{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:B3V4B6GGHN6N5CV7YNMVFCWC4C","short_pith_number":"pith:B3V4B6GG","canonical_record":{"source":{"id":"2412.19543","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T09:10:30Z","cross_cats_sorted":[],"title_canon_sha256":"a927d900af6ee42a6897667d5a12ff3fd25aadfe8bca3b1b5b80fb32e7a34218","abstract_canon_sha256":"a749ebd121c5bfa26e4b806544b5748efe02c84f36c18c019249529beef6bfbf"},"schema_version":"1.0"},"canonical_sha256":"0eebc0f8c63b7cde8abfc359528ac2e0b326895300dc506812a9cfdc2b67a3c8","source":{"kind":"arxiv","id":"2412.19543","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19543","created_at":"2026-07-05T09:57:49Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19543v2","created_at":"2026-07-05T09:57:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19543","created_at":"2026-07-05T09:57:49Z"},{"alias_kind":"pith_short_12","alias_value":"B3V4B6GGHN6N","created_at":"2026-07-05T09:57:49Z"},{"alias_kind":"pith_short_16","alias_value":"B3V4B6GGHN6N5CV7","created_at":"2026-07-05T09:57:49Z"},{"alias_kind":"pith_short_8","alias_value":"B3V4B6GG","created_at":"2026-07-05T09:57:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:B3V4B6GGHN6N5CV7YNMVFCWC4C","target":"record","payload":{"canonical_record":{"source":{"id":"2412.19543","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T09:10:30Z","cross_cats_sorted":[],"title_canon_sha256":"a927d900af6ee42a6897667d5a12ff3fd25aadfe8bca3b1b5b80fb32e7a34218","abstract_canon_sha256":"a749ebd121c5bfa26e4b806544b5748efe02c84f36c18c019249529beef6bfbf"},"schema_version":"1.0"},"canonical_sha256":"0eebc0f8c63b7cde8abfc359528ac2e0b326895300dc506812a9cfdc2b67a3c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:49.875181Z","signature_b64":"6SqjKuoO8mo+OmdLNg9MDPNFuszxLjPNAgp5bnF4hXbr7QwyqF44UzD9r5F2lUwupw1nB3xnLmrJoJXZVGhLDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0eebc0f8c63b7cde8abfc359528ac2e0b326895300dc506812a9cfdc2b67a3c8","last_reissued_at":"2026-07-05T09:57:49.874676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:49.874676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.19543","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:57:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"URgzmvRqOkjIluKQ50UM5/B55rAgVGaQgD/Dv2pg29lVj52Xqw7gpJ0/g3Wg6mQlDAeNS5n8ol+TKRZ7dYMPBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T14:03:14.519788Z"},"content_sha256":"ffefefab46d69037ca3c5b6f631d1434dbba8d0da22bafcb473f70936f7c8ab5","schema_version":"1.0","event_id":"sha256:ffefefab46d69037ca3c5b6f631d1434dbba8d0da22bafcb473f70936f7c8ab5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:B3V4B6GGHN6N5CV7YNMVFCWC4C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diverse Rare Sample Generation with Pretrained GANs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jaesik Choi, Jiyeon Han, Soyeon Kim, SuBeen Lee","submitted_at":"2024-12-27T09:10:30Z","abstract_excerpt":"Deep generative models are proficient in generating realistic data but struggle with producing rare samples in low density regions due to their scarcity of training datasets and the mode collapse problem. While recent methods aim to improve the fidelity of generated samples, they often reduce diversity and coverage by ignoring rare and novel samples. This study proposes a novel approach for generating diverse rare samples from high-resolution image datasets with pretrained GANs. Our method employs gradient-based optimization of latent vectors within a multi-objective framework and utilizes nor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19543","kind":"arxiv","version":2},"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/2412.19543/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":"2026-07-05T09:57:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l+uYmn2thuYuEfwAgY/SzF/BtolqaMjXaPQ5ZF+XilRjunXnZKgx29FSdgaJnbKkXtmz2DCWGZQbxcfpjtm0CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T14:03:14.520316Z"},"content_sha256":"57e9c9579a927eba2548d47276a4508f1ed7e988c597fe345b03bc6e5a309d57","schema_version":"1.0","event_id":"sha256:57e9c9579a927eba2548d47276a4508f1ed7e988c597fe345b03bc6e5a309d57"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B3V4B6GGHN6N5CV7YNMVFCWC4C/bundle.json","state_url":"https://pith.science/pith/B3V4B6GGHN6N5CV7YNMVFCWC4C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B3V4B6GGHN6N5CV7YNMVFCWC4C/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":"2026-08-12T14:03:14Z","links":{"resolver":"https://pith.science/pith/B3V4B6GGHN6N5CV7YNMVFCWC4C","bundle":"https://pith.science/pith/B3V4B6GGHN6N5CV7YNMVFCWC4C/bundle.json","state":"https://pith.science/pith/B3V4B6GGHN6N5CV7YNMVFCWC4C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B3V4B6GGHN6N5CV7YNMVFCWC4C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B3V4B6GGHN6N5CV7YNMVFCWC4C","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":"a749ebd121c5bfa26e4b806544b5748efe02c84f36c18c019249529beef6bfbf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T09:10:30Z","title_canon_sha256":"a927d900af6ee42a6897667d5a12ff3fd25aadfe8bca3b1b5b80fb32e7a34218"},"schema_version":"1.0","source":{"id":"2412.19543","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19543","created_at":"2026-07-05T09:57:49Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19543v2","created_at":"2026-07-05T09:57:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19543","created_at":"2026-07-05T09:57:49Z"},{"alias_kind":"pith_short_12","alias_value":"B3V4B6GGHN6N","created_at":"2026-07-05T09:57:49Z"},{"alias_kind":"pith_short_16","alias_value":"B3V4B6GGHN6N5CV7","created_at":"2026-07-05T09:57:49Z"},{"alias_kind":"pith_short_8","alias_value":"B3V4B6GG","created_at":"2026-07-05T09:57:49Z"}],"graph_snapshots":[{"event_id":"sha256:57e9c9579a927eba2548d47276a4508f1ed7e988c597fe345b03bc6e5a309d57","target":"graph","created_at":"2026-07-05T09:57:49Z","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/2412.19543/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep generative models are proficient in generating realistic data but struggle with producing rare samples in low density regions due to their scarcity of training datasets and the mode collapse problem. While recent methods aim to improve the fidelity of generated samples, they often reduce diversity and coverage by ignoring rare and novel samples. This study proposes a novel approach for generating diverse rare samples from high-resolution image datasets with pretrained GANs. Our method employs gradient-based optimization of latent vectors within a multi-objective framework and utilizes nor","authors_text":"Jaesik Choi, Jiyeon Han, Soyeon Kim, SuBeen Lee","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T09:10:30Z","title":"Diverse Rare Sample Generation with Pretrained GANs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19543","kind":"arxiv","version":2},"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:ffefefab46d69037ca3c5b6f631d1434dbba8d0da22bafcb473f70936f7c8ab5","target":"record","created_at":"2026-07-05T09:57:49Z","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":"a749ebd121c5bfa26e4b806544b5748efe02c84f36c18c019249529beef6bfbf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T09:10:30Z","title_canon_sha256":"a927d900af6ee42a6897667d5a12ff3fd25aadfe8bca3b1b5b80fb32e7a34218"},"schema_version":"1.0","source":{"id":"2412.19543","kind":"arxiv","version":2}},"canonical_sha256":"0eebc0f8c63b7cde8abfc359528ac2e0b326895300dc506812a9cfdc2b67a3c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0eebc0f8c63b7cde8abfc359528ac2e0b326895300dc506812a9cfdc2b67a3c8","first_computed_at":"2026-07-05T09:57:49.874676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:49.874676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6SqjKuoO8mo+OmdLNg9MDPNFuszxLjPNAgp5bnF4hXbr7QwyqF44UzD9r5F2lUwupw1nB3xnLmrJoJXZVGhLDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:49.875181Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19543","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ffefefab46d69037ca3c5b6f631d1434dbba8d0da22bafcb473f70936f7c8ab5","sha256:57e9c9579a927eba2548d47276a4508f1ed7e988c597fe345b03bc6e5a309d57"],"state_sha256":"dbe05b9e8a6ee6329fd78061e7c984f91677052b579d165da00774169e6c2b86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xVg2uSFZ9SuAb8gd6GbxGDWTxyZj0Qkp7V2PYNN5yfuIJvcXrAGe+yTW5v/7mnh9Iz6oHe8fu1A78s+Xa6hLAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T14:03:14.525123Z","bundle_sha256":"baaa5a9b3bd68e7a5416bf10a93e7b105968c1f6ac352926550163f34e0ec424"}}