{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:6FZIOH6DFTUBR3UDNFQEJE4J5N","short_pith_number":"pith:6FZIOH6D","canonical_record":{"source":{"id":"1702.02382","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-08T11:40:15Z","cross_cats_sorted":[],"title_canon_sha256":"2a201148b1ee59c000d19170472877ccea370aa11e97e99702bc4a3eb4bd9e82","abstract_canon_sha256":"7c3f696075556014a3eb495963ea8f93c68c544560ae1bfa16832234f6262f84"},"schema_version":"1.0"},"canonical_sha256":"f172871fc32ce818ee836960449389eb7881bc6e076901de8d1aa8c097c3863b","source":{"kind":"arxiv","id":"1702.02382","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.02382","created_at":"2026-05-18T00:51:06Z"},{"alias_kind":"arxiv_version","alias_value":"1702.02382v1","created_at":"2026-05-18T00:51:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.02382","created_at":"2026-05-18T00:51:06Z"},{"alias_kind":"pith_short_12","alias_value":"6FZIOH6DFTUB","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6FZIOH6DFTUBR3UD","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6FZIOH6D","created_at":"2026-05-18T12:31:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:6FZIOH6DFTUBR3UDNFQEJE4J5N","target":"record","payload":{"canonical_record":{"source":{"id":"1702.02382","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-08T11:40:15Z","cross_cats_sorted":[],"title_canon_sha256":"2a201148b1ee59c000d19170472877ccea370aa11e97e99702bc4a3eb4bd9e82","abstract_canon_sha256":"7c3f696075556014a3eb495963ea8f93c68c544560ae1bfa16832234f6262f84"},"schema_version":"1.0"},"canonical_sha256":"f172871fc32ce818ee836960449389eb7881bc6e076901de8d1aa8c097c3863b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:06.059674Z","signature_b64":"SswqPwRVZv3H590XWomXLr+TdSolG/tr9Gou7ub6vPiz3IcF7s0mlJET+Kh+bMV1K5DQ2pkfY/duUfaqXb8fCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f172871fc32ce818ee836960449389eb7881bc6e076901de8d1aa8c097c3863b","last_reissued_at":"2026-05-18T00:51:06.059230Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:06.059230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.02382","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":"2026-05-18T00:51:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jSXtBl5NX+NsDKi05rCvnj3njWXbuwjlYL/cKroKZ40TYzblBHbw45hlgUDjt6/IiVdEC4v2W3OLKiwTfqPEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T14:37:23.225939Z"},"content_sha256":"24888d54a04d178e15b4a13ad91b546f5db9c5fa4ed00ab05f616f6eda6754a3","schema_version":"1.0","event_id":"sha256:24888d54a04d178e15b4a13ad91b546f5db9c5fa4ed00ab05f616f6eda6754a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:6FZIOH6DFTUBR3UDNFQEJE4J5N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fr\\'ed\\'eric Jurie, Lo\\\"ic Simon, Mateusz Kozi\\'nski","submitted_at":"2017-02-08T11:40:15Z","abstract_excerpt":"We propose a method for semi-supervised training of structured-output neural networks. Inspired by the framework of Generative Adversarial Networks (GAN), we train a discriminator network to capture the notion of a quality of network output. To this end, we leverage the qualitative difference between outputs obtained on the labelled training data and unannotated data. We then use the discriminator as a source of error signal for unlabelled data. This effectively boosts the performance of a network on a held out test set. Initial experiments in image segmentation demonstrate that the proposed f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.02382","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":""},"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":"2026-05-18T00:51:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7w3M2zUKkr3QYqUSxph8YkyjgTdb9+5ukRDOMP3nP37qwedYJJnQKbjrixNkiDFNESiYNrGIP3XOkLY3Gi5EBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T14:37:23.226272Z"},"content_sha256":"5f4c1a01d10aa6b260e8e2825d25d86b03b0e7f2f9c37902d882ffecc5c1448e","schema_version":"1.0","event_id":"sha256:5f4c1a01d10aa6b260e8e2825d25d86b03b0e7f2f9c37902d882ffecc5c1448e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6FZIOH6DFTUBR3UDNFQEJE4J5N/bundle.json","state_url":"https://pith.science/pith/6FZIOH6DFTUBR3UDNFQEJE4J5N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6FZIOH6DFTUBR3UDNFQEJE4J5N/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":"2026-06-08T14:37:23Z","links":{"resolver":"https://pith.science/pith/6FZIOH6DFTUBR3UDNFQEJE4J5N","bundle":"https://pith.science/pith/6FZIOH6DFTUBR3UDNFQEJE4J5N/bundle.json","state":"https://pith.science/pith/6FZIOH6DFTUBR3UDNFQEJE4J5N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6FZIOH6DFTUBR3UDNFQEJE4J5N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:6FZIOH6DFTUBR3UDNFQEJE4J5N","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":"7c3f696075556014a3eb495963ea8f93c68c544560ae1bfa16832234f6262f84","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-08T11:40:15Z","title_canon_sha256":"2a201148b1ee59c000d19170472877ccea370aa11e97e99702bc4a3eb4bd9e82"},"schema_version":"1.0","source":{"id":"1702.02382","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.02382","created_at":"2026-05-18T00:51:06Z"},{"alias_kind":"arxiv_version","alias_value":"1702.02382v1","created_at":"2026-05-18T00:51:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.02382","created_at":"2026-05-18T00:51:06Z"},{"alias_kind":"pith_short_12","alias_value":"6FZIOH6DFTUB","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6FZIOH6DFTUBR3UD","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6FZIOH6D","created_at":"2026-05-18T12:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:5f4c1a01d10aa6b260e8e2825d25d86b03b0e7f2f9c37902d882ffecc5c1448e","target":"graph","created_at":"2026-05-18T00:51:06Z","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"},"paper":{"abstract_excerpt":"We propose a method for semi-supervised training of structured-output neural networks. Inspired by the framework of Generative Adversarial Networks (GAN), we train a discriminator network to capture the notion of a quality of network output. To this end, we leverage the qualitative difference between outputs obtained on the labelled training data and unannotated data. We then use the discriminator as a source of error signal for unlabelled data. This effectively boosts the performance of a network on a held out test set. Initial experiments in image segmentation demonstrate that the proposed f","authors_text":"Fr\\'ed\\'eric Jurie, Lo\\\"ic Simon, Mateusz Kozi\\'nski","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-08T11:40:15Z","title":"An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.02382","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":"sha256:24888d54a04d178e15b4a13ad91b546f5db9c5fa4ed00ab05f616f6eda6754a3","target":"record","created_at":"2026-05-18T00:51:06Z","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":"7c3f696075556014a3eb495963ea8f93c68c544560ae1bfa16832234f6262f84","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-08T11:40:15Z","title_canon_sha256":"2a201148b1ee59c000d19170472877ccea370aa11e97e99702bc4a3eb4bd9e82"},"schema_version":"1.0","source":{"id":"1702.02382","kind":"arxiv","version":1}},"canonical_sha256":"f172871fc32ce818ee836960449389eb7881bc6e076901de8d1aa8c097c3863b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f172871fc32ce818ee836960449389eb7881bc6e076901de8d1aa8c097c3863b","first_computed_at":"2026-05-18T00:51:06.059230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:51:06.059230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SswqPwRVZv3H590XWomXLr+TdSolG/tr9Gou7ub6vPiz3IcF7s0mlJET+Kh+bMV1K5DQ2pkfY/duUfaqXb8fCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:51:06.059674Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.02382","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24888d54a04d178e15b4a13ad91b546f5db9c5fa4ed00ab05f616f6eda6754a3","sha256:5f4c1a01d10aa6b260e8e2825d25d86b03b0e7f2f9c37902d882ffecc5c1448e"],"state_sha256":"2a35be25a2f50b1b1d3552caf1d5b1b68d6379d4a1ac0b45e412475236339a83"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SUZNAOuyfHnicLh5QBP+KXrbT9MXkBWh50fXLewnKCl81F/+dUoqfLDT8/ftZ/sGpRk5jwHqCrRk5tWijPI8BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T14:37:23.228531Z","bundle_sha256":"d18ea9336bc3abf5b00b84cef538b4eff3759d30a43a45510f883679568f7a91"}}