{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VFEJ6GGQ7Q53KVKOZH6QHOHPEK","short_pith_number":"pith:VFEJ6GGQ","canonical_record":{"source":{"id":"2606.20543","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T17:52:30Z","cross_cats_sorted":[],"title_canon_sha256":"b5b50cfba2e491f3d209114cdb8d54253c99ed467a0f1d1e6a655b415579be54","abstract_canon_sha256":"5492b49ab10706d8864d90c1679a106c7f1967721bfce8efa2c2683c121de57c"},"schema_version":"1.0"},"canonical_sha256":"a9489f18d0fc3bb5554ec9fd03b8ef22adcf2b3f5ce2da43e7c94ddd04095e73","source":{"kind":"arxiv","id":"2606.20543","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20543","created_at":"2026-06-19T16:13:14Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20543v1","created_at":"2026-06-19T16:13:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20543","created_at":"2026-06-19T16:13:14Z"},{"alias_kind":"pith_short_12","alias_value":"VFEJ6GGQ7Q53","created_at":"2026-06-19T16:13:14Z"},{"alias_kind":"pith_short_16","alias_value":"VFEJ6GGQ7Q53KVKO","created_at":"2026-06-19T16:13:14Z"},{"alias_kind":"pith_short_8","alias_value":"VFEJ6GGQ","created_at":"2026-06-19T16:13:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VFEJ6GGQ7Q53KVKOZH6QHOHPEK","target":"record","payload":{"canonical_record":{"source":{"id":"2606.20543","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T17:52:30Z","cross_cats_sorted":[],"title_canon_sha256":"b5b50cfba2e491f3d209114cdb8d54253c99ed467a0f1d1e6a655b415579be54","abstract_canon_sha256":"5492b49ab10706d8864d90c1679a106c7f1967721bfce8efa2c2683c121de57c"},"schema_version":"1.0"},"canonical_sha256":"a9489f18d0fc3bb5554ec9fd03b8ef22adcf2b3f5ce2da43e7c94ddd04095e73","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:14.894732Z","signature_b64":"hrreDQNcuv3BWCgHTeG4krVearIdlK9O0sUyfb7D/zCCPYY/osBm+pWRXoRKE7sCUEfi8bv2MSoMhyR/KdSZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9489f18d0fc3bb5554ec9fd03b8ef22adcf2b3f5ce2da43e7c94ddd04095e73","last_reissued_at":"2026-06-19T16:13:14.894391Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:14.894391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.20543","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:13:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I6Ow7MIODrmo6ws5S4HjIE+1qTtInpMOm2rDUZ4J64fx7MxApl3uOA1+TvyymV3JFG81H/Fk0gWN+SIz6O7FDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T20:37:21.281645Z"},"content_sha256":"057ad4532d922ec8ca100a90b5e718a9f735d93bce6f944915c6779db09f9771","schema_version":"1.0","event_id":"sha256:057ad4532d922ec8ca100a90b5e718a9f735d93bce6f944915c6779db09f9771"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VFEJ6GGQ7Q53KVKOZH6QHOHPEK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SSD: Spatially Speculative Decoding Accelerates Autoregressive Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengzhi Mao, Lijun Yu, Shilong Xiang, Zirui Zhang","submitted_at":"2026-06-18T17:52:30Z","abstract_excerpt":"Autoregressive models excel in visual generation by treating images as 1D sequences of discrete tokens, mirroring language modeling. However, this flattening discards the intrinsic 2D spatial locality of visual signals, creating severe computational bottlenecks during inference. We introduce Spatially Speculative Decoding (SSD), a framework that aligns the predictive objective with the natural geometry of images. Rather than predicting only the immediate next token in a 1D sequence, our model simultaneously predicts the adjacent horizontal token and the token directly below it. By capitalizing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20543","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/2606.20543/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:13:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YdxcieTB07NW8YucVo7t+WBdiihV0DmSkwJX4ppJwDcuDZ1cVq+TDme/GjnWOaU2FQ0r9P66cu3OZm2dmWiFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T20:37:21.282008Z"},"content_sha256":"72d90093bc5da2ddb9d3ece4b2345b913fdf89d9686fdf5638eb3a99cf4a68b1","schema_version":"1.0","event_id":"sha256:72d90093bc5da2ddb9d3ece4b2345b913fdf89d9686fdf5638eb3a99cf4a68b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VFEJ6GGQ7Q53KVKOZH6QHOHPEK/bundle.json","state_url":"https://pith.science/pith/VFEJ6GGQ7Q53KVKOZH6QHOHPEK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VFEJ6GGQ7Q53KVKOZH6QHOHPEK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-28T20:37:21Z","links":{"resolver":"https://pith.science/pith/VFEJ6GGQ7Q53KVKOZH6QHOHPEK","bundle":"https://pith.science/pith/VFEJ6GGQ7Q53KVKOZH6QHOHPEK/bundle.json","state":"https://pith.science/pith/VFEJ6GGQ7Q53KVKOZH6QHOHPEK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VFEJ6GGQ7Q53KVKOZH6QHOHPEK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VFEJ6GGQ7Q53KVKOZH6QHOHPEK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5492b49ab10706d8864d90c1679a106c7f1967721bfce8efa2c2683c121de57c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T17:52:30Z","title_canon_sha256":"b5b50cfba2e491f3d209114cdb8d54253c99ed467a0f1d1e6a655b415579be54"},"schema_version":"1.0","source":{"id":"2606.20543","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20543","created_at":"2026-06-19T16:13:14Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20543v1","created_at":"2026-06-19T16:13:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20543","created_at":"2026-06-19T16:13:14Z"},{"alias_kind":"pith_short_12","alias_value":"VFEJ6GGQ7Q53","created_at":"2026-06-19T16:13:14Z"},{"alias_kind":"pith_short_16","alias_value":"VFEJ6GGQ7Q53KVKO","created_at":"2026-06-19T16:13:14Z"},{"alias_kind":"pith_short_8","alias_value":"VFEJ6GGQ","created_at":"2026-06-19T16:13:14Z"}],"graph_snapshots":[{"event_id":"sha256:72d90093bc5da2ddb9d3ece4b2345b913fdf89d9686fdf5638eb3a99cf4a68b1","target":"graph","created_at":"2026-06-19T16:13:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.20543/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregressive models excel in visual generation by treating images as 1D sequences of discrete tokens, mirroring language modeling. However, this flattening discards the intrinsic 2D spatial locality of visual signals, creating severe computational bottlenecks during inference. We introduce Spatially Speculative Decoding (SSD), a framework that aligns the predictive objective with the natural geometry of images. Rather than predicting only the immediate next token in a 1D sequence, our model simultaneously predicts the adjacent horizontal token and the token directly below it. By capitalizing","authors_text":"Chengzhi Mao, Lijun Yu, Shilong Xiang, Zirui Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T17:52:30Z","title":"SSD: Spatially Speculative Decoding Accelerates Autoregressive Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20543","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:057ad4532d922ec8ca100a90b5e718a9f735d93bce6f944915c6779db09f9771","target":"record","created_at":"2026-06-19T16:13:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5492b49ab10706d8864d90c1679a106c7f1967721bfce8efa2c2683c121de57c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T17:52:30Z","title_canon_sha256":"b5b50cfba2e491f3d209114cdb8d54253c99ed467a0f1d1e6a655b415579be54"},"schema_version":"1.0","source":{"id":"2606.20543","kind":"arxiv","version":1}},"canonical_sha256":"a9489f18d0fc3bb5554ec9fd03b8ef22adcf2b3f5ce2da43e7c94ddd04095e73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9489f18d0fc3bb5554ec9fd03b8ef22adcf2b3f5ce2da43e7c94ddd04095e73","first_computed_at":"2026-06-19T16:13:14.894391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:13:14.894391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hrreDQNcuv3BWCgHTeG4krVearIdlK9O0sUyfb7D/zCCPYY/osBm+pWRXoRKE7sCUEfi8bv2MSoMhyR/KdSZDw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:13:14.894732Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.20543","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:057ad4532d922ec8ca100a90b5e718a9f735d93bce6f944915c6779db09f9771","sha256:72d90093bc5da2ddb9d3ece4b2345b913fdf89d9686fdf5638eb3a99cf4a68b1"],"state_sha256":"0ffdf361201dc8e0f641d62b58f2fce785e09fc62313a548979f670831a9b308"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s9DZk1xfV+P96HmYrLGndLi0mxjxwOaaK79HGRLWBC2MCfxxRnVXAJ+QvyjlzsrCSl1Zs0cpo2GuIJBptI6KAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T20:37:21.284175Z","bundle_sha256":"2d1145c6f243e3932e7e461a385608eeb4936a399325f08c77203dbdf8df7825"}}