{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IGZOZFD7W2CXS7N4F5JZCAPSRF","short_pith_number":"pith:IGZOZFD7","schema_version":"1.0","canonical_sha256":"41b2ec947fb685797dbc2f539101f2894df854415f45422addb12638785d4223","source":{"kind":"arxiv","id":"2510.06928","version":2},"attestation_state":"computed","paper":{"title":"IAR2: Improving Autoregressive Visual Generation with Semantic-Detail Associated Token Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangning Zhang, Lizhuang Ma, Ran Yi, Teng Hu, Zihan Su","submitted_at":"2025-10-08T12:08:21Z","abstract_excerpt":"Autoregressive models have emerged as a powerful paradigm for visual content creation, but often overlook the intrinsic structural properties of visual data. Our prior work, IAR, initiated a direction to address this by reorganizing the visual codebook based on embedding similarity, thereby improving generation robustness. However, it is constrained by the rigidity of pre-trained codebooks and the inaccuracies of hard, uniform clustering. To overcome these limitations, we propose IAR2, an advanced autoregressive framework that enables a hierarchical semantic-detail synthesis process. At the co"},"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":"2510.06928","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-08T12:08:21Z","cross_cats_sorted":[],"title_canon_sha256":"3c88eb55582e0bd50c720af2281ee0c0bcf262805201f226e5da390544bf339a","abstract_canon_sha256":"65b4a86265d1daca33d9a817db34baf7c9ebaaac3c2eede2c7b1f3dc33f3d274"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:31.385814Z","signature_b64":"eTugkct0+5AyKNc9mlo74jwEX7/VpKW2F5+5haIKcClbHAFCePy/a1ku35tDMdQEVlZ+JncUzmbEXmpGFLmtCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41b2ec947fb685797dbc2f539101f2894df854415f45422addb12638785d4223","last_reissued_at":"2026-05-28T01:04:31.385248Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:31.385248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IAR2: Improving Autoregressive Visual Generation with Semantic-Detail Associated Token Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangning Zhang, Lizhuang Ma, Ran Yi, Teng Hu, Zihan Su","submitted_at":"2025-10-08T12:08:21Z","abstract_excerpt":"Autoregressive models have emerged as a powerful paradigm for visual content creation, but often overlook the intrinsic structural properties of visual data. Our prior work, IAR, initiated a direction to address this by reorganizing the visual codebook based on embedding similarity, thereby improving generation robustness. However, it is constrained by the rigidity of pre-trained codebooks and the inaccuracies of hard, uniform clustering. To overcome these limitations, we propose IAR2, an advanced autoregressive framework that enables a hierarchical semantic-detail synthesis process. At the co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.06928","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/2510.06928/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":"2510.06928","created_at":"2026-05-28T01:04:31.385326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.06928v2","created_at":"2026-05-28T01:04:31.385326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.06928","created_at":"2026-05-28T01:04:31.385326+00:00"},{"alias_kind":"pith_short_12","alias_value":"IGZOZFD7W2CX","created_at":"2026-05-28T01:04:31.385326+00:00"},{"alias_kind":"pith_short_16","alias_value":"IGZOZFD7W2CXS7N4","created_at":"2026-05-28T01:04:31.385326+00:00"},{"alias_kind":"pith_short_8","alias_value":"IGZOZFD7","created_at":"2026-05-28T01:04:31.385326+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/IGZOZFD7W2CXS7N4F5JZCAPSRF","json":"https://pith.science/pith/IGZOZFD7W2CXS7N4F5JZCAPSRF.json","graph_json":"https://pith.science/api/pith-number/IGZOZFD7W2CXS7N4F5JZCAPSRF/graph.json","events_json":"https://pith.science/api/pith-number/IGZOZFD7W2CXS7N4F5JZCAPSRF/events.json","paper":"https://pith.science/paper/IGZOZFD7"},"agent_actions":{"view_html":"https://pith.science/pith/IGZOZFD7W2CXS7N4F5JZCAPSRF","download_json":"https://pith.science/pith/IGZOZFD7W2CXS7N4F5JZCAPSRF.json","view_paper":"https://pith.science/paper/IGZOZFD7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.06928&json=true","fetch_graph":"https://pith.science/api/pith-number/IGZOZFD7W2CXS7N4F5JZCAPSRF/graph.json","fetch_events":"https://pith.science/api/pith-number/IGZOZFD7W2CXS7N4F5JZCAPSRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IGZOZFD7W2CXS7N4F5JZCAPSRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IGZOZFD7W2CXS7N4F5JZCAPSRF/action/storage_attestation","attest_author":"https://pith.science/pith/IGZOZFD7W2CXS7N4F5JZCAPSRF/action/author_attestation","sign_citation":"https://pith.science/pith/IGZOZFD7W2CXS7N4F5JZCAPSRF/action/citation_signature","submit_replication":"https://pith.science/pith/IGZOZFD7W2CXS7N4F5JZCAPSRF/action/replication_record"}},"created_at":"2026-05-28T01:04:31.385326+00:00","updated_at":"2026-05-28T01:04:31.385326+00:00"}