{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TUM7LJCEY77AOEC42WOTJV2B2U","short_pith_number":"pith:TUM7LJCE","canonical_record":{"source":{"id":"2411.04406","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T03:55:23Z","cross_cats_sorted":[],"title_canon_sha256":"9c6a058a033cf28222463f9d6080376de08cda2095eea83c65010b35ad65568c","abstract_canon_sha256":"b2c39feb3f7e000d9fce9acf01af83c67c0e23637bc66b3da66b057e69e0187b"},"schema_version":"1.0"},"canonical_sha256":"9d19f5a444c7fe07105cd59d34d741d53de492fa98d5385ecb4edcd9f390d2f0","source":{"kind":"arxiv","id":"2411.04406","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04406","created_at":"2026-07-05T09:32:19Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04406v1","created_at":"2026-07-05T09:32:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04406","created_at":"2026-07-05T09:32:19Z"},{"alias_kind":"pith_short_12","alias_value":"TUM7LJCEY77A","created_at":"2026-07-05T09:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"TUM7LJCEY77AOEC4","created_at":"2026-07-05T09:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"TUM7LJCE","created_at":"2026-07-05T09:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TUM7LJCEY77AOEC42WOTJV2B2U","target":"record","payload":{"canonical_record":{"source":{"id":"2411.04406","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T03:55:23Z","cross_cats_sorted":[],"title_canon_sha256":"9c6a058a033cf28222463f9d6080376de08cda2095eea83c65010b35ad65568c","abstract_canon_sha256":"b2c39feb3f7e000d9fce9acf01af83c67c0e23637bc66b3da66b057e69e0187b"},"schema_version":"1.0"},"canonical_sha256":"9d19f5a444c7fe07105cd59d34d741d53de492fa98d5385ecb4edcd9f390d2f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:19.040932Z","signature_b64":"6K9iJqB42lnl1YWscj+MJVvSguVHv3RDu8sbSAOnI5wWKE+WHH+cpJsqql3LpeQCtKw0g9pIhIPk8yFAJ9FkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d19f5a444c7fe07105cd59d34d741d53de492fa98d5385ecb4edcd9f390d2f0","last_reissued_at":"2026-07-05T09:32:19.040439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:19.040439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.04406","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":"2026-07-05T09:32:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"152/4hnBYFsFRspxFxjn5K6f6gVDgZmAFtrupAYGa8cK/l61C62wVBmrWreMUK5caykGodQQ4FRYcmLb0mEtDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T23:08:30.047618Z"},"content_sha256":"875f80e141616d86deb9054fe2e5d9f4400094a5ba66b7ebb6315b4b8bec31cf","schema_version":"1.0","event_id":"sha256:875f80e141616d86deb9054fe2e5d9f4400094a5ba66b7ebb6315b4b8bec31cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TUM7LJCEY77AOEC42WOTJV2B2U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Image Understanding Makes for A Good Tokenizer for Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyi Kang, Jiashi Feng, Luting Wang, Si Liu, Yang Zhao, Zijian Zhang","submitted_at":"2024-11-07T03:55:23Z","abstract_excerpt":"Abstract Modern image generation (IG) models have been shown to capture rich semantics valuable for image understanding (IU) tasks. However, the potential of IU models to improve IG performance remains uncharted. We address this issue using a token-based IG framework, which relies on effective tokenizers to project images into token sequences. Currently, pixel reconstruction (e.g., VQGAN) dominates the training objective for image tokenizers. In contrast, our approach adopts the feature reconstruction objective, where tokenizers are trained by distilling knowledge from pretrained IU encoders. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04406","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/2411.04406/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":"2026-07-05T09:32:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iTyLGeJJJx33uxpbn235TjRr6RWRPdwdViC/m/bufOmf88Llaua4JcE2a/111RaIv99V7uO1L6M6n2dgAsrXCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T23:08:30.048110Z"},"content_sha256":"a6130c606efcfa01590fd6b505527582cccce312984992e8d8bccb0d2e453166","schema_version":"1.0","event_id":"sha256:a6130c606efcfa01590fd6b505527582cccce312984992e8d8bccb0d2e453166"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TUM7LJCEY77AOEC42WOTJV2B2U/bundle.json","state_url":"https://pith.science/pith/TUM7LJCEY77AOEC42WOTJV2B2U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TUM7LJCEY77AOEC42WOTJV2B2U/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":"2026-08-14T23:08:30Z","links":{"resolver":"https://pith.science/pith/TUM7LJCEY77AOEC42WOTJV2B2U","bundle":"https://pith.science/pith/TUM7LJCEY77AOEC42WOTJV2B2U/bundle.json","state":"https://pith.science/pith/TUM7LJCEY77AOEC42WOTJV2B2U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TUM7LJCEY77AOEC42WOTJV2B2U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TUM7LJCEY77AOEC42WOTJV2B2U","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":"b2c39feb3f7e000d9fce9acf01af83c67c0e23637bc66b3da66b057e69e0187b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T03:55:23Z","title_canon_sha256":"9c6a058a033cf28222463f9d6080376de08cda2095eea83c65010b35ad65568c"},"schema_version":"1.0","source":{"id":"2411.04406","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04406","created_at":"2026-07-05T09:32:19Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04406v1","created_at":"2026-07-05T09:32:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04406","created_at":"2026-07-05T09:32:19Z"},{"alias_kind":"pith_short_12","alias_value":"TUM7LJCEY77A","created_at":"2026-07-05T09:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"TUM7LJCEY77AOEC4","created_at":"2026-07-05T09:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"TUM7LJCE","created_at":"2026-07-05T09:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:a6130c606efcfa01590fd6b505527582cccce312984992e8d8bccb0d2e453166","target":"graph","created_at":"2026-07-05T09:32:19Z","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/2411.04406/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Abstract Modern image generation (IG) models have been shown to capture rich semantics valuable for image understanding (IU) tasks. However, the potential of IU models to improve IG performance remains uncharted. We address this issue using a token-based IG framework, which relies on effective tokenizers to project images into token sequences. Currently, pixel reconstruction (e.g., VQGAN) dominates the training objective for image tokenizers. In contrast, our approach adopts the feature reconstruction objective, where tokenizers are trained by distilling knowledge from pretrained IU encoders. ","authors_text":"Bingyi Kang, Jiashi Feng, Luting Wang, Si Liu, Yang Zhao, Zijian Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T03:55:23Z","title":"Image Understanding Makes for A Good Tokenizer for Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04406","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":"sha256:875f80e141616d86deb9054fe2e5d9f4400094a5ba66b7ebb6315b4b8bec31cf","target":"record","created_at":"2026-07-05T09:32:19Z","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":"b2c39feb3f7e000d9fce9acf01af83c67c0e23637bc66b3da66b057e69e0187b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T03:55:23Z","title_canon_sha256":"9c6a058a033cf28222463f9d6080376de08cda2095eea83c65010b35ad65568c"},"schema_version":"1.0","source":{"id":"2411.04406","kind":"arxiv","version":1}},"canonical_sha256":"9d19f5a444c7fe07105cd59d34d741d53de492fa98d5385ecb4edcd9f390d2f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d19f5a444c7fe07105cd59d34d741d53de492fa98d5385ecb4edcd9f390d2f0","first_computed_at":"2026-07-05T09:32:19.040439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:32:19.040439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6K9iJqB42lnl1YWscj+MJVvSguVHv3RDu8sbSAOnI5wWKE+WHH+cpJsqql3LpeQCtKw0g9pIhIPk8yFAJ9FkDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:32:19.040932Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.04406","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:875f80e141616d86deb9054fe2e5d9f4400094a5ba66b7ebb6315b4b8bec31cf","sha256:a6130c606efcfa01590fd6b505527582cccce312984992e8d8bccb0d2e453166"],"state_sha256":"85c3c4c41afc9a2dade70faf0ed18f6182a5fce08b1ac717165373fffbcfa41d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uSIe4YQcwUd/fKwBDHIlrxDdHEj5Z64B5eugjWi59j0nirMBaSJwC8srZVpqdeIxINBAYTHb7BwZoocbcS0mBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T23:08:30.051341Z","bundle_sha256":"f5e79d9a98719eeea5588d0c7b897de89c90ad228cf3d54d2acf1d1130db5403"}}