{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IKTQ4KXH2RHJ5KC3W6QX6I6VMS","short_pith_number":"pith:IKTQ4KXH","schema_version":"1.0","canonical_sha256":"42a70e2ae7d44e9ea85bb7a17f23d5649f62049b6c7782fb6bd23f138627f3f3","source":{"kind":"arxiv","id":"2606.05703","version":1},"attestation_state":"computed","paper":{"title":"Parallel Jacobi Decoding for Fast Autoregressive Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boya Liao, Huan Wang, Siyong Jian, Ying Li","submitted_at":"2026-06-04T04:50:22Z","abstract_excerpt":"Autoregressive (AR) models have demonstrated remarkable performance in generating high-fidelity images. However, their inherently sequential next-token prediction leads to significantly slower inference. Recent studies have introduced Jacobi-style decoding to accelerate autoregressive image generation. Extending the draft sequence initially improves efficiency, yet the acceleration quickly saturates as error propagation in the one-dimensional sequence hinders convergence. Observing that images exhibit strong local spatial correlations, we propose Parallel Jacobi Decoding (PJD), a training-free"},"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":"2606.05703","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T04:50:22Z","cross_cats_sorted":[],"title_canon_sha256":"bb382e35e5d9c506bf2ae3ba4e75591b64559587729af5da7678861c55365910","abstract_canon_sha256":"145fd59e9c18546d409f710c214865dd2307abb301dceed81e6d226ec23b74fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:14:59.818042Z","signature_b64":"0BA8Eilf2pyhAXrj/Mgsu7OPKFqf3i8xz0CQrHeGsjqpjnCzBd2yEBiey1vHyLU4R8HYwwIOlzSPJBNJhy1OBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42a70e2ae7d44e9ea85bb7a17f23d5649f62049b6c7782fb6bd23f138627f3f3","last_reissued_at":"2026-06-05T01:14:59.817439Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:14:59.817439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parallel Jacobi Decoding for Fast Autoregressive Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boya Liao, Huan Wang, Siyong Jian, Ying Li","submitted_at":"2026-06-04T04:50:22Z","abstract_excerpt":"Autoregressive (AR) models have demonstrated remarkable performance in generating high-fidelity images. However, their inherently sequential next-token prediction leads to significantly slower inference. Recent studies have introduced Jacobi-style decoding to accelerate autoregressive image generation. Extending the draft sequence initially improves efficiency, yet the acceleration quickly saturates as error propagation in the one-dimensional sequence hinders convergence. Observing that images exhibit strong local spatial correlations, we propose Parallel Jacobi Decoding (PJD), a training-free"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05703","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/2606.05703/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":"2606.05703","created_at":"2026-06-05T01:14:59.817542+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05703v1","created_at":"2026-06-05T01:14:59.817542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05703","created_at":"2026-06-05T01:14:59.817542+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKTQ4KXH2RHJ","created_at":"2026-06-05T01:14:59.817542+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKTQ4KXH2RHJ5KC3","created_at":"2026-06-05T01:14:59.817542+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKTQ4KXH","created_at":"2026-06-05T01:14:59.817542+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/IKTQ4KXH2RHJ5KC3W6QX6I6VMS","json":"https://pith.science/pith/IKTQ4KXH2RHJ5KC3W6QX6I6VMS.json","graph_json":"https://pith.science/api/pith-number/IKTQ4KXH2RHJ5KC3W6QX6I6VMS/graph.json","events_json":"https://pith.science/api/pith-number/IKTQ4KXH2RHJ5KC3W6QX6I6VMS/events.json","paper":"https://pith.science/paper/IKTQ4KXH"},"agent_actions":{"view_html":"https://pith.science/pith/IKTQ4KXH2RHJ5KC3W6QX6I6VMS","download_json":"https://pith.science/pith/IKTQ4KXH2RHJ5KC3W6QX6I6VMS.json","view_paper":"https://pith.science/paper/IKTQ4KXH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05703&json=true","fetch_graph":"https://pith.science/api/pith-number/IKTQ4KXH2RHJ5KC3W6QX6I6VMS/graph.json","fetch_events":"https://pith.science/api/pith-number/IKTQ4KXH2RHJ5KC3W6QX6I6VMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKTQ4KXH2RHJ5KC3W6QX6I6VMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKTQ4KXH2RHJ5KC3W6QX6I6VMS/action/storage_attestation","attest_author":"https://pith.science/pith/IKTQ4KXH2RHJ5KC3W6QX6I6VMS/action/author_attestation","sign_citation":"https://pith.science/pith/IKTQ4KXH2RHJ5KC3W6QX6I6VMS/action/citation_signature","submit_replication":"https://pith.science/pith/IKTQ4KXH2RHJ5KC3W6QX6I6VMS/action/replication_record"}},"created_at":"2026-06-05T01:14:59.817542+00:00","updated_at":"2026-06-05T01:14:59.817542+00:00"}