{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2GYQR6KA2MGDOCZZBM44IO6DPB","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":"36a708e0238aa8c92fa6b20371067186617f25d8c6aaaec0757fbc1dc95175e1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T17:12:19Z","title_canon_sha256":"6028440f4ecf5d73a7aa660c0db1ac0cbd688ec121f4d8e24ea63a4371ddc1e5"},"schema_version":"1.0","source":{"id":"2505.05422","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05422","created_at":"2026-07-05T11:54:11Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05422v2","created_at":"2026-07-05T11:54:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05422","created_at":"2026-07-05T11:54:11Z"},{"alias_kind":"pith_short_12","alias_value":"2GYQR6KA2MGD","created_at":"2026-07-05T11:54:11Z"},{"alias_kind":"pith_short_16","alias_value":"2GYQR6KA2MGDOCZZ","created_at":"2026-07-05T11:54:11Z"},{"alias_kind":"pith_short_8","alias_value":"2GYQR6KA","created_at":"2026-07-05T11:54:11Z"}],"graph_snapshots":[{"event_id":"sha256:ea82771315e4e9ebd45cd92ce8bced93be58ba5146883082bb7638a22af7559c","target":"graph","created_at":"2026-07-05T11:54:11Z","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/2505.05422/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pioneering token-based works such as Chameleon and Emu3 have established a foundation for multimodal unification but face challenges of high training computational overhead and limited comprehension performance due to a lack of high-level semantics. In this paper, we introduce TokLIP, a visual tokenizer that enhances comprehension by semanticizing vector-quantized (VQ) tokens and incorporating CLIP-level semantics while enabling end-to-end multimodal autoregressive training with standard VQ tokens. TokLIP integrates a low-level discrete VQ tokenizer with a ViT-based token encoder to capture hi","authors_text":"Haokun Lin, Qingfu Zhang, Teng Wang, Ying Shan, Ying Wei, Yixiao Ge, Yuying Ge, Zhenan Sun, Zhichao Lu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T17:12:19Z","title":"TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05422","kind":"arxiv","version":2},"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":"sha256:60bafc5ed3d397ca7cf54a250b571481ab96c7094e187333825a2db085b5506e","target":"record","created_at":"2026-07-05T11:54:11Z","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":"36a708e0238aa8c92fa6b20371067186617f25d8c6aaaec0757fbc1dc95175e1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T17:12:19Z","title_canon_sha256":"6028440f4ecf5d73a7aa660c0db1ac0cbd688ec121f4d8e24ea63a4371ddc1e5"},"schema_version":"1.0","source":{"id":"2505.05422","kind":"arxiv","version":2}},"canonical_sha256":"d1b108f940d30c370b390b39c43bc37874bc570e95f8938e4239c1af3a68c105","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1b108f940d30c370b390b39c43bc37874bc570e95f8938e4239c1af3a68c105","first_computed_at":"2026-07-05T11:54:11.995716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:11.995716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A+AtSAQGVeG1Kwv0wlX2kF1RJ5WDk3TE1c9rJDATj50XxC/6QCrmp5f2rLSIR9fDM8xy3tvTy53uNuX/FYK/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:11.996222Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.05422","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60bafc5ed3d397ca7cf54a250b571481ab96c7094e187333825a2db085b5506e","sha256:ea82771315e4e9ebd45cd92ce8bced93be58ba5146883082bb7638a22af7559c"],"state_sha256":"0fc4044c23ebdb7a9a4807cbdbff764105ecc9a071003d068bb0ff82fe830b1c"}