{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:DVI4DCQXRMJLEZZ7UOKDBB4GNI","short_pith_number":"pith:DVI4DCQX","canonical_record":{"source":{"id":"2006.13144","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-23T16:39:59Z","cross_cats_sorted":[],"title_canon_sha256":"160817190b92874f02abbd53e1755989cfe1d821a329432327b89f097f9cf893","abstract_canon_sha256":"bcaeec68e88a9a0c3b276c66bb7f5f24333840a4c5bf8b1848cdc290a3b36d09"},"schema_version":"1.0"},"canonical_sha256":"1d51c18a178b12b2673fa3943087866a30ace8a292c8299e2027719adb761a5c","source":{"kind":"arxiv","id":"2006.13144","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.13144","created_at":"2026-07-05T03:03:17Z"},{"alias_kind":"arxiv_version","alias_value":"2006.13144v3","created_at":"2026-07-05T03:03:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13144","created_at":"2026-07-05T03:03:17Z"},{"alias_kind":"pith_short_12","alias_value":"DVI4DCQXRMJL","created_at":"2026-07-05T03:03:17Z"},{"alias_kind":"pith_short_16","alias_value":"DVI4DCQXRMJLEZZ7","created_at":"2026-07-05T03:03:17Z"},{"alias_kind":"pith_short_8","alias_value":"DVI4DCQX","created_at":"2026-07-05T03:03:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:DVI4DCQXRMJLEZZ7UOKDBB4GNI","target":"record","payload":{"canonical_record":{"source":{"id":"2006.13144","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-23T16:39:59Z","cross_cats_sorted":[],"title_canon_sha256":"160817190b92874f02abbd53e1755989cfe1d821a329432327b89f097f9cf893","abstract_canon_sha256":"bcaeec68e88a9a0c3b276c66bb7f5f24333840a4c5bf8b1848cdc290a3b36d09"},"schema_version":"1.0"},"canonical_sha256":"1d51c18a178b12b2673fa3943087866a30ace8a292c8299e2027719adb761a5c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:17.881362Z","signature_b64":"yaWFc5nxfcSPUxlueiUXJ7oKKAhRaqqBO90+sAQNrQEPBgeXGdYtBn7kiYFYvwtaXMOO2LAFZsYCWhemrqm8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d51c18a178b12b2673fa3943087866a30ace8a292c8299e2027719adb761a5c","last_reissued_at":"2026-07-05T03:03:17.880907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:17.880907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.13144","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:03:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cuQ90QtyY2eHzXAP/ro+1Z7e0q/ZKBwgUtZsx/G0ojdNLIWUnLCQ/R/LZ0VwA6o3wSO083qkj7MReFNhLdylBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T05:33:14.554739Z"},"content_sha256":"76f22b770eef80711bf7758816be5f79d88313d9e88161f44b98a6d6100aec40","schema_version":"1.0","event_id":"sha256:76f22b770eef80711bf7758816be5f79d88313d9e88161f44b98a6d6100aec40"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:DVI4DCQXRMJLEZZ7UOKDBB4GNI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Calibrated Adversarial Refinement for Stochastic Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cedric Nugteren, Deepak K. Gupta, Elias Kassapis, Georgi Dikov","submitted_at":"2020-06-23T16:39:59Z","abstract_excerpt":"In semantic segmentation tasks, input images can often have more than one plausible interpretation, thus allowing for multiple valid labels. To capture such ambiguities, recent work has explored the use of probabilistic networks that can learn a distribution over predictions. However, these do not necessarily represent the empirical distribution accurately. In this work, we present a strategy for learning a calibrated predictive distribution over semantic maps, where the probability associated with each prediction reflects its ground truth correctness likelihood. To this end, we propose a nove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13144","kind":"arxiv","version":3},"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/2006.13144/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":"2026-07-05T03:03:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w41aQz8DJlg6849UIiheFFOUGCo6WtqNay+lbDyFqvrQcGlvTP+DL2iidt9HVf78/XoZmZTA3OKSWjNX+BM6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T05:33:14.555630Z"},"content_sha256":"0e55f6d97f0fc91144cced259506ebfb19ecd65c8a75d71b20fe154f3f0545c7","schema_version":"1.0","event_id":"sha256:0e55f6d97f0fc91144cced259506ebfb19ecd65c8a75d71b20fe154f3f0545c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DVI4DCQXRMJLEZZ7UOKDBB4GNI/bundle.json","state_url":"https://pith.science/pith/DVI4DCQXRMJLEZZ7UOKDBB4GNI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DVI4DCQXRMJLEZZ7UOKDBB4GNI/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":"2026-08-15T05:33:14Z","links":{"resolver":"https://pith.science/pith/DVI4DCQXRMJLEZZ7UOKDBB4GNI","bundle":"https://pith.science/pith/DVI4DCQXRMJLEZZ7UOKDBB4GNI/bundle.json","state":"https://pith.science/pith/DVI4DCQXRMJLEZZ7UOKDBB4GNI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DVI4DCQXRMJLEZZ7UOKDBB4GNI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:DVI4DCQXRMJLEZZ7UOKDBB4GNI","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":"bcaeec68e88a9a0c3b276c66bb7f5f24333840a4c5bf8b1848cdc290a3b36d09","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-23T16:39:59Z","title_canon_sha256":"160817190b92874f02abbd53e1755989cfe1d821a329432327b89f097f9cf893"},"schema_version":"1.0","source":{"id":"2006.13144","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.13144","created_at":"2026-07-05T03:03:17Z"},{"alias_kind":"arxiv_version","alias_value":"2006.13144v3","created_at":"2026-07-05T03:03:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13144","created_at":"2026-07-05T03:03:17Z"},{"alias_kind":"pith_short_12","alias_value":"DVI4DCQXRMJL","created_at":"2026-07-05T03:03:17Z"},{"alias_kind":"pith_short_16","alias_value":"DVI4DCQXRMJLEZZ7","created_at":"2026-07-05T03:03:17Z"},{"alias_kind":"pith_short_8","alias_value":"DVI4DCQX","created_at":"2026-07-05T03:03:17Z"}],"graph_snapshots":[{"event_id":"sha256:0e55f6d97f0fc91144cced259506ebfb19ecd65c8a75d71b20fe154f3f0545c7","target":"graph","created_at":"2026-07-05T03:03:17Z","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/2006.13144/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In semantic segmentation tasks, input images can often have more than one plausible interpretation, thus allowing for multiple valid labels. To capture such ambiguities, recent work has explored the use of probabilistic networks that can learn a distribution over predictions. However, these do not necessarily represent the empirical distribution accurately. In this work, we present a strategy for learning a calibrated predictive distribution over semantic maps, where the probability associated with each prediction reflects its ground truth correctness likelihood. To this end, we propose a nove","authors_text":"Cedric Nugteren, Deepak K. Gupta, Elias Kassapis, Georgi Dikov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-23T16:39:59Z","title":"Calibrated Adversarial Refinement for Stochastic Semantic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13144","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":"sha256:76f22b770eef80711bf7758816be5f79d88313d9e88161f44b98a6d6100aec40","target":"record","created_at":"2026-07-05T03:03:17Z","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":"bcaeec68e88a9a0c3b276c66bb7f5f24333840a4c5bf8b1848cdc290a3b36d09","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-23T16:39:59Z","title_canon_sha256":"160817190b92874f02abbd53e1755989cfe1d821a329432327b89f097f9cf893"},"schema_version":"1.0","source":{"id":"2006.13144","kind":"arxiv","version":3}},"canonical_sha256":"1d51c18a178b12b2673fa3943087866a30ace8a292c8299e2027719adb761a5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d51c18a178b12b2673fa3943087866a30ace8a292c8299e2027719adb761a5c","first_computed_at":"2026-07-05T03:03:17.880907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:03:17.880907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yaWFc5nxfcSPUxlueiUXJ7oKKAhRaqqBO90+sAQNrQEPBgeXGdYtBn7kiYFYvwtaXMOO2LAFZsYCWhemrqm8BA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:03:17.881362Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.13144","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76f22b770eef80711bf7758816be5f79d88313d9e88161f44b98a6d6100aec40","sha256:0e55f6d97f0fc91144cced259506ebfb19ecd65c8a75d71b20fe154f3f0545c7"],"state_sha256":"3eff6ab891b9114781d6e05a353e5c9ee998d8713d80e5d0ecd11b20b506da24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YUdWqEMOL9nfVjdM2ietGwssbUYj+MtyuanQB30colBXIAXfhCU882veH0VrfDpTioKaMGUP83C4cebkhrVvCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T05:33:14.564165Z","bundle_sha256":"b43c5a831bfeebfa23acfce436d800b3dee9837a7cc1a6371b429a7aca969623"}}