{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:CRS7JZHDJE6UV45UM7WB7GCB5O","short_pith_number":"pith:CRS7JZHD","canonical_record":{"source":{"id":"1910.08540","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-18T05:47:08Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"b9c4b35ce6eba6e7453ca0f0ef256532bc8f833e0b2555c441b26029435bb429","abstract_canon_sha256":"67ec7d049c0465626506c5682c6f3046afdcb9c165d33e713f8833bb36168d27"},"schema_version":"1.0"},"canonical_sha256":"1465f4e4e3493d4af3b467ec1f9841eba8562f2d390f971203ef1faa786d544b","source":{"kind":"arxiv","id":"1910.08540","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.08540","created_at":"2026-07-05T00:13:17Z"},{"alias_kind":"arxiv_version","alias_value":"1910.08540v1","created_at":"2026-07-05T00:13:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.08540","created_at":"2026-07-05T00:13:17Z"},{"alias_kind":"pith_short_12","alias_value":"CRS7JZHDJE6U","created_at":"2026-07-05T00:13:17Z"},{"alias_kind":"pith_short_16","alias_value":"CRS7JZHDJE6UV45U","created_at":"2026-07-05T00:13:17Z"},{"alias_kind":"pith_short_8","alias_value":"CRS7JZHD","created_at":"2026-07-05T00:13:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:CRS7JZHDJE6UV45UM7WB7GCB5O","target":"record","payload":{"canonical_record":{"source":{"id":"1910.08540","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-18T05:47:08Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"b9c4b35ce6eba6e7453ca0f0ef256532bc8f833e0b2555c441b26029435bb429","abstract_canon_sha256":"67ec7d049c0465626506c5682c6f3046afdcb9c165d33e713f8833bb36168d27"},"schema_version":"1.0"},"canonical_sha256":"1465f4e4e3493d4af3b467ec1f9841eba8562f2d390f971203ef1faa786d544b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:13:17.479095Z","signature_b64":"Law4PzyHIWuV1bWjPiQeQlfcL+sEu5F6XHPXGhfNx0GASUmMS1VkfIW8ODsXIlkzUppUYSEQcgfJvPbhvDKqDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1465f4e4e3493d4af3b467ec1f9841eba8562f2d390f971203ef1faa786d544b","last_reissued_at":"2026-07-05T00:13:17.478695Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:13:17.478695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.08540","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":"2026-07-05T00:13:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qJU+emvPjmgmuu+NzahJeQm7BYqdJq0+MO9C2dw3ZIvG2NrwJIR/FnpEv6UO2aGsQgWbn4l5BxXH4atznsbaDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:38:24.023573Z"},"content_sha256":"77410e368814eb11d58124577058e1362bba3c20ac6d21356b2993be0e121b27","schema_version":"1.0","event_id":"sha256:77410e368814eb11d58124577058e1362bba3c20ac6d21356b2993be0e121b27"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:CRS7JZHDJE6UV45UM7WB7GCB5O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-supervised Learning using Adversarial Training with Good and Bad Samples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Corey W. Arnold, Jiayun Li, Mingyuan Zhou, Wenyuan Li, William Speier, Yuguang Yue, Zichen Wang","submitted_at":"2019-10-18T05:47:08Z","abstract_excerpt":"In this work, we investigate semi-supervised learning (SSL) for image classification using adversarial training. Previous results have illustrated that generative adversarial networks (GANs) can be used for multiple purposes. Triple-GAN, which aims to jointly optimize model components by incorporating three players, generates suitable image-label pairs to compensate for the lack of labeled data in SSL with improved benchmark performance. Conversely, Bad (or complementary) GAN, optimizes generation to produce complementary data-label pairs and force a classifier's decision boundary to lie betwe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.08540","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/1910.08540/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":"2026-07-05T00:13:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bIfHBVYF00ucpX83wFjlQwBD1QKK9/aycxZMn4B8ox6AEcsXm66L/UZ9HZm2L+I+mPjd8+qecrnBM4GN9llSDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:38:24.023963Z"},"content_sha256":"36456aa1d48e8d68c9782a5aa024760903d4e6276162565076c7bab1c6c280c9","schema_version":"1.0","event_id":"sha256:36456aa1d48e8d68c9782a5aa024760903d4e6276162565076c7bab1c6c280c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CRS7JZHDJE6UV45UM7WB7GCB5O/bundle.json","state_url":"https://pith.science/pith/CRS7JZHDJE6UV45UM7WB7GCB5O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CRS7JZHDJE6UV45UM7WB7GCB5O/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":"2026-08-17T07:38:24Z","links":{"resolver":"https://pith.science/pith/CRS7JZHDJE6UV45UM7WB7GCB5O","bundle":"https://pith.science/pith/CRS7JZHDJE6UV45UM7WB7GCB5O/bundle.json","state":"https://pith.science/pith/CRS7JZHDJE6UV45UM7WB7GCB5O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CRS7JZHDJE6UV45UM7WB7GCB5O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:CRS7JZHDJE6UV45UM7WB7GCB5O","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":"67ec7d049c0465626506c5682c6f3046afdcb9c165d33e713f8833bb36168d27","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-18T05:47:08Z","title_canon_sha256":"b9c4b35ce6eba6e7453ca0f0ef256532bc8f833e0b2555c441b26029435bb429"},"schema_version":"1.0","source":{"id":"1910.08540","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.08540","created_at":"2026-07-05T00:13:17Z"},{"alias_kind":"arxiv_version","alias_value":"1910.08540v1","created_at":"2026-07-05T00:13:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.08540","created_at":"2026-07-05T00:13:17Z"},{"alias_kind":"pith_short_12","alias_value":"CRS7JZHDJE6U","created_at":"2026-07-05T00:13:17Z"},{"alias_kind":"pith_short_16","alias_value":"CRS7JZHDJE6UV45U","created_at":"2026-07-05T00:13:17Z"},{"alias_kind":"pith_short_8","alias_value":"CRS7JZHD","created_at":"2026-07-05T00:13:17Z"}],"graph_snapshots":[{"event_id":"sha256:36456aa1d48e8d68c9782a5aa024760903d4e6276162565076c7bab1c6c280c9","target":"graph","created_at":"2026-07-05T00:13:17Z","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/1910.08540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we investigate semi-supervised learning (SSL) for image classification using adversarial training. Previous results have illustrated that generative adversarial networks (GANs) can be used for multiple purposes. Triple-GAN, which aims to jointly optimize model components by incorporating three players, generates suitable image-label pairs to compensate for the lack of labeled data in SSL with improved benchmark performance. Conversely, Bad (or complementary) GAN, optimizes generation to produce complementary data-label pairs and force a classifier's decision boundary to lie betwe","authors_text":"Corey W. Arnold, Jiayun Li, Mingyuan Zhou, Wenyuan Li, William Speier, Yuguang Yue, Zichen Wang","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-18T05:47:08Z","title":"Semi-supervised Learning using Adversarial Training with Good and Bad Samples"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.08540","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":"sha256:77410e368814eb11d58124577058e1362bba3c20ac6d21356b2993be0e121b27","target":"record","created_at":"2026-07-05T00:13:17Z","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":"67ec7d049c0465626506c5682c6f3046afdcb9c165d33e713f8833bb36168d27","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-18T05:47:08Z","title_canon_sha256":"b9c4b35ce6eba6e7453ca0f0ef256532bc8f833e0b2555c441b26029435bb429"},"schema_version":"1.0","source":{"id":"1910.08540","kind":"arxiv","version":1}},"canonical_sha256":"1465f4e4e3493d4af3b467ec1f9841eba8562f2d390f971203ef1faa786d544b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1465f4e4e3493d4af3b467ec1f9841eba8562f2d390f971203ef1faa786d544b","first_computed_at":"2026-07-05T00:13:17.478695Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:13:17.478695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Law4PzyHIWuV1bWjPiQeQlfcL+sEu5F6XHPXGhfNx0GASUmMS1VkfIW8ODsXIlkzUppUYSEQcgfJvPbhvDKqDw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:13:17.479095Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.08540","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77410e368814eb11d58124577058e1362bba3c20ac6d21356b2993be0e121b27","sha256:36456aa1d48e8d68c9782a5aa024760903d4e6276162565076c7bab1c6c280c9"],"state_sha256":"3520d456988b5a84efc590b1e5e505355f7a6b982115b798e117be812d1095a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N+/CeZbLkceE2HcaS+T0TDs0fK9PkqKoLtseHccgV+f42ZNjnrjrnyh2EvdOE29+hrLgbC0xQF3FI7dOymTZDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T07:38:24.026761Z","bundle_sha256":"5ed8c2c16966adf9909d3a3aa251bad3077dbe294a3cca7157aeede8d9a5bb06"}}