{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CSEWIPDCJTY5ONMKRLRG6K5XAB","short_pith_number":"pith:CSEWIPDC","schema_version":"1.0","canonical_sha256":"1489643c624cf1d7358a8ae26f2bb700739f84fa25be4cffe9e33cf6a4eaa503","source":{"kind":"arxiv","id":"2509.23876","version":3},"attestation_state":"computed","paper":{"title":"Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anh-Dung Dinh, Chang Xu, Daochang Liu, Hoang Lam Tran, Ky Dan Nguyen, Weidong Cai, Xiuying Wang","submitted_at":"2025-09-28T13:33:49Z","abstract_excerpt":"Autoregressive (AR) models based on next-scale prediction have emerged as a powerful tool for image generation, but they face a critical weakness: information inconsistencies between patches across timesteps introduced by progressive resolution scaling. These inconsistencies scatter guidance signals, causing them to drift away from salient regions within the image and leaving behind ambiguous, unfaithful features during sampling. We tackle this challenge with Information-Grounding Guidance (IGG), a novel framework that anchors guidance to semantically important tokens via an attention-based dy"},"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":"2509.23876","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-28T13:33:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"44eab4f919b09378ac1bfd2bfb6b99b30a8a71b54c18cfb91ea885235a89997c","abstract_canon_sha256":"420fe01b1d195e5d84a36c867233669fc4c097ccf1f972da9702f0559033fe00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:19:07.098429Z","signature_b64":"nIEB3e2rv4U/9OjjhTFzUFOUBewaTlqzTDWL3q4/buubb68u0MpVzE4RL6CF+lxzuhFVdD9aIpV31SB5LedqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1489643c624cf1d7358a8ae26f2bb700739f84fa25be4cffe9e33cf6a4eaa503","last_reissued_at":"2026-07-08T01:19:07.097898Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:19:07.097898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anh-Dung Dinh, Chang Xu, Daochang Liu, Hoang Lam Tran, Ky Dan Nguyen, Weidong Cai, Xiuying Wang","submitted_at":"2025-09-28T13:33:49Z","abstract_excerpt":"Autoregressive (AR) models based on next-scale prediction have emerged as a powerful tool for image generation, but they face a critical weakness: information inconsistencies between patches across timesteps introduced by progressive resolution scaling. These inconsistencies scatter guidance signals, causing them to drift away from salient regions within the image and leaving behind ambiguous, unfaithful features during sampling. We tackle this challenge with Information-Grounding Guidance (IGG), a novel framework that anchors guidance to semantically important tokens via an attention-based dy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.23876","kind":"arxiv","version":3},"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/2509.23876/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":"2509.23876","created_at":"2026-07-08T01:19:07.097954+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.23876v3","created_at":"2026-07-08T01:19:07.097954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.23876","created_at":"2026-07-08T01:19:07.097954+00:00"},{"alias_kind":"pith_short_12","alias_value":"CSEWIPDCJTY5","created_at":"2026-07-08T01:19:07.097954+00:00"},{"alias_kind":"pith_short_16","alias_value":"CSEWIPDCJTY5ONMK","created_at":"2026-07-08T01:19:07.097954+00:00"},{"alias_kind":"pith_short_8","alias_value":"CSEWIPDC","created_at":"2026-07-08T01:19:07.097954+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/CSEWIPDCJTY5ONMKRLRG6K5XAB","json":"https://pith.science/pith/CSEWIPDCJTY5ONMKRLRG6K5XAB.json","graph_json":"https://pith.science/api/pith-number/CSEWIPDCJTY5ONMKRLRG6K5XAB/graph.json","events_json":"https://pith.science/api/pith-number/CSEWIPDCJTY5ONMKRLRG6K5XAB/events.json","paper":"https://pith.science/paper/CSEWIPDC"},"agent_actions":{"view_html":"https://pith.science/pith/CSEWIPDCJTY5ONMKRLRG6K5XAB","download_json":"https://pith.science/pith/CSEWIPDCJTY5ONMKRLRG6K5XAB.json","view_paper":"https://pith.science/paper/CSEWIPDC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.23876&json=true","fetch_graph":"https://pith.science/api/pith-number/CSEWIPDCJTY5ONMKRLRG6K5XAB/graph.json","fetch_events":"https://pith.science/api/pith-number/CSEWIPDCJTY5ONMKRLRG6K5XAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CSEWIPDCJTY5ONMKRLRG6K5XAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CSEWIPDCJTY5ONMKRLRG6K5XAB/action/storage_attestation","attest_author":"https://pith.science/pith/CSEWIPDCJTY5ONMKRLRG6K5XAB/action/author_attestation","sign_citation":"https://pith.science/pith/CSEWIPDCJTY5ONMKRLRG6K5XAB/action/citation_signature","submit_replication":"https://pith.science/pith/CSEWIPDCJTY5ONMKRLRG6K5XAB/action/replication_record"}},"created_at":"2026-07-08T01:19:07.097954+00:00","updated_at":"2026-07-08T01:19:07.097954+00:00"}