{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EFOEWMDNPVFGDMJ42WP2YNXB3A","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":"4bae7ba232acee95fc5c6a355caec109ce91b30dc2a50ff467eab667fbd876b0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T09:48:29Z","title_canon_sha256":"efc09d761e0579e9339edeb6f2a1c411d978cfc2a10819ceed9b397a5aa6320b"},"schema_version":"1.0","source":{"id":"2312.01771","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.01771","created_at":"2026-07-05T07:19:59Z"},{"alias_kind":"arxiv_version","alias_value":"2312.01771v1","created_at":"2026-07-05T07:19:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01771","created_at":"2026-07-05T07:19:59Z"},{"alias_kind":"pith_short_12","alias_value":"EFOEWMDNPVFG","created_at":"2026-07-05T07:19:59Z"},{"alias_kind":"pith_short_16","alias_value":"EFOEWMDNPVFGDMJ4","created_at":"2026-07-05T07:19:59Z"},{"alias_kind":"pith_short_8","alias_value":"EFOEWMDN","created_at":"2026-07-05T07:19:59Z"}],"graph_snapshots":[{"event_id":"sha256:989fd6277af59fb883db984deeadf803985d9b7217786af5f6f535efa9d99c0f","target":"graph","created_at":"2026-07-05T07:19:59Z","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/2312.01771/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In-context learning allows adapting a model to new tasks given a task description at test time. In this paper, we present IMProv - a generative model that is able to in-context learn visual tasks from multimodal prompts. Given a textual description of a visual task (e.g. \"Left: input image, Right: foreground segmentation\"), a few input-output visual examples, or both, the model in-context learns to solve it for a new test input. We train a masked generative transformer on a new dataset of figures from computer vision papers and their associated captions, together with a captioned large-scale i","authors_text":"Amir Bar, Jianfeng Gao, Jianwei Yang, Jiarui Xu, Trevor Darrell, Xiaolong Wang, Yossi Gandelsman","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T09:48:29Z","title":"IMProv: Inpainting-based Multimodal Prompting for Computer Vision Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01771","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":"sha256:0fe4e10d24d2ead821327f8c8c83fb4128adaf0c46fca410ecd8d73a9752c94e","target":"record","created_at":"2026-07-05T07:19:59Z","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":"4bae7ba232acee95fc5c6a355caec109ce91b30dc2a50ff467eab667fbd876b0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T09:48:29Z","title_canon_sha256":"efc09d761e0579e9339edeb6f2a1c411d978cfc2a10819ceed9b397a5aa6320b"},"schema_version":"1.0","source":{"id":"2312.01771","kind":"arxiv","version":1}},"canonical_sha256":"215c4b306d7d4a61b13cd59fac36e1d82ccad025dac42ec0acf4c57699b36616","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"215c4b306d7d4a61b13cd59fac36e1d82ccad025dac42ec0acf4c57699b36616","first_computed_at":"2026-07-05T07:19:59.694410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:19:59.694410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tOLOlj4C0GupqMJdMGrBAVlqlPceK5PdeTEbdMxAgyEvy8ehp0bWD+z2qQP74Tqmdju2mOGRlpR/TChXFaRzBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:19:59.694870Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.01771","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fe4e10d24d2ead821327f8c8c83fb4128adaf0c46fca410ecd8d73a9752c94e","sha256:989fd6277af59fb883db984deeadf803985d9b7217786af5f6f535efa9d99c0f"],"state_sha256":"6bb77263295f3bf6da706197b2496e6155f048cf05842b39b5c1c6e8ff15f7dc"}