{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YAAAYMTYXVAWMDDMJZ5LKCHZDE","short_pith_number":"pith:YAAAYMTY","schema_version":"1.0","canonical_sha256":"c0000c3278bd41660c6c4e7ab508f9193517331f03e686a51c6d81218c11fdc1","source":{"kind":"arxiv","id":"2211.16791","version":1},"attestation_state":"computed","paper":{"title":"Adaptive adversarial training method for improving multi-scale GAN based on generalization bound theory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Bo Tao, Jing Tang, Zeyu Gong, Zhouping Yin","submitted_at":"2022-11-30T07:11:56Z","abstract_excerpt":"In recent years, multi-scale generative adversarial networks (GANs) have been proposed to build generalized image processing models based on single sample. Constraining on the sample size, multi-scale GANs have much difficulty converging to the global optimum, which ultimately leads to limitations in their capabilities. In this paper, we pioneered the introduction of PAC-Bayes generalized bound theory into the training analysis of specific models under different adversarial training methods, which can obtain a non-vacuous upper bound on the generalization error for the specified multi-scale GA"},"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":"2211.16791","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-30T07:11:56Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"8d357e6d6f50d9c50a2908533a7d46f6ddeb4501a44eb19e2cfde7aa275b7603","abstract_canon_sha256":"8a85634ce388c12565c650345d0fb648af21373c70f1313f326deb0389acdbae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:11.109655Z","signature_b64":"CrDRBk7OoaguEKhluRyx2vaO73ycy9RbASdfqSXhGUNMx8Jg8KlBJ6p4u1yLbDm5F90+rzbOfjYt+briSJ5eDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0000c3278bd41660c6c4e7ab508f9193517331f03e686a51c6d81218c11fdc1","last_reissued_at":"2026-07-05T05:21:11.109255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:11.109255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive adversarial training method for improving multi-scale GAN based on generalization bound theory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Bo Tao, Jing Tang, Zeyu Gong, Zhouping Yin","submitted_at":"2022-11-30T07:11:56Z","abstract_excerpt":"In recent years, multi-scale generative adversarial networks (GANs) have been proposed to build generalized image processing models based on single sample. Constraining on the sample size, multi-scale GANs have much difficulty converging to the global optimum, which ultimately leads to limitations in their capabilities. In this paper, we pioneered the introduction of PAC-Bayes generalized bound theory into the training analysis of specific models under different adversarial training methods, which can obtain a non-vacuous upper bound on the generalization error for the specified multi-scale GA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.16791","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/2211.16791/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":"2211.16791","created_at":"2026-07-05T05:21:11.109310+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.16791v1","created_at":"2026-07-05T05:21:11.109310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.16791","created_at":"2026-07-05T05:21:11.109310+00:00"},{"alias_kind":"pith_short_12","alias_value":"YAAAYMTYXVAW","created_at":"2026-07-05T05:21:11.109310+00:00"},{"alias_kind":"pith_short_16","alias_value":"YAAAYMTYXVAWMDDM","created_at":"2026-07-05T05:21:11.109310+00:00"},{"alias_kind":"pith_short_8","alias_value":"YAAAYMTY","created_at":"2026-07-05T05:21:11.109310+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/YAAAYMTYXVAWMDDMJZ5LKCHZDE","json":"https://pith.science/pith/YAAAYMTYXVAWMDDMJZ5LKCHZDE.json","graph_json":"https://pith.science/api/pith-number/YAAAYMTYXVAWMDDMJZ5LKCHZDE/graph.json","events_json":"https://pith.science/api/pith-number/YAAAYMTYXVAWMDDMJZ5LKCHZDE/events.json","paper":"https://pith.science/paper/YAAAYMTY"},"agent_actions":{"view_html":"https://pith.science/pith/YAAAYMTYXVAWMDDMJZ5LKCHZDE","download_json":"https://pith.science/pith/YAAAYMTYXVAWMDDMJZ5LKCHZDE.json","view_paper":"https://pith.science/paper/YAAAYMTY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.16791&json=true","fetch_graph":"https://pith.science/api/pith-number/YAAAYMTYXVAWMDDMJZ5LKCHZDE/graph.json","fetch_events":"https://pith.science/api/pith-number/YAAAYMTYXVAWMDDMJZ5LKCHZDE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YAAAYMTYXVAWMDDMJZ5LKCHZDE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YAAAYMTYXVAWMDDMJZ5LKCHZDE/action/storage_attestation","attest_author":"https://pith.science/pith/YAAAYMTYXVAWMDDMJZ5LKCHZDE/action/author_attestation","sign_citation":"https://pith.science/pith/YAAAYMTYXVAWMDDMJZ5LKCHZDE/action/citation_signature","submit_replication":"https://pith.science/pith/YAAAYMTYXVAWMDDMJZ5LKCHZDE/action/replication_record"}},"created_at":"2026-07-05T05:21:11.109310+00:00","updated_at":"2026-07-05T05:21:11.109310+00:00"}