{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:35D37QXLUJXQX3UNIEOLXMMNRT","short_pith_number":"pith:35D37QXL","schema_version":"1.0","canonical_sha256":"df47bfc2eba26f0bee8d411cbbb18d8cd5555fcb05c04b922a3cf47a35dbb672","source":{"kind":"arxiv","id":"2605.24843","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Error Correction for Visual Autoregressive Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chang Xu, Jianyuan Guo, Ligong Bi, Tao Huang","submitted_at":"2026-05-24T03:22:22Z","abstract_excerpt":"Visual Autoregressive (VAR) models have emerged as a powerful paradigm for image synthesis by performing hierarchical next-scale prediction. However, VAR models are inherently prone to cascading error propagation, where subtle coarse-scale mispredictions are amplified across the hierarchy, ultimately distorting the final synthesis. To mitigate this, we propose AID-VAR, a plug-and-play framework that enhances pre-trained VARs through Adversarially Injected Diagnosis. Instead of a standard passive generation, AID-VAR introduces a proactive error-correction mechanism inspired by the adversarial f"},"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":"2605.24843","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-24T03:22:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"05340affead1a5e6969b97052fc4372a124153267e82ebbb7a620cf4831e1907","abstract_canon_sha256":"0bb095dee4f1d11aa9ca4999f15d1a40d4deee02feb095f7d4d29afd29855eac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:04:01.334899Z","signature_b64":"XM/ZEbbXl43tfqvaAXNC8ynXwKJv4Dyr5XKmkb2wxfRVrogZe0LNFwhoUbXfiQ0d2QOxPoQL1f4KXsao3JWSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df47bfc2eba26f0bee8d411cbbb18d8cd5555fcb05c04b922a3cf47a35dbb672","last_reissued_at":"2026-05-26T01:04:01.334355Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:04:01.334355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Error Correction for Visual Autoregressive Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chang Xu, Jianyuan Guo, Ligong Bi, Tao Huang","submitted_at":"2026-05-24T03:22:22Z","abstract_excerpt":"Visual Autoregressive (VAR) models have emerged as a powerful paradigm for image synthesis by performing hierarchical next-scale prediction. However, VAR models are inherently prone to cascading error propagation, where subtle coarse-scale mispredictions are amplified across the hierarchy, ultimately distorting the final synthesis. To mitigate this, we propose AID-VAR, a plug-and-play framework that enhances pre-trained VARs through Adversarially Injected Diagnosis. Instead of a standard passive generation, AID-VAR introduces a proactive error-correction mechanism inspired by the adversarial f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24843","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/2605.24843/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":"2605.24843","created_at":"2026-05-26T01:04:01.334446+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24843v1","created_at":"2026-05-26T01:04:01.334446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24843","created_at":"2026-05-26T01:04:01.334446+00:00"},{"alias_kind":"pith_short_12","alias_value":"35D37QXLUJXQ","created_at":"2026-05-26T01:04:01.334446+00:00"},{"alias_kind":"pith_short_16","alias_value":"35D37QXLUJXQX3UN","created_at":"2026-05-26T01:04:01.334446+00:00"},{"alias_kind":"pith_short_8","alias_value":"35D37QXL","created_at":"2026-05-26T01:04:01.334446+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/35D37QXLUJXQX3UNIEOLXMMNRT","json":"https://pith.science/pith/35D37QXLUJXQX3UNIEOLXMMNRT.json","graph_json":"https://pith.science/api/pith-number/35D37QXLUJXQX3UNIEOLXMMNRT/graph.json","events_json":"https://pith.science/api/pith-number/35D37QXLUJXQX3UNIEOLXMMNRT/events.json","paper":"https://pith.science/paper/35D37QXL"},"agent_actions":{"view_html":"https://pith.science/pith/35D37QXLUJXQX3UNIEOLXMMNRT","download_json":"https://pith.science/pith/35D37QXLUJXQX3UNIEOLXMMNRT.json","view_paper":"https://pith.science/paper/35D37QXL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24843&json=true","fetch_graph":"https://pith.science/api/pith-number/35D37QXLUJXQX3UNIEOLXMMNRT/graph.json","fetch_events":"https://pith.science/api/pith-number/35D37QXLUJXQX3UNIEOLXMMNRT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35D37QXLUJXQX3UNIEOLXMMNRT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35D37QXLUJXQX3UNIEOLXMMNRT/action/storage_attestation","attest_author":"https://pith.science/pith/35D37QXLUJXQX3UNIEOLXMMNRT/action/author_attestation","sign_citation":"https://pith.science/pith/35D37QXLUJXQX3UNIEOLXMMNRT/action/citation_signature","submit_replication":"https://pith.science/pith/35D37QXLUJXQX3UNIEOLXMMNRT/action/replication_record"}},"created_at":"2026-05-26T01:04:01.334446+00:00","updated_at":"2026-05-26T01:04:01.334446+00:00"}