{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SV7CF53QZDRKYHLJHD4JCEVDJZ","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":"cb74381eceb09beead48c3e4f882e0403ca3c677d95243bfd5b18c13861b1ca5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-13T17:59:50Z","title_canon_sha256":"ee3a28cc911d0526e4d24aa060e014b778c08fffe9252bd119cce48a0db0e375"},"schema_version":"1.0","source":{"id":"2107.06278","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.06278","created_at":"2026-07-05T03:27:33Z"},{"alias_kind":"arxiv_version","alias_value":"2107.06278v2","created_at":"2026-07-05T03:27:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.06278","created_at":"2026-07-05T03:27:33Z"},{"alias_kind":"pith_short_12","alias_value":"SV7CF53QZDRK","created_at":"2026-07-05T03:27:33Z"},{"alias_kind":"pith_short_16","alias_value":"SV7CF53QZDRKYHLJ","created_at":"2026-07-05T03:27:33Z"},{"alias_kind":"pith_short_8","alias_value":"SV7CF53Q","created_at":"2026-07-05T03:27:33Z"}],"graph_snapshots":[{"event_id":"sha256:33ad44bab11a44b4be11eb1e6f6dd41546c1def190e609a16e6e1c2690f11a4e","target":"graph","created_at":"2026-07-05T03:27:33Z","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/2107.06278/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern approaches typically formulate semantic segmentation as a per-pixel classification task, while instance-level segmentation is handled with an alternative mask classification. Our key insight: mask classification is sufficiently general to solve both semantic- and instance-level segmentation tasks in a unified manner using the exact same model, loss, and training procedure. Following this observation, we propose MaskFormer, a simple mask classification model which predicts a set of binary masks, each associated with a single global class label prediction. Overall, the proposed mask class","authors_text":"Alexander G. Schwing, Alexander Kirillov, Bowen Cheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-13T17:59:50Z","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.06278","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:a7cb3cfa5e17ea57e284eab1d11e29e73983fa652b15fe6e26d0d0814617ec33","target":"record","created_at":"2026-07-05T03:27:33Z","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":"cb74381eceb09beead48c3e4f882e0403ca3c677d95243bfd5b18c13861b1ca5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-13T17:59:50Z","title_canon_sha256":"ee3a28cc911d0526e4d24aa060e014b778c08fffe9252bd119cce48a0db0e375"},"schema_version":"1.0","source":{"id":"2107.06278","kind":"arxiv","version":2}},"canonical_sha256":"957e22f770c8e2ac1d6938f89112a34e6435534f6a60bf37124511aa00e01c72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"957e22f770c8e2ac1d6938f89112a34e6435534f6a60bf37124511aa00e01c72","first_computed_at":"2026-07-05T03:27:33.843166Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:27:33.843166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D/RyBZNTDevag7k3iP7wVEoEBzNMTsfQzKLNnhaTK3F9fSP1ylbaIT9yKUjhSoJvq4n5WobIen9apMxRBg+eBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:27:33.843692Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.06278","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7cb3cfa5e17ea57e284eab1d11e29e73983fa652b15fe6e26d0d0814617ec33","sha256:33ad44bab11a44b4be11eb1e6f6dd41546c1def190e609a16e6e1c2690f11a4e"],"state_sha256":"e4c62365c3b59fdad1e7690dad63a1586d9feec59e6b2cd736e80fe50d6eaebb"}