{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4HUUYFRZDTO6HSAINRHAOUMWUQ","short_pith_number":"pith:4HUUYFRZ","schema_version":"1.0","canonical_sha256":"e1e94c16391cdde3c8086c4e075196a40f5f2f2bd5bcd8f643fc9d0bede24adc","source":{"kind":"arxiv","id":"2506.18226","version":1},"attestation_state":"computed","paper":{"title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Qi Fan, Xunzhi Xiang","submitted_at":"2025-06-23T01:27:06Z","abstract_excerpt":"Autoregressive conditional image generation models have emerged as a dominant paradigm in text-to-image synthesis. These methods typically convert images into one-dimensional token sequences and leverage the self-attention mechanism, which has achieved remarkable success in natural language processing, to capture long-range dependencies, model global context, and ensure semantic coherence. However, excessively long contexts during inference lead to significant memory overhead caused by KV-cache and computational delays. To alleviate these challenges, we systematically analyze how global semant"},"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":"2506.18226","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T01:27:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"37f5c196b951e8f201329fae826b31e4ae37a18c23882e90d4aed023d9769ed5","abstract_canon_sha256":"a6a4d4e0dc677b9232aee344e628459f569131740917d22d28e8cbb2168dbc37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:30.748878Z","signature_b64":"e2PjPuVVR7mh1Eu1L5/EQqnEN5zJ20j4ROFxGxEWEKJezyOw5+xYCwmCcPkxKugg2bJNpic58DgaZLfTTZPPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1e94c16391cdde3c8086c4e075196a40f5f2f2bd5bcd8f643fc9d0bede24adc","last_reissued_at":"2026-07-05T11:25:30.748390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:30.748390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Qi Fan, Xunzhi Xiang","submitted_at":"2025-06-23T01:27:06Z","abstract_excerpt":"Autoregressive conditional image generation models have emerged as a dominant paradigm in text-to-image synthesis. These methods typically convert images into one-dimensional token sequences and leverage the self-attention mechanism, which has achieved remarkable success in natural language processing, to capture long-range dependencies, model global context, and ensure semantic coherence. However, excessively long contexts during inference lead to significant memory overhead caused by KV-cache and computational delays. To alleviate these challenges, we systematically analyze how global semant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18226","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/2506.18226/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":"2506.18226","created_at":"2026-07-05T11:25:30.748452+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.18226v1","created_at":"2026-07-05T11:25:30.748452+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18226","created_at":"2026-07-05T11:25:30.748452+00:00"},{"alias_kind":"pith_short_12","alias_value":"4HUUYFRZDTO6","created_at":"2026-07-05T11:25:30.748452+00:00"},{"alias_kind":"pith_short_16","alias_value":"4HUUYFRZDTO6HSAI","created_at":"2026-07-05T11:25:30.748452+00:00"},{"alias_kind":"pith_short_8","alias_value":"4HUUYFRZ","created_at":"2026-07-05T11:25:30.748452+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02436","citing_title":"Geometry-Aware Implicit Memory for Video World Models","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4HUUYFRZDTO6HSAINRHAOUMWUQ","json":"https://pith.science/pith/4HUUYFRZDTO6HSAINRHAOUMWUQ.json","graph_json":"https://pith.science/api/pith-number/4HUUYFRZDTO6HSAINRHAOUMWUQ/graph.json","events_json":"https://pith.science/api/pith-number/4HUUYFRZDTO6HSAINRHAOUMWUQ/events.json","paper":"https://pith.science/paper/4HUUYFRZ"},"agent_actions":{"view_html":"https://pith.science/pith/4HUUYFRZDTO6HSAINRHAOUMWUQ","download_json":"https://pith.science/pith/4HUUYFRZDTO6HSAINRHAOUMWUQ.json","view_paper":"https://pith.science/paper/4HUUYFRZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.18226&json=true","fetch_graph":"https://pith.science/api/pith-number/4HUUYFRZDTO6HSAINRHAOUMWUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/4HUUYFRZDTO6HSAINRHAOUMWUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4HUUYFRZDTO6HSAINRHAOUMWUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4HUUYFRZDTO6HSAINRHAOUMWUQ/action/storage_attestation","attest_author":"https://pith.science/pith/4HUUYFRZDTO6HSAINRHAOUMWUQ/action/author_attestation","sign_citation":"https://pith.science/pith/4HUUYFRZDTO6HSAINRHAOUMWUQ/action/citation_signature","submit_replication":"https://pith.science/pith/4HUUYFRZDTO6HSAINRHAOUMWUQ/action/replication_record"}},"created_at":"2026-07-05T11:25:30.748452+00:00","updated_at":"2026-07-05T11:25:30.748452+00:00"}