{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:5ETPYPRDLIBGRIJXLNBMDFE6OJ","short_pith_number":"pith:5ETPYPRD","canonical_record":{"source":{"id":"2012.09673","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-17T15:40:27Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"0ba3a622019c07c862e8fee59b0e709bafb5a5bbb0d67199e12b8b892b9bbb97","abstract_canon_sha256":"800095e35d0f248fc4fb519d2443ef373d838c736c8113bd1abfb51ef2405aca"},"schema_version":"1.0"},"canonical_sha256":"e926fc3e235a0268a1375b42c1949e7246d863d45c902c99b7a0dcd80807cfc7","source":{"kind":"arxiv","id":"2012.09673","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.09673","created_at":"2026-07-05T02:00:20Z"},{"alias_kind":"arxiv_version","alias_value":"2012.09673v1","created_at":"2026-07-05T02:00:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.09673","created_at":"2026-07-05T02:00:20Z"},{"alias_kind":"pith_short_12","alias_value":"5ETPYPRDLIBG","created_at":"2026-07-05T02:00:20Z"},{"alias_kind":"pith_short_16","alias_value":"5ETPYPRDLIBGRIJX","created_at":"2026-07-05T02:00:20Z"},{"alias_kind":"pith_short_8","alias_value":"5ETPYPRD","created_at":"2026-07-05T02:00:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:5ETPYPRDLIBGRIJXLNBMDFE6OJ","target":"record","payload":{"canonical_record":{"source":{"id":"2012.09673","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-17T15:40:27Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"0ba3a622019c07c862e8fee59b0e709bafb5a5bbb0d67199e12b8b892b9bbb97","abstract_canon_sha256":"800095e35d0f248fc4fb519d2443ef373d838c736c8113bd1abfb51ef2405aca"},"schema_version":"1.0"},"canonical_sha256":"e926fc3e235a0268a1375b42c1949e7246d863d45c902c99b7a0dcd80807cfc7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:00:20.071786Z","signature_b64":"73CaAtDBbRTGCfZT8Zrdz0YLR7Tnb2p699j4n93Bn1TQ1OjxemmsnK80CKvk4XoqwSwbIuxCeCnO6aCOoKLNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e926fc3e235a0268a1375b42c1949e7246d863d45c902c99b7a0dcd80807cfc7","last_reissued_at":"2026-07-05T02:00:20.071212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:00:20.071212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.09673","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":"2026-07-05T02:00:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IL7fi9MLOlzpu706jhdTcS10XCXrvyB28X9Z5rDsa4v9Po7LQApmWrg/vLxwtM6LlCoaG8Zx/kUN/4obT52hCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:57:47.439901Z"},"content_sha256":"9d9984b7d07b1189e9968974e36dd5c3cd5639907fd3c6c4c42898fe3976c59f","schema_version":"1.0","event_id":"sha256:9d9984b7d07b1189e9968974e36dd5c3cd5639907fd3c6c4c42898fe3976c59f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:5ETPYPRDLIBGRIJXLNBMDFE6OJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Combating Mode Collapse in GAN training: An Empirical Analysis using Hessian Eigenvalues","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Avraam Chatzimichailidis, Janis Keuper, Peter Labus, Ricard Durall","submitted_at":"2020-12-17T15:40:27Z","abstract_excerpt":"Generative adversarial networks (GANs) provide state-of-the-art results in image generation. However, despite being so powerful, they still remain very challenging to train. This is in particular caused by their highly non-convex optimization space leading to a number of instabilities. Among them, mode collapse stands out as one of the most daunting ones. This undesirable event occurs when the model can only fit a few modes of the data distribution, while ignoring the majority of them. In this work, we combat mode collapse using second-order gradient information. To do so, we analyse the loss "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.09673","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/2012.09673/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":"2026-07-05T02:00:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iJgBJb3KnoSILlw9VFZQR+SKBwOOtN4Rzsgqj3AiDWXs0WRA1Pw4ogO2ToEZ7CYSGLgxWWdH6YARdw5OabZWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:57:47.440280Z"},"content_sha256":"94ef02fb0c1aedc837610d77db236a7109fa5bf075b73736d460c2e1c1a52053","schema_version":"1.0","event_id":"sha256:94ef02fb0c1aedc837610d77db236a7109fa5bf075b73736d460c2e1c1a52053"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5ETPYPRDLIBGRIJXLNBMDFE6OJ/bundle.json","state_url":"https://pith.science/pith/5ETPYPRDLIBGRIJXLNBMDFE6OJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5ETPYPRDLIBGRIJXLNBMDFE6OJ/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":"2026-08-05T22:57:47Z","links":{"resolver":"https://pith.science/pith/5ETPYPRDLIBGRIJXLNBMDFE6OJ","bundle":"https://pith.science/pith/5ETPYPRDLIBGRIJXLNBMDFE6OJ/bundle.json","state":"https://pith.science/pith/5ETPYPRDLIBGRIJXLNBMDFE6OJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5ETPYPRDLIBGRIJXLNBMDFE6OJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:5ETPYPRDLIBGRIJXLNBMDFE6OJ","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":"800095e35d0f248fc4fb519d2443ef373d838c736c8113bd1abfb51ef2405aca","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-17T15:40:27Z","title_canon_sha256":"0ba3a622019c07c862e8fee59b0e709bafb5a5bbb0d67199e12b8b892b9bbb97"},"schema_version":"1.0","source":{"id":"2012.09673","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.09673","created_at":"2026-07-05T02:00:20Z"},{"alias_kind":"arxiv_version","alias_value":"2012.09673v1","created_at":"2026-07-05T02:00:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.09673","created_at":"2026-07-05T02:00:20Z"},{"alias_kind":"pith_short_12","alias_value":"5ETPYPRDLIBG","created_at":"2026-07-05T02:00:20Z"},{"alias_kind":"pith_short_16","alias_value":"5ETPYPRDLIBGRIJX","created_at":"2026-07-05T02:00:20Z"},{"alias_kind":"pith_short_8","alias_value":"5ETPYPRD","created_at":"2026-07-05T02:00:20Z"}],"graph_snapshots":[{"event_id":"sha256:94ef02fb0c1aedc837610d77db236a7109fa5bf075b73736d460c2e1c1a52053","target":"graph","created_at":"2026-07-05T02:00:20Z","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/2012.09673/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative adversarial networks (GANs) provide state-of-the-art results in image generation. However, despite being so powerful, they still remain very challenging to train. This is in particular caused by their highly non-convex optimization space leading to a number of instabilities. Among them, mode collapse stands out as one of the most daunting ones. This undesirable event occurs when the model can only fit a few modes of the data distribution, while ignoring the majority of them. In this work, we combat mode collapse using second-order gradient information. To do so, we analyse the loss ","authors_text":"Avraam Chatzimichailidis, Janis Keuper, Peter Labus, Ricard Durall","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-17T15:40:27Z","title":"Combating Mode Collapse in GAN training: An Empirical Analysis using Hessian Eigenvalues"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.09673","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":"sha256:9d9984b7d07b1189e9968974e36dd5c3cd5639907fd3c6c4c42898fe3976c59f","target":"record","created_at":"2026-07-05T02:00:20Z","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":"800095e35d0f248fc4fb519d2443ef373d838c736c8113bd1abfb51ef2405aca","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-17T15:40:27Z","title_canon_sha256":"0ba3a622019c07c862e8fee59b0e709bafb5a5bbb0d67199e12b8b892b9bbb97"},"schema_version":"1.0","source":{"id":"2012.09673","kind":"arxiv","version":1}},"canonical_sha256":"e926fc3e235a0268a1375b42c1949e7246d863d45c902c99b7a0dcd80807cfc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e926fc3e235a0268a1375b42c1949e7246d863d45c902c99b7a0dcd80807cfc7","first_computed_at":"2026-07-05T02:00:20.071212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:00:20.071212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"73CaAtDBbRTGCfZT8Zrdz0YLR7Tnb2p699j4n93Bn1TQ1OjxemmsnK80CKvk4XoqwSwbIuxCeCnO6aCOoKLNDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:00:20.071786Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.09673","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d9984b7d07b1189e9968974e36dd5c3cd5639907fd3c6c4c42898fe3976c59f","sha256:94ef02fb0c1aedc837610d77db236a7109fa5bf075b73736d460c2e1c1a52053"],"state_sha256":"4f9e3c103ba201ab86ace18100b85d5e5bef6e5c478b842740277a1fb85537df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M9z/4WLeb0WYCKrhZrsCBoj+AFnJiEk+PseWK9Fhi0UHzXJyTyuBmixPgPr89NA2iGvmVyZ760ZGpUuRvRosAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:57:47.442550Z","bundle_sha256":"ebbde92c49b77408c70614d3a5f4e943026fc5fa502b3488f3d2ac4d36b7439f"}}