{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TVJYMOI7BYLVAD2IAWQFFSDNOQ","short_pith_number":"pith:TVJYMOI7","canonical_record":{"source":{"id":"2605.01220","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-02T03:23:17Z","cross_cats_sorted":[],"title_canon_sha256":"7cfe217f457e820674ec49e1e5d4bae0ad9be3faa8d84b98ee571e7155adfa86","abstract_canon_sha256":"d9a79303a0fff059355a99145d9725e225594bbcd4262220397dffccb674c08c"},"schema_version":"1.0"},"canonical_sha256":"9d5386391f0e17500f4805a052c86d742547267ede009c929cb2fb0da07f00ac","source":{"kind":"arxiv","id":"2605.01220","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.01220","created_at":"2026-07-07T02:19:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.01220v2","created_at":"2026-07-07T02:19:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.01220","created_at":"2026-07-07T02:19:51Z"},{"alias_kind":"pith_short_12","alias_value":"TVJYMOI7BYLV","created_at":"2026-07-07T02:19:51Z"},{"alias_kind":"pith_short_16","alias_value":"TVJYMOI7BYLVAD2I","created_at":"2026-07-07T02:19:51Z"},{"alias_kind":"pith_short_8","alias_value":"TVJYMOI7","created_at":"2026-07-07T02:19:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TVJYMOI7BYLVAD2IAWQFFSDNOQ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.01220","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-02T03:23:17Z","cross_cats_sorted":[],"title_canon_sha256":"7cfe217f457e820674ec49e1e5d4bae0ad9be3faa8d84b98ee571e7155adfa86","abstract_canon_sha256":"d9a79303a0fff059355a99145d9725e225594bbcd4262220397dffccb674c08c"},"schema_version":"1.0"},"canonical_sha256":"9d5386391f0e17500f4805a052c86d742547267ede009c929cb2fb0da07f00ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:51.649947Z","signature_b64":"K4EBvP67rFG6mdPMFs1TcWmmvP9eGIlay7h2VkFVEgqemdVDooXVJMq5AJz7DLh4brBIXiea9v+hpPgfPDNXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d5386391f0e17500f4805a052c86d742547267ede009c929cb2fb0da07f00ac","last_reissued_at":"2026-07-07T02:19:51.649073Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:51.649073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.01220","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-07T02:19:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u9Z/6kB/wSxDR0QVdjf1YuXF84YA804MJ1rnj/fpcT0xDFPsxJaDg/DsFPlLOUMs881l56pvgxY0ZK2XrCtlAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:38:39.195189Z"},"content_sha256":"291b2d603347ccdda149df397db79d031ec585228cbcbc20897f53883060c72c","schema_version":"1.0","event_id":"sha256:291b2d603347ccdda149df397db79d031ec585228cbcbc20897f53883060c72c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TVJYMOI7BYLVAD2IAWQFFSDNOQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Implicit Autoregressive Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"VIAR embeds an implicit equilibrium layer in next-scale autoregressive generation to match VAR quality with 38% of the parameters and flexible inference compute.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jixiang Luo, Luxi Lin, Pengfei Jiang, Xuelong Li, Zhaohong Huang","submitted_at":"2026-05-02T03:23:17Z","abstract_excerpt":"Visual Autoregressive Modeling (VAR) based on next-scale prediction achieves strong generation quality, but their explicit deep stacks fix the amount of computation per scale and inflate memory at high resolutions. We introduce Visual Implicit Autoregressive Modeling (VIAR), a next-scale autoregressive generator that embeds an implicit equilibrium layer between shallow pre/post blocks. The implicit layer is trained with Jacobian-Free Backpropagation, yielding constant training memory, while inference exposes a per-scale iteration knob that enables compute control. On ImageNet 256x256 benchmark"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On ImageNet 256x256 benchmark, VIAR attains FID 2.16, and sFID 8.07 with only 38.4% parameters of VAR, matching or surpassing strong AR baselines and remaining competitive with large diffusion models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The implicit equilibrium layer converges reliably under Jacobian-Free Backpropagation and that the per-scale iteration count can be varied post-training without degrading the learned fixed point.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"VIAR embeds implicit equilibrium layers in visual autoregressive models to achieve ImageNet FID 2.16 with 38.4% of VAR parameters and controllable inference compute.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"VIAR embeds an implicit equilibrium layer in next-scale autoregressive generation to match VAR quality with 38% of the parameters and flexible inference compute.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b00bf48e169574c19b1f7cbd3a6bf9ed55885f5764d93d21bf80043efef4dc77"},"source":{"id":"2605.01220","kind":"arxiv","version":2},"verdict":{"id":"a50afde5-502c-461b-ac6d-fc6cef970808","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T15:17:05.163107Z","strongest_claim":"On ImageNet 256x256 benchmark, VIAR attains FID 2.16, and sFID 8.07 with only 38.4% parameters of VAR, matching or surpassing strong AR baselines and remaining competitive with large diffusion models.","one_line_summary":"VIAR embeds implicit equilibrium layers in visual autoregressive models to achieve ImageNet FID 2.16 with 38.4% of VAR parameters and controllable inference compute.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The implicit equilibrium layer converges reliably under Jacobian-Free Backpropagation and that the per-scale iteration count can be varied post-training without degrading the learned fixed point.","pith_extraction_headline":"VIAR embeds an implicit equilibrium layer in next-scale autoregressive generation to match VAR quality with 38% of the parameters and flexible inference compute."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.01220/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T18:36:39.018813Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T17:29:15.800483Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"6f1bfb281bf06b55962717449bf4665a77a5033090aebef2c298536b426b9e25"},"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":"a50afde5-502c-461b-ac6d-fc6cef970808"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-07T02:19:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hu8a4NzBPwMe9gqzW+lx9/kvNpmNrcj5oh+R9LPt7b5n4Y7puxcgYsnmkIgnnq9HoSnvbQmMNcI/uA1VeAiCAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:38:39.196031Z"},"content_sha256":"c144110f6304decda23ce3232371a8e6424fbbd7a7126031a5d358658d0f46f0","schema_version":"1.0","event_id":"sha256:c144110f6304decda23ce3232371a8e6424fbbd7a7126031a5d358658d0f46f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TVJYMOI7BYLVAD2IAWQFFSDNOQ/bundle.json","state_url":"https://pith.science/pith/TVJYMOI7BYLVAD2IAWQFFSDNOQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TVJYMOI7BYLVAD2IAWQFFSDNOQ/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":"2026-08-07T10:38:39Z","links":{"resolver":"https://pith.science/pith/TVJYMOI7BYLVAD2IAWQFFSDNOQ","bundle":"https://pith.science/pith/TVJYMOI7BYLVAD2IAWQFFSDNOQ/bundle.json","state":"https://pith.science/pith/TVJYMOI7BYLVAD2IAWQFFSDNOQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TVJYMOI7BYLVAD2IAWQFFSDNOQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TVJYMOI7BYLVAD2IAWQFFSDNOQ","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":"d9a79303a0fff059355a99145d9725e225594bbcd4262220397dffccb674c08c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-02T03:23:17Z","title_canon_sha256":"7cfe217f457e820674ec49e1e5d4bae0ad9be3faa8d84b98ee571e7155adfa86"},"schema_version":"1.0","source":{"id":"2605.01220","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.01220","created_at":"2026-07-07T02:19:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.01220v2","created_at":"2026-07-07T02:19:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.01220","created_at":"2026-07-07T02:19:51Z"},{"alias_kind":"pith_short_12","alias_value":"TVJYMOI7BYLV","created_at":"2026-07-07T02:19:51Z"},{"alias_kind":"pith_short_16","alias_value":"TVJYMOI7BYLVAD2I","created_at":"2026-07-07T02:19:51Z"},{"alias_kind":"pith_short_8","alias_value":"TVJYMOI7","created_at":"2026-07-07T02:19:51Z"}],"graph_snapshots":[{"event_id":"sha256:c144110f6304decda23ce3232371a8e6424fbbd7a7126031a5d358658d0f46f0","target":"graph","created_at":"2026-07-07T02:19:51Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"On ImageNet 256x256 benchmark, VIAR attains FID 2.16, and sFID 8.07 with only 38.4% parameters of VAR, matching or surpassing strong AR baselines and remaining competitive with large diffusion models."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The implicit equilibrium layer converges reliably under Jacobian-Free Backpropagation and that the per-scale iteration count can be varied post-training without degrading the learned fixed point."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"VIAR embeds implicit equilibrium layers in visual autoregressive models to achieve ImageNet FID 2.16 with 38.4% of VAR parameters and controllable inference compute."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"VIAR embeds an implicit equilibrium layer in next-scale autoregressive generation to match VAR quality with 38% of the parameters and flexible inference compute."}],"snapshot_sha256":"b00bf48e169574c19b1f7cbd3a6bf9ed55885f5764d93d21bf80043efef4dc77"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T18:36:39.018813Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T17:29:15.800483Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.01220/integrity.json","findings":[],"snapshot_sha256":"6f1bfb281bf06b55962717449bf4665a77a5033090aebef2c298536b426b9e25","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Autoregressive Modeling (VAR) based on next-scale prediction achieves strong generation quality, but their explicit deep stacks fix the amount of computation per scale and inflate memory at high resolutions. We introduce Visual Implicit Autoregressive Modeling (VIAR), a next-scale autoregressive generator that embeds an implicit equilibrium layer between shallow pre/post blocks. The implicit layer is trained with Jacobian-Free Backpropagation, yielding constant training memory, while inference exposes a per-scale iteration knob that enables compute control. On ImageNet 256x256 benchmark","authors_text":"Jixiang Luo, Luxi Lin, Pengfei Jiang, Xuelong Li, Zhaohong Huang","cross_cats":[],"headline":"VIAR embeds an implicit equilibrium layer in next-scale autoregressive generation to match VAR quality with 38% of the parameters and flexible inference compute.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-02T03:23:17Z","title":"Visual Implicit Autoregressive Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.01220","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-09T15:17:05.163107Z","id":"a50afde5-502c-461b-ac6d-fc6cef970808","model_set":{"reader":"grok-4.3"},"one_line_summary":"VIAR embeds implicit equilibrium layers in visual autoregressive models to achieve ImageNet FID 2.16 with 38.4% of VAR parameters and controllable inference compute.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"VIAR embeds an implicit equilibrium layer in next-scale autoregressive generation to match VAR quality with 38% of the parameters and flexible inference compute.","strongest_claim":"On ImageNet 256x256 benchmark, VIAR attains FID 2.16, and sFID 8.07 with only 38.4% parameters of VAR, matching or surpassing strong AR baselines and remaining competitive with large diffusion models.","weakest_assumption":"The implicit equilibrium layer converges reliably under Jacobian-Free Backpropagation and that the per-scale iteration count can be varied post-training without degrading the learned fixed point."}},"verdict_id":"a50afde5-502c-461b-ac6d-fc6cef970808"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:291b2d603347ccdda149df397db79d031ec585228cbcbc20897f53883060c72c","target":"record","created_at":"2026-07-07T02:19:51Z","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":"d9a79303a0fff059355a99145d9725e225594bbcd4262220397dffccb674c08c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-02T03:23:17Z","title_canon_sha256":"7cfe217f457e820674ec49e1e5d4bae0ad9be3faa8d84b98ee571e7155adfa86"},"schema_version":"1.0","source":{"id":"2605.01220","kind":"arxiv","version":2}},"canonical_sha256":"9d5386391f0e17500f4805a052c86d742547267ede009c929cb2fb0da07f00ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d5386391f0e17500f4805a052c86d742547267ede009c929cb2fb0da07f00ac","first_computed_at":"2026-07-07T02:19:51.649073Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:19:51.649073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K4EBvP67rFG6mdPMFs1TcWmmvP9eGIlay7h2VkFVEgqemdVDooXVJMq5AJz7DLh4brBIXiea9v+hpPgfPDNXCw==","signature_status":"signed_v1","signed_at":"2026-07-07T02:19:51.649947Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.01220","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:291b2d603347ccdda149df397db79d031ec585228cbcbc20897f53883060c72c","sha256:c144110f6304decda23ce3232371a8e6424fbbd7a7126031a5d358658d0f46f0"],"state_sha256":"49ee58feb4ff7ef307adbb11c6826a49ca4591f7c65a07b452e2f95c82fe06ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+iI0XB2JfadPv36ejrm7mVjEAraf9fr5bZ5OsAjNhHqsv8S0bYW2YJWrshRz9FbHW7V8tnjQkCqpL/hQTQSlDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T10:38:39.201981Z","bundle_sha256":"e3c166fb8aba2cf72aa3cdb1d7b020ed6c707f1a37c17f513a620daabd89b58c"}}