{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:AP6NUUDKA4WHN4JXGZSQ3NZOPJ","short_pith_number":"pith:AP6NUUDK","canonical_record":{"source":{"id":"2210.02025","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-05T05:20:49Z","cross_cats_sorted":[],"title_canon_sha256":"111efbc979852984a9f9c53fca2e3b5d55e23455540fc7503afee7a09927ab0c","abstract_canon_sha256":"e32d09fab1d01945012a97af8da657cae62ff030415ad4322dbc7b848b23978b"},"schema_version":"1.0"},"canonical_sha256":"03fcda506a072c76f13736650db72e7a6ee2f6c2b01cba6a2264456640c875ac","source":{"kind":"arxiv","id":"2210.02025","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.02025","created_at":"2026-07-05T05:03:42Z"},{"alias_kind":"arxiv_version","alias_value":"2210.02025v1","created_at":"2026-07-05T05:03:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02025","created_at":"2026-07-05T05:03:42Z"},{"alias_kind":"pith_short_12","alias_value":"AP6NUUDKA4WH","created_at":"2026-07-05T05:03:42Z"},{"alias_kind":"pith_short_16","alias_value":"AP6NUUDKA4WHN4JX","created_at":"2026-07-05T05:03:42Z"},{"alias_kind":"pith_short_8","alias_value":"AP6NUUDK","created_at":"2026-07-05T05:03:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:AP6NUUDKA4WHN4JXGZSQ3NZOPJ","target":"record","payload":{"canonical_record":{"source":{"id":"2210.02025","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-05T05:20:49Z","cross_cats_sorted":[],"title_canon_sha256":"111efbc979852984a9f9c53fca2e3b5d55e23455540fc7503afee7a09927ab0c","abstract_canon_sha256":"e32d09fab1d01945012a97af8da657cae62ff030415ad4322dbc7b848b23978b"},"schema_version":"1.0"},"canonical_sha256":"03fcda506a072c76f13736650db72e7a6ee2f6c2b01cba6a2264456640c875ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:42.458269Z","signature_b64":"DrPx+LRFdp4NgBkQ3aj5A2E/51/oUWQPIIqW58B3XpsOU5PEc4C6V2UhoviLT6MaMWwauOuI/tCjcTcd9cj5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03fcda506a072c76f13736650db72e7a6ee2f6c2b01cba6a2264456640c875ac","last_reissued_at":"2026-07-05T05:03:42.457785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:42.457785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.02025","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:03:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GZVHxB6so80ifRZPSMeEF9IvCRlrDhpE+cy9K8RFI3NoeOmjiifkiaLakjg05gj9cA3IS+2G+3posZoQ8X9BAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T12:21:57.874983Z"},"content_sha256":"46277ad39fe55516050dd2dec785230185dc0d9203f79aef47542b40f50e403a","schema_version":"1.0","event_id":"sha256:46277ad39fe55516050dd2dec785230185dc0d9203f79aef47542b40f50e403a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:AP6NUUDKA4WHN4JXGZSQ3NZOPJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Liang, Jiaxu Miao, Wenguan Wang, Yi Yang","submitted_at":"2022-10-05T05:20:49Z","abstract_excerpt":"Prevalent semantic segmentation solutions are, in essence, a dense discriminative classifier of p(class|pixel feature). Though straightforward, this de facto paradigm neglects the underlying data distribution p(pixel feature|class), and struggles to identify out-of-distribution data. Going beyond this, we propose GMMSeg, a new family of segmentation models that rely on a dense generative classifier for the joint distribution p(pixel feature,class). For each class, GMMSeg builds Gaussian Mixture Models (GMMs) via Expectation-Maximization (EM), so as to capture class-conditional densities. Meanw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02025","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/2210.02025/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":"2026-07-05T05:03:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/DFmWNoa23yW5Zv7jyjAP1S0a7pwPe+fo/f1HJgbK5hOTvK8hZoQQyz2NKRvi1RmWtDsw1S3dR3SIw/7zJuVAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T12:21:57.875548Z"},"content_sha256":"82c07def090f3e32101893c8949d85e0eabc2acabd5cb13dc880920acf032ba4","schema_version":"1.0","event_id":"sha256:82c07def090f3e32101893c8949d85e0eabc2acabd5cb13dc880920acf032ba4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AP6NUUDKA4WHN4JXGZSQ3NZOPJ/bundle.json","state_url":"https://pith.science/pith/AP6NUUDKA4WHN4JXGZSQ3NZOPJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AP6NUUDKA4WHN4JXGZSQ3NZOPJ/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":"2026-08-11T12:21:57Z","links":{"resolver":"https://pith.science/pith/AP6NUUDKA4WHN4JXGZSQ3NZOPJ","bundle":"https://pith.science/pith/AP6NUUDKA4WHN4JXGZSQ3NZOPJ/bundle.json","state":"https://pith.science/pith/AP6NUUDKA4WHN4JXGZSQ3NZOPJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AP6NUUDKA4WHN4JXGZSQ3NZOPJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:AP6NUUDKA4WHN4JXGZSQ3NZOPJ","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":"e32d09fab1d01945012a97af8da657cae62ff030415ad4322dbc7b848b23978b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-05T05:20:49Z","title_canon_sha256":"111efbc979852984a9f9c53fca2e3b5d55e23455540fc7503afee7a09927ab0c"},"schema_version":"1.0","source":{"id":"2210.02025","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.02025","created_at":"2026-07-05T05:03:42Z"},{"alias_kind":"arxiv_version","alias_value":"2210.02025v1","created_at":"2026-07-05T05:03:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02025","created_at":"2026-07-05T05:03:42Z"},{"alias_kind":"pith_short_12","alias_value":"AP6NUUDKA4WH","created_at":"2026-07-05T05:03:42Z"},{"alias_kind":"pith_short_16","alias_value":"AP6NUUDKA4WHN4JX","created_at":"2026-07-05T05:03:42Z"},{"alias_kind":"pith_short_8","alias_value":"AP6NUUDK","created_at":"2026-07-05T05:03:42Z"}],"graph_snapshots":[{"event_id":"sha256:82c07def090f3e32101893c8949d85e0eabc2acabd5cb13dc880920acf032ba4","target":"graph","created_at":"2026-07-05T05:03:42Z","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/2210.02025/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prevalent semantic segmentation solutions are, in essence, a dense discriminative classifier of p(class|pixel feature). Though straightforward, this de facto paradigm neglects the underlying data distribution p(pixel feature|class), and struggles to identify out-of-distribution data. Going beyond this, we propose GMMSeg, a new family of segmentation models that rely on a dense generative classifier for the joint distribution p(pixel feature,class). For each class, GMMSeg builds Gaussian Mixture Models (GMMs) via Expectation-Maximization (EM), so as to capture class-conditional densities. Meanw","authors_text":"Chen Liang, Jiaxu Miao, Wenguan Wang, Yi Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-05T05:20:49Z","title":"GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02025","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":"sha256:46277ad39fe55516050dd2dec785230185dc0d9203f79aef47542b40f50e403a","target":"record","created_at":"2026-07-05T05:03:42Z","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":"e32d09fab1d01945012a97af8da657cae62ff030415ad4322dbc7b848b23978b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-05T05:20:49Z","title_canon_sha256":"111efbc979852984a9f9c53fca2e3b5d55e23455540fc7503afee7a09927ab0c"},"schema_version":"1.0","source":{"id":"2210.02025","kind":"arxiv","version":1}},"canonical_sha256":"03fcda506a072c76f13736650db72e7a6ee2f6c2b01cba6a2264456640c875ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03fcda506a072c76f13736650db72e7a6ee2f6c2b01cba6a2264456640c875ac","first_computed_at":"2026-07-05T05:03:42.457785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:42.457785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DrPx+LRFdp4NgBkQ3aj5A2E/51/oUWQPIIqW58B3XpsOU5PEc4C6V2UhoviLT6MaMWwauOuI/tCjcTcd9cj5AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:42.458269Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.02025","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46277ad39fe55516050dd2dec785230185dc0d9203f79aef47542b40f50e403a","sha256:82c07def090f3e32101893c8949d85e0eabc2acabd5cb13dc880920acf032ba4"],"state_sha256":"1546b9c3de8332a4701f2503d09af5471e17d1d88d4226073e6bb931a0ed0b4f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pPRGwelT554kHqBgpP++qQsfYfxHGL+q3kt0hMb/2GtKIbY9Utquidn4gaXiX2YfL0EJi0qt2pa05ZzUIVXXDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T12:21:57.883095Z","bundle_sha256":"5ba9faff5867e08d8ca6ac5eb374ae6a3ecaedd2a466088b3d3605fb62f65e67"}}