{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OISG6UEEPJDWW4LDGI3YIYBEIP","short_pith_number":"pith:OISG6UEE","schema_version":"1.0","canonical_sha256":"72246f50847a476b7163323784602443d3749951b0f282d078708b66f6668870","source":{"kind":"arxiv","id":"2410.04764","version":1},"attestation_state":"computed","paper":{"title":"Double Oracle Neural Architecture Search for Game Theoretic Deep Learning Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Aye Phyu Phyu Aung, Bo An, Hau Chan, J. Senthilnath, Ruiyu Wang, Xiaoli Li, Xinrun Wang","submitted_at":"2024-10-07T05:42:01Z","abstract_excerpt":"In this paper, we propose a new approach to train deep learning models using game theory concepts including Generative Adversarial Networks (GANs) and Adversarial Training (AT) where we deploy a double-oracle framework using best response oracles. GAN is essentially a two-player zero-sum game between the generator and the discriminator. The same concept can be applied to AT with attacker and classifier as players. Training these models is challenging as a pure Nash equilibrium may not exist and even finding the mixed Nash equilibrium is difficult as training algorithms for both GAN and AT have"},"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":"2410.04764","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-07T05:42:01Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"2f00206f12803cfaffbf47e00ae8179ebfd95f7c51750a7e675318aa706a3830","abstract_canon_sha256":"839f88e894ada9c99aa9c445816b1f29d55a8b068af496df05d7af3cce4dcbbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:55.715642Z","signature_b64":"LeS9GCi0U2uiyFm3OZA7xPSgLPTNTxdlt2a4YkKpDk4uBmUZmSXsC2m70clP7fBsHrq2BcUeMqcw69/cQWU8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72246f50847a476b7163323784602443d3749951b0f282d078708b66f6668870","last_reissued_at":"2026-07-05T09:16:55.715125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:55.715125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Double Oracle Neural Architecture Search for Game Theoretic Deep Learning Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Aye Phyu Phyu Aung, Bo An, Hau Chan, J. Senthilnath, Ruiyu Wang, Xiaoli Li, Xinrun Wang","submitted_at":"2024-10-07T05:42:01Z","abstract_excerpt":"In this paper, we propose a new approach to train deep learning models using game theory concepts including Generative Adversarial Networks (GANs) and Adversarial Training (AT) where we deploy a double-oracle framework using best response oracles. GAN is essentially a two-player zero-sum game between the generator and the discriminator. The same concept can be applied to AT with attacker and classifier as players. Training these models is challenging as a pure Nash equilibrium may not exist and even finding the mixed Nash equilibrium is difficult as training algorithms for both GAN and AT have"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04764","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/2410.04764/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":"2410.04764","created_at":"2026-07-05T09:16:55.715189+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04764v1","created_at":"2026-07-05T09:16:55.715189+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04764","created_at":"2026-07-05T09:16:55.715189+00:00"},{"alias_kind":"pith_short_12","alias_value":"OISG6UEEPJDW","created_at":"2026-07-05T09:16:55.715189+00:00"},{"alias_kind":"pith_short_16","alias_value":"OISG6UEEPJDWW4LD","created_at":"2026-07-05T09:16:55.715189+00:00"},{"alias_kind":"pith_short_8","alias_value":"OISG6UEE","created_at":"2026-07-05T09:16:55.715189+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/OISG6UEEPJDWW4LDGI3YIYBEIP","json":"https://pith.science/pith/OISG6UEEPJDWW4LDGI3YIYBEIP.json","graph_json":"https://pith.science/api/pith-number/OISG6UEEPJDWW4LDGI3YIYBEIP/graph.json","events_json":"https://pith.science/api/pith-number/OISG6UEEPJDWW4LDGI3YIYBEIP/events.json","paper":"https://pith.science/paper/OISG6UEE"},"agent_actions":{"view_html":"https://pith.science/pith/OISG6UEEPJDWW4LDGI3YIYBEIP","download_json":"https://pith.science/pith/OISG6UEEPJDWW4LDGI3YIYBEIP.json","view_paper":"https://pith.science/paper/OISG6UEE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04764&json=true","fetch_graph":"https://pith.science/api/pith-number/OISG6UEEPJDWW4LDGI3YIYBEIP/graph.json","fetch_events":"https://pith.science/api/pith-number/OISG6UEEPJDWW4LDGI3YIYBEIP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OISG6UEEPJDWW4LDGI3YIYBEIP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OISG6UEEPJDWW4LDGI3YIYBEIP/action/storage_attestation","attest_author":"https://pith.science/pith/OISG6UEEPJDWW4LDGI3YIYBEIP/action/author_attestation","sign_citation":"https://pith.science/pith/OISG6UEEPJDWW4LDGI3YIYBEIP/action/citation_signature","submit_replication":"https://pith.science/pith/OISG6UEEPJDWW4LDGI3YIYBEIP/action/replication_record"}},"created_at":"2026-07-05T09:16:55.715189+00:00","updated_at":"2026-07-05T09:16:55.715189+00:00"}