{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CGPTBF643G7DCBMDRR45JJNG3Z","short_pith_number":"pith:CGPTBF64","schema_version":"1.0","canonical_sha256":"119f3097dcd9be3105838c79d4a5a6de68b7d90375d992db859c6a43585a894f","source":{"kind":"arxiv","id":"2312.06592","version":1},"attestation_state":"computed","paper":{"title":"Flexible visual prompts for in-context learning in computer vision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christoffer Edlund, Ioana Croitoru, Jon Almaz\\'an, Robert Dorfman, Thomas Foster, Thomas Varsavsky","submitted_at":"2023-12-11T18:27:42Z","abstract_excerpt":"In this work, we address in-context learning (ICL) for the task of image segmentation, introducing a novel approach that adapts a modern Video Object Segmentation (VOS) technique for visual in-context learning. This adaptation is inspired by the VOS method's ability to efficiently and flexibly learn objects from a few examples. Through evaluations across a range of support set sizes and on diverse segmentation datasets, our method consistently surpasses existing techniques. Notably, it excels with data containing classes not encountered during training. Additionally, we propose a technique for"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.06592","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T18:27:42Z","cross_cats_sorted":[],"title_canon_sha256":"3b5d6edbf54651f59c3ba58cd00b6406d32be057996125f330d869deb60c4668","abstract_canon_sha256":"cf46af603053bfbe2b3b5526b4d9ea277ff0ba428b77bdb30e5aaf045ca3df68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:47.433688Z","signature_b64":"0CKTej/eh2Wu5IY2SynNP/++UX7F+BksA7CQAuvBn+6Dl6JrN0EH8hhVkVvhBDWr/StrlbxpFwu+gmfbMhXzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"119f3097dcd9be3105838c79d4a5a6de68b7d90375d992db859c6a43585a894f","last_reissued_at":"2026-07-05T07:22:47.433160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:47.433160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flexible visual prompts for in-context learning in computer vision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christoffer Edlund, Ioana Croitoru, Jon Almaz\\'an, Robert Dorfman, Thomas Foster, Thomas Varsavsky","submitted_at":"2023-12-11T18:27:42Z","abstract_excerpt":"In this work, we address in-context learning (ICL) for the task of image segmentation, introducing a novel approach that adapts a modern Video Object Segmentation (VOS) technique for visual in-context learning. This adaptation is inspired by the VOS method's ability to efficiently and flexibly learn objects from a few examples. Through evaluations across a range of support set sizes and on diverse segmentation datasets, our method consistently surpasses existing techniques. Notably, it excels with data containing classes not encountered during training. Additionally, we propose a technique for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06592","kind":"arxiv","version":1},"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/2312.06592/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2312.06592","created_at":"2026-07-05T07:22:47.433223+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.06592v1","created_at":"2026-07-05T07:22:47.433223+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06592","created_at":"2026-07-05T07:22:47.433223+00:00"},{"alias_kind":"pith_short_12","alias_value":"CGPTBF643G7D","created_at":"2026-07-05T07:22:47.433223+00:00"},{"alias_kind":"pith_short_16","alias_value":"CGPTBF643G7DCBMD","created_at":"2026-07-05T07:22:47.433223+00:00"},{"alias_kind":"pith_short_8","alias_value":"CGPTBF64","created_at":"2026-07-05T07:22:47.433223+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17837","citing_title":"Time-Contrastive Pretraining for In-Context Image and Video Segmentation","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CGPTBF643G7DCBMDRR45JJNG3Z","json":"https://pith.science/pith/CGPTBF643G7DCBMDRR45JJNG3Z.json","graph_json":"https://pith.science/api/pith-number/CGPTBF643G7DCBMDRR45JJNG3Z/graph.json","events_json":"https://pith.science/api/pith-number/CGPTBF643G7DCBMDRR45JJNG3Z/events.json","paper":"https://pith.science/paper/CGPTBF64"},"agent_actions":{"view_html":"https://pith.science/pith/CGPTBF643G7DCBMDRR45JJNG3Z","download_json":"https://pith.science/pith/CGPTBF643G7DCBMDRR45JJNG3Z.json","view_paper":"https://pith.science/paper/CGPTBF64","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.06592&json=true","fetch_graph":"https://pith.science/api/pith-number/CGPTBF643G7DCBMDRR45JJNG3Z/graph.json","fetch_events":"https://pith.science/api/pith-number/CGPTBF643G7DCBMDRR45JJNG3Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CGPTBF643G7DCBMDRR45JJNG3Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CGPTBF643G7DCBMDRR45JJNG3Z/action/storage_attestation","attest_author":"https://pith.science/pith/CGPTBF643G7DCBMDRR45JJNG3Z/action/author_attestation","sign_citation":"https://pith.science/pith/CGPTBF643G7DCBMDRR45JJNG3Z/action/citation_signature","submit_replication":"https://pith.science/pith/CGPTBF643G7DCBMDRR45JJNG3Z/action/replication_record"}},"created_at":"2026-07-05T07:22:47.433223+00:00","updated_at":"2026-07-05T07:22:47.433223+00:00"}