{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AF7OQMR6WP6BHK2HGI3DUECQOK","short_pith_number":"pith:AF7OQMR6","canonical_record":{"source":{"id":"2407.18467","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-26T02:28:32Z","cross_cats_sorted":[],"title_canon_sha256":"512c1cb140838b987c6579e697ca947153dd0977400367db4fa8c6bf7f871650","abstract_canon_sha256":"6b8edd34f2b1ac6c59171162e80eeb09bcb427c942114df06be7bfab71b967fb"},"schema_version":"1.0"},"canonical_sha256":"017ee8323eb3fc13ab4732363a10507286288100dbe0107717d6ce8c9bfd0e6b","source":{"kind":"arxiv","id":"2407.18467","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18467","created_at":"2026-07-05T08:48:50Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18467v1","created_at":"2026-07-05T08:48:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18467","created_at":"2026-07-05T08:48:50Z"},{"alias_kind":"pith_short_12","alias_value":"AF7OQMR6WP6B","created_at":"2026-07-05T08:48:50Z"},{"alias_kind":"pith_short_16","alias_value":"AF7OQMR6WP6BHK2H","created_at":"2026-07-05T08:48:50Z"},{"alias_kind":"pith_short_8","alias_value":"AF7OQMR6","created_at":"2026-07-05T08:48:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AF7OQMR6WP6BHK2HGI3DUECQOK","target":"record","payload":{"canonical_record":{"source":{"id":"2407.18467","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-26T02:28:32Z","cross_cats_sorted":[],"title_canon_sha256":"512c1cb140838b987c6579e697ca947153dd0977400367db4fa8c6bf7f871650","abstract_canon_sha256":"6b8edd34f2b1ac6c59171162e80eeb09bcb427c942114df06be7bfab71b967fb"},"schema_version":"1.0"},"canonical_sha256":"017ee8323eb3fc13ab4732363a10507286288100dbe0107717d6ce8c9bfd0e6b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:50.006207Z","signature_b64":"FeffIeqYx6qHoimKrLyViqx/UOxFBfp8OxRtKc52fxZbmrloiQpAeZQborpllq/q40W/UJP4Y3o6JUTpeyucBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"017ee8323eb3fc13ab4732363a10507286288100dbe0107717d6ce8c9bfd0e6b","last_reissued_at":"2026-07-05T08:48:50.005807Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:50.005807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.18467","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":"2026-07-05T08:48:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v5QSwnLs90Wq84cwePVtADb8jWpSyoi9CgEQelhy6DKlMJPIlXsR8l+1VPddqRYp1IE1W7uiWO7OtMnnhyy/DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T21:05:34.770861Z"},"content_sha256":"a15dbc6d4dd64c7129aeecc04761396b28513e6f043ed30170896a3bb45c3d8a","schema_version":"1.0","event_id":"sha256:a15dbc6d4dd64c7129aeecc04761396b28513e6f043ed30170896a3bb45c3d8a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AF7OQMR6WP6BHK2HGI3DUECQOK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Machine Unlearning using a Multi-GAN based Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amartya Hatua, Andrew H. Sung, Trung T. Nguyen","submitted_at":"2024-07-26T02:28:32Z","abstract_excerpt":"This article presents a new machine unlearning approach that utilizes multiple Generative Adversarial Network (GAN) based models. The proposed method comprises two phases: i) data reorganization in which synthetic data using the GAN model is introduced with inverted class labels of the forget datasets, and ii) fine-tuning the pre-trained model. The GAN models consist of two pairs of generators and discriminators. The generator discriminator pairs generate synthetic data for the retain and forget datasets. Then, a pre-trained model is utilized to get the class labels of the synthetic datasets. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18467","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/2407.18467/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":"2026-07-05T08:48:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GDg6CnQYaYvYHxol5sl9tSVkfGp0/eQlp7w4DIf5XU3sYHBzpX4hOYG608IrnN+hQ3nUj4bhIs8LE8IqWJy+CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T21:05:34.771685Z"},"content_sha256":"921ec3133c073470ef166cf6b49ac526aace5632cb422873febe93fb543ac686","schema_version":"1.0","event_id":"sha256:921ec3133c073470ef166cf6b49ac526aace5632cb422873febe93fb543ac686"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AF7OQMR6WP6BHK2HGI3DUECQOK/bundle.json","state_url":"https://pith.science/pith/AF7OQMR6WP6BHK2HGI3DUECQOK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AF7OQMR6WP6BHK2HGI3DUECQOK/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":"2026-08-12T21:05:34Z","links":{"resolver":"https://pith.science/pith/AF7OQMR6WP6BHK2HGI3DUECQOK","bundle":"https://pith.science/pith/AF7OQMR6WP6BHK2HGI3DUECQOK/bundle.json","state":"https://pith.science/pith/AF7OQMR6WP6BHK2HGI3DUECQOK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AF7OQMR6WP6BHK2HGI3DUECQOK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AF7OQMR6WP6BHK2HGI3DUECQOK","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":"6b8edd34f2b1ac6c59171162e80eeb09bcb427c942114df06be7bfab71b967fb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-26T02:28:32Z","title_canon_sha256":"512c1cb140838b987c6579e697ca947153dd0977400367db4fa8c6bf7f871650"},"schema_version":"1.0","source":{"id":"2407.18467","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18467","created_at":"2026-07-05T08:48:50Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18467v1","created_at":"2026-07-05T08:48:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18467","created_at":"2026-07-05T08:48:50Z"},{"alias_kind":"pith_short_12","alias_value":"AF7OQMR6WP6B","created_at":"2026-07-05T08:48:50Z"},{"alias_kind":"pith_short_16","alias_value":"AF7OQMR6WP6BHK2H","created_at":"2026-07-05T08:48:50Z"},{"alias_kind":"pith_short_8","alias_value":"AF7OQMR6","created_at":"2026-07-05T08:48:50Z"}],"graph_snapshots":[{"event_id":"sha256:921ec3133c073470ef166cf6b49ac526aace5632cb422873febe93fb543ac686","target":"graph","created_at":"2026-07-05T08:48:50Z","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/2407.18467/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This article presents a new machine unlearning approach that utilizes multiple Generative Adversarial Network (GAN) based models. The proposed method comprises two phases: i) data reorganization in which synthetic data using the GAN model is introduced with inverted class labels of the forget datasets, and ii) fine-tuning the pre-trained model. The GAN models consist of two pairs of generators and discriminators. The generator discriminator pairs generate synthetic data for the retain and forget datasets. Then, a pre-trained model is utilized to get the class labels of the synthetic datasets. ","authors_text":"Amartya Hatua, Andrew H. Sung, Trung T. Nguyen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-26T02:28:32Z","title":"Machine Unlearning using a Multi-GAN based Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18467","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:a15dbc6d4dd64c7129aeecc04761396b28513e6f043ed30170896a3bb45c3d8a","target":"record","created_at":"2026-07-05T08:48:50Z","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":"6b8edd34f2b1ac6c59171162e80eeb09bcb427c942114df06be7bfab71b967fb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-26T02:28:32Z","title_canon_sha256":"512c1cb140838b987c6579e697ca947153dd0977400367db4fa8c6bf7f871650"},"schema_version":"1.0","source":{"id":"2407.18467","kind":"arxiv","version":1}},"canonical_sha256":"017ee8323eb3fc13ab4732363a10507286288100dbe0107717d6ce8c9bfd0e6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"017ee8323eb3fc13ab4732363a10507286288100dbe0107717d6ce8c9bfd0e6b","first_computed_at":"2026-07-05T08:48:50.005807Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:50.005807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FeffIeqYx6qHoimKrLyViqx/UOxFBfp8OxRtKc52fxZbmrloiQpAeZQborpllq/q40W/UJP4Y3o6JUTpeyucBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:50.006207Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.18467","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a15dbc6d4dd64c7129aeecc04761396b28513e6f043ed30170896a3bb45c3d8a","sha256:921ec3133c073470ef166cf6b49ac526aace5632cb422873febe93fb543ac686"],"state_sha256":"1117b02ceff43df1976e9c6b30bcf1cf1b0f5652c7f33c8ef492419a5a26a10f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kW+ZU8KDn8M84DVeDevJ22JSQU5RTK+a18dt79wR0UnXZ0pbT8g4papuAtRKqXRUWbak5Ek+O9YREav7B35SCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T21:05:34.777365Z","bundle_sha256":"93dfbf6fbe3331f2be787e3d003c9aecc300e121730e2c5e7984853025a4098c"}}