI tasks spanning classical computer vision tasks, including pose estimation, object detection, depth estimation and image generation, vision-and-language tasks such as region captioning and referring expression, to natural language processing tasks such as question answering and paraphrasing. Developing a single unified model for such a large variety of tasks poses unique challenges due to the heterogeneous inputs and outputs pertaining to each task, including RGB images, per-pixel maps, binary masks, bounding boxes, and language"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08916","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/2206.08916/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":"2026-07-05T05:03:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yl/b9ARrfIJm8kfx2w5SK8/sIMjdUUafmBXXW5xfRziW0wDDPS/Idnyi7zqAsMVvpvDev9OqvlxpqSfcAoqMAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T15:14:36.557124Z"},"content_sha256":"db69f0d69f78e03d3a0764e789dd262479328635b1d4e708695b7f9e653edcfe","schema_version":"1.0","event_id":"sha256:db69f0d69f78e03d3a0764e789dd262479328635b1d4e708695b7f9e653edcfe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W75QZ2VHRGACCRAL6VHE6BRVBF/bundle.json","state_url":"https://pith.science/pith/W75QZ2VHRGACCRAL6VHE6BRVBF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W75QZ2VHRGACCRAL6VHE6BRVBF/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":"2026-08-17T15:14:36Z","links":{"resolver":"https://pith.science/pith/W75QZ2VHRGACCRAL6VHE6BRVBF","bundle":"https://pith.science/pith/W75QZ2VHRGACCRAL6VHE6BRVBF/bundle.json","state":"https://pith.science/pith/W75QZ2VHRGACCRAL6VHE6BRVBF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W75QZ2VHRGACCRAL6VHE6BRVBF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:W75QZ2VHRGACCRAL6VHE6BRVBF","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":"64c220e772d9cc1aa4ddb2d7db5f3983c9434ba7cf4c3cd07ff8c3de4f14c15a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-17T17:53:47Z","title_canon_sha256":"5ac584da3d7e066a87346000c779ed6abeda11556b7bff1ed2e1563faed83a3e"},"schema_version":"1.0","source":{"id":"2206.08916","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.08916","created_at":"2026-07-05T05:03:37Z"},{"alias_kind":"arxiv_version","alias_value":"2206.08916v2","created_at":"2026-07-05T05:03:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08916","created_at":"2026-07-05T05:03:37Z"},{"alias_kind":"pith_short_12","alias_value":"W75QZ2VHRGAC","created_at":"2026-07-05T05:03:37Z"},{"alias_kind":"pith_short_16","alias_value":"W75QZ2VHRGACCRAL","created_at":"2026-07-05T05:03:37Z"},{"alias_kind":"pith_short_8","alias_value":"W75QZ2VH","created_at":"2026-07-05T05:03:37Z"}],"graph_snapshots":[{"event_id":"sha256:db69f0d69f78e03d3a0764e789dd262479328635b1d4e708695b7f9e653edcfe","target":"graph","created_at":"2026-07-05T05:03:37Z","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/2206.08916/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Unified-IO, a model that performs a large variety of AI tasks spanning classical computer vision tasks, including pose estimation, object detection, depth estimation and image generation, vision-and-language tasks such as region captioning and referring expression, to natural language processing tasks such as question answering and paraphrasing. Developing a single unified model for such a large variety of tasks poses unique challenges due to the heterogeneous inputs and outputs pertaining to each task, including RGB images, per-pixel maps, binary masks, bounding boxes, and language","authors_text":"Aniruddha Kembhavi, Christopher Clark, Jiasen Lu, Roozbeh Mottaghi, Rowan Zellers","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-17T17:53:47Z","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08916","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":"sha256:1650323ed3ec3df4eb6617d3a1722d2cf9957332a622a01b224d8cf85be7d752","target":"record","created_at":"2026-07-05T05:03:37Z","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":"64c220e772d9cc1aa4ddb2d7db5f3983c9434ba7cf4c3cd07ff8c3de4f14c15a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-17T17:53:47Z","title_canon_sha256":"5ac584da3d7e066a87346000c779ed6abeda11556b7bff1ed2e1563faed83a3e"},"schema_version":"1.0","source":{"id":"2206.08916","kind":"arxiv","version":2}},"canonical_sha256":"b7fb0ceaa7898021440bf54e4f06350959f6a2bc630a5c8f14861ffd455d8d33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7fb0ceaa7898021440bf54e4f06350959f6a2bc630a5c8f14861ffd455d8d33","first_computed_at":"2026-07-05T05:03:37.936357Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:37.936357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2L+qQzUN0QhjzovrKQIKdkWrdFGaJF/C5WcNNzRFfWBwYNBq2is8e9guDNCXRREI7KOncug2X6a6EOdwgZoJAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:37.936838Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.08916","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1650323ed3ec3df4eb6617d3a1722d2cf9957332a622a01b224d8cf85be7d752","sha256:db69f0d69f78e03d3a0764e789dd262479328635b1d4e708695b7f9e653edcfe"],"state_sha256":"3307f9bcd5bb95e24835b573b60f5d8e41c61c4ccef6fdae4a58f1b19107a1b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CSEh5+jfetG/s6AmhmVbzua6xgrFLGG/C4H9L0T6SijwsZR+xJsVUKmSnD2DlE1Ge/dCQHft7n13lscWJNJdCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T15:14:36.563954Z","bundle_sha256":"2b6bc1a4b2154240f646c6fd04e9cebe71286f61fef8b5e0dcecb909f4f5d9b2"}}