{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JSHSQAJ6FENOQBNIZV47W3QV5I","short_pith_number":"pith:JSHSQAJ6","schema_version":"1.0","canonical_sha256":"4c8f28013e291ae805a8cd79fb6e15ea1254825806532912afe7a0a2f58e8cac","source":{"kind":"arxiv","id":"2105.04801","version":2},"attestation_state":"computed","paper":{"title":"On Characterizing GAN Convergence Through Proximal Duality Gap","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aroof Aimen, Narayanan C. Krishnan, Sahil Sidheekh","submitted_at":"2021-05-11T06:27:27Z","abstract_excerpt":"Despite the accomplishments of Generative Adversarial Networks (GANs) in modeling data distributions, training them remains a challenging task. A contributing factor to this difficulty is the non-intuitive nature of the GAN loss curves, which necessitates a subjective evaluation of the generated output to infer training progress. Recently, motivated by game theory, duality gap has been proposed as a domain agnostic measure to monitor GAN training. However, it is restricted to the setting when the GAN converges to a Nash equilibrium. But GANs need not always converge to a Nash equilibrium to mo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2105.04801","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-11T06:27:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f48d4586b3ea99686ea0ef02c4cbf751e4f38af0b64d2eac48ca816b344f2792","abstract_canon_sha256":"501fe8bd1b94ad630a1ba00f8f5aa5bef6cb39d3bce30f63a2be0983830f9196"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:58.136728Z","signature_b64":"bVicxBaIN9QCWlv9DMFO0w3EM5JP3pARmoTNVD7140H7e+JqZr4rxVZrwnQxpwql2sbL6sxHK7jdHM9FCx+wAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c8f28013e291ae805a8cd79fb6e15ea1254825806532912afe7a0a2f58e8cac","last_reissued_at":"2026-07-05T02:56:58.136242Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:58.136242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Characterizing GAN Convergence Through Proximal Duality Gap","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aroof Aimen, Narayanan C. Krishnan, Sahil Sidheekh","submitted_at":"2021-05-11T06:27:27Z","abstract_excerpt":"Despite the accomplishments of Generative Adversarial Networks (GANs) in modeling data distributions, training them remains a challenging task. A contributing factor to this difficulty is the non-intuitive nature of the GAN loss curves, which necessitates a subjective evaluation of the generated output to infer training progress. Recently, motivated by game theory, duality gap has been proposed as a domain agnostic measure to monitor GAN training. However, it is restricted to the setting when the GAN converges to a Nash equilibrium. But GANs need not always converge to a Nash equilibrium to mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.04801","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/2105.04801/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2105.04801","created_at":"2026-07-05T02:56:58.136300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.04801v2","created_at":"2026-07-05T02:56:58.136300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.04801","created_at":"2026-07-05T02:56:58.136300+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSHSQAJ6FENO","created_at":"2026-07-05T02:56:58.136300+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSHSQAJ6FENOQBNI","created_at":"2026-07-05T02:56:58.136300+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSHSQAJ6","created_at":"2026-07-05T02:56:58.136300+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JSHSQAJ6FENOQBNIZV47W3QV5I","json":"https://pith.science/pith/JSHSQAJ6FENOQBNIZV47W3QV5I.json","graph_json":"https://pith.science/api/pith-number/JSHSQAJ6FENOQBNIZV47W3QV5I/graph.json","events_json":"https://pith.science/api/pith-number/JSHSQAJ6FENOQBNIZV47W3QV5I/events.json","paper":"https://pith.science/paper/JSHSQAJ6"},"agent_actions":{"view_html":"https://pith.science/pith/JSHSQAJ6FENOQBNIZV47W3QV5I","download_json":"https://pith.science/pith/JSHSQAJ6FENOQBNIZV47W3QV5I.json","view_paper":"https://pith.science/paper/JSHSQAJ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.04801&json=true","fetch_graph":"https://pith.science/api/pith-number/JSHSQAJ6FENOQBNIZV47W3QV5I/graph.json","fetch_events":"https://pith.science/api/pith-number/JSHSQAJ6FENOQBNIZV47W3QV5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSHSQAJ6FENOQBNIZV47W3QV5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSHSQAJ6FENOQBNIZV47W3QV5I/action/storage_attestation","attest_author":"https://pith.science/pith/JSHSQAJ6FENOQBNIZV47W3QV5I/action/author_attestation","sign_citation":"https://pith.science/pith/JSHSQAJ6FENOQBNIZV47W3QV5I/action/citation_signature","submit_replication":"https://pith.science/pith/JSHSQAJ6FENOQBNIZV47W3QV5I/action/replication_record"}},"created_at":"2026-07-05T02:56:58.136300+00:00","updated_at":"2026-07-05T02:56:58.136300+00:00"}