{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:T6ZXFIM2EBAPOGNYIIKSNLEN5Y","short_pith_number":"pith:T6ZXFIM2","canonical_record":{"source":{"id":"2606.32039","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T17:59:57Z","cross_cats_sorted":[],"title_canon_sha256":"9d99d435769758d6131a2c26c398cedf48a98b41bf404c4b984ee3bb317f3faf","abstract_canon_sha256":"4d004026551c6e5ba062b571533c87d6d7eb60325c7480931c66ee02e916cced"},"schema_version":"1.0"},"canonical_sha256":"9fb372a19a2040f719b8421526ac8dee287f659509452485ca04612b97faf133","source":{"kind":"arxiv","id":"2606.32039","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.32039","created_at":"2026-07-01T02:17:48Z"},{"alias_kind":"arxiv_version","alias_value":"2606.32039v1","created_at":"2026-07-01T02:17:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.32039","created_at":"2026-07-01T02:17:48Z"},{"alias_kind":"pith_short_12","alias_value":"T6ZXFIM2EBAP","created_at":"2026-07-01T02:17:48Z"},{"alias_kind":"pith_short_16","alias_value":"T6ZXFIM2EBAPOGNY","created_at":"2026-07-01T02:17:48Z"},{"alias_kind":"pith_short_8","alias_value":"T6ZXFIM2","created_at":"2026-07-01T02:17:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:T6ZXFIM2EBAPOGNYIIKSNLEN5Y","target":"record","payload":{"canonical_record":{"source":{"id":"2606.32039","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T17:59:57Z","cross_cats_sorted":[],"title_canon_sha256":"9d99d435769758d6131a2c26c398cedf48a98b41bf404c4b984ee3bb317f3faf","abstract_canon_sha256":"4d004026551c6e5ba062b571533c87d6d7eb60325c7480931c66ee02e916cced"},"schema_version":"1.0"},"canonical_sha256":"9fb372a19a2040f719b8421526ac8dee287f659509452485ca04612b97faf133","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T02:17:48.057198Z","signature_b64":"doaEdOD5IooTTrmfniELKpTCmceCm/BxQjnEV/vQyOStJe+9IxCHrk3KR5oqwRcU8fhLDtE/OG6Frz53YCWYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fb372a19a2040f719b8421526ac8dee287f659509452485ca04612b97faf133","last_reissued_at":"2026-07-01T02:17:48.056716Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T02:17:48.056716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.32039","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":"2026-07-01T02:17:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1sMbvCn1plK9VQydPc6AXOMOr2gu36Wfai0Hqk5C7eN/Uw0jBM+5X4EAt8W3orcbqCEgYF79uXH+ry6iBEySBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T21:50:40.527308Z"},"content_sha256":"b6bd4c5d4a9fe631f4282cff3aa18b3324ac142877b4d74f759dd63e98666312","schema_version":"1.0","event_id":"sha256:b6bd4c5d4a9fe631f4282cff3aa18b3324ac142877b4d74f759dd63e98666312"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:T6ZXFIM2EBAPOGNYIIKSNLEN5Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GEAR: Guided End-to-End AutoRegression for Image Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Lin, Chenguo Lin, Jianwei Zhang, Liefeng Bo, Li Yuan, Miles Yang, Sixiang Chen, Yunlong Lin, Yunyang Ge, Zhao Zhong, Zheyuan Liu","submitted_at":"2026-06-30T17:59:57Z","abstract_excerpt":"Visual generative models are typically trained in two stages. A tokenizer is first trained for reconstruction and then frozen, after which a generator is trained on its discrete indices or continuous latents. This decoupling leaves the tokenizer unaware of what the generator finds easy to model. We present GEAR (Guided End-to-end AutoRegression), which trains a vector-quantized (VQ) tokenizer and an autoregressive (AR) generator jointly and end-to-end, guided by representation alignment. The key obstacle is that the VQ index fed to the AR model is non-differentiable, so gradients cannot reach "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.32039","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/2606.32039/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":"2026-07-01T02:17:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iK0EXUGvvpXa4FzeFZVCMrLDHEKORRJuLiBDdCVnBnOn9pRpKrDa9X9HLO9Yi+rAU8tVtwdiq7qNWUwV6Z3SDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T21:50:40.527708Z"},"content_sha256":"61f8fdca85451ed8985a65d5a9c361ba735a335dd208ce44cbd5ac395e0d78c8","schema_version":"1.0","event_id":"sha256:61f8fdca85451ed8985a65d5a9c361ba735a335dd208ce44cbd5ac395e0d78c8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T6ZXFIM2EBAPOGNYIIKSNLEN5Y/bundle.json","state_url":"https://pith.science/pith/T6ZXFIM2EBAPOGNYIIKSNLEN5Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T6ZXFIM2EBAPOGNYIIKSNLEN5Y/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":"2026-07-01T21:50:40Z","links":{"resolver":"https://pith.science/pith/T6ZXFIM2EBAPOGNYIIKSNLEN5Y","bundle":"https://pith.science/pith/T6ZXFIM2EBAPOGNYIIKSNLEN5Y/bundle.json","state":"https://pith.science/pith/T6ZXFIM2EBAPOGNYIIKSNLEN5Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T6ZXFIM2EBAPOGNYIIKSNLEN5Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:T6ZXFIM2EBAPOGNYIIKSNLEN5Y","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":"4d004026551c6e5ba062b571533c87d6d7eb60325c7480931c66ee02e916cced","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T17:59:57Z","title_canon_sha256":"9d99d435769758d6131a2c26c398cedf48a98b41bf404c4b984ee3bb317f3faf"},"schema_version":"1.0","source":{"id":"2606.32039","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.32039","created_at":"2026-07-01T02:17:48Z"},{"alias_kind":"arxiv_version","alias_value":"2606.32039v1","created_at":"2026-07-01T02:17:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.32039","created_at":"2026-07-01T02:17:48Z"},{"alias_kind":"pith_short_12","alias_value":"T6ZXFIM2EBAP","created_at":"2026-07-01T02:17:48Z"},{"alias_kind":"pith_short_16","alias_value":"T6ZXFIM2EBAPOGNY","created_at":"2026-07-01T02:17:48Z"},{"alias_kind":"pith_short_8","alias_value":"T6ZXFIM2","created_at":"2026-07-01T02:17:48Z"}],"graph_snapshots":[{"event_id":"sha256:61f8fdca85451ed8985a65d5a9c361ba735a335dd208ce44cbd5ac395e0d78c8","target":"graph","created_at":"2026-07-01T02:17:48Z","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/2606.32039/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual generative models are typically trained in two stages. A tokenizer is first trained for reconstruction and then frozen, after which a generator is trained on its discrete indices or continuous latents. This decoupling leaves the tokenizer unaware of what the generator finds easy to model. We present GEAR (Guided End-to-end AutoRegression), which trains a vector-quantized (VQ) tokenizer and an autoregressive (AR) generator jointly and end-to-end, guided by representation alignment. The key obstacle is that the VQ index fed to the AR model is non-differentiable, so gradients cannot reach ","authors_text":"Bin Lin, Chenguo Lin, Jianwei Zhang, Liefeng Bo, Li Yuan, Miles Yang, Sixiang Chen, Yunlong Lin, Yunyang Ge, Zhao Zhong, Zheyuan Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T17:59:57Z","title":"GEAR: Guided End-to-End AutoRegression for Image Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.32039","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:b6bd4c5d4a9fe631f4282cff3aa18b3324ac142877b4d74f759dd63e98666312","target":"record","created_at":"2026-07-01T02:17:48Z","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":"4d004026551c6e5ba062b571533c87d6d7eb60325c7480931c66ee02e916cced","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T17:59:57Z","title_canon_sha256":"9d99d435769758d6131a2c26c398cedf48a98b41bf404c4b984ee3bb317f3faf"},"schema_version":"1.0","source":{"id":"2606.32039","kind":"arxiv","version":1}},"canonical_sha256":"9fb372a19a2040f719b8421526ac8dee287f659509452485ca04612b97faf133","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fb372a19a2040f719b8421526ac8dee287f659509452485ca04612b97faf133","first_computed_at":"2026-07-01T02:17:48.056716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T02:17:48.056716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"doaEdOD5IooTTrmfniELKpTCmceCm/BxQjnEV/vQyOStJe+9IxCHrk3KR5oqwRcU8fhLDtE/OG6Frz53YCWYDQ==","signature_status":"signed_v1","signed_at":"2026-07-01T02:17:48.057198Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.32039","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6bd4c5d4a9fe631f4282cff3aa18b3324ac142877b4d74f759dd63e98666312","sha256:61f8fdca85451ed8985a65d5a9c361ba735a335dd208ce44cbd5ac395e0d78c8"],"state_sha256":"512129e94813a2d9929e201255e162cc4b6d0a97e15d910208238c9065675452"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d309CnYYOW+HUlmVenRITiMnhX0qW7yqqMQ5NiaGXCvxRyH+T2a0QphBnenSHwL3JEeIF5tghv/1RyQA4n1HAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T21:50:40.529805Z","bundle_sha256":"628ff8195eba64f91f131da3c78d0cade1b2be96e1ae9ccccc47a0c6435bf728"}}