{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2ES3ABWKDJFV6IXKHNPVUHUFQN","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":"5f9f5bb722f790ad2b439b53fb86bf14407cda87db415bd1cc2292ad8cfe4a8e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-02T18:59:58Z","title_canon_sha256":"c34d5a0c1a2e312b11f745b2344ec5df49a47dd394cef21e1abd4bc0bb87ec8a"},"schema_version":"1.0","source":{"id":"2112.01527","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.01527","created_at":"2026-07-05T04:32:13Z"},{"alias_kind":"arxiv_version","alias_value":"2112.01527v3","created_at":"2026-07-05T04:32:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01527","created_at":"2026-07-05T04:32:13Z"},{"alias_kind":"pith_short_12","alias_value":"2ES3ABWKDJFV","created_at":"2026-07-05T04:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"2ES3ABWKDJFV6IXK","created_at":"2026-07-05T04:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"2ES3ABWK","created_at":"2026-07-05T04:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:97e72989c9f1b03417e4d923eceb9a82f0f15ddeef153ea7d0968afc4c546a20","target":"graph","created_at":"2026-07-05T04:32:13Z","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/2112.01527/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image segmentation is about grouping pixels with different semantics, e.g., category or instance membership, where each choice of semantics defines a task. While only the semantics of each task differ, current research focuses on designing specialized architectures for each task. We present Masked-attention Mask Transformer (Mask2Former), a new architecture capable of addressing any image segmentation task (panoptic, instance or semantic). Its key components include masked attention, which extracts localized features by constraining cross-attention within predicted mask regions. In addition to","authors_text":"Alexander G. Schwing, Alexander Kirillov, Bowen Cheng, Ishan Misra, Rohit Girdhar","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-02T18:59:58Z","title":"Masked-attention Mask Transformer for Universal Image Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01527","kind":"arxiv","version":3},"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:ec4cb6f335397391b4c9637d2381ef4a774f7a387b58b51a3ce8a2f928b7f05f","target":"record","created_at":"2026-07-05T04:32:13Z","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":"5f9f5bb722f790ad2b439b53fb86bf14407cda87db415bd1cc2292ad8cfe4a8e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-02T18:59:58Z","title_canon_sha256":"c34d5a0c1a2e312b11f745b2344ec5df49a47dd394cef21e1abd4bc0bb87ec8a"},"schema_version":"1.0","source":{"id":"2112.01527","kind":"arxiv","version":3}},"canonical_sha256":"d125b006ca1a4b5f22ea3b5f5a1e85834794dcd21c84fcbef153b997769b3f10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d125b006ca1a4b5f22ea3b5f5a1e85834794dcd21c84fcbef153b997769b3f10","first_computed_at":"2026-07-05T04:32:13.487771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:32:13.487771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L/dNaXshpIYjtm7ckOiFfPK59cr6P05PW0cXfQLiLLYFIvqacyjTO8MGsVcO0iZ1Y5pGOriG8xSmQOqAzQlcCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:32:13.488278Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.01527","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec4cb6f335397391b4c9637d2381ef4a774f7a387b58b51a3ce8a2f928b7f05f","sha256:97e72989c9f1b03417e4d923eceb9a82f0f15ddeef153ea7d0968afc4c546a20"],"state_sha256":"8f13b94515e78496bb9df31e3283e5697e256c2662b0d437e86d1f4f9b8d8be8"}