{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YDY4JWRX5E6QAZCYGASZETKQ3Q","short_pith_number":"pith:YDY4JWRX","canonical_record":{"source":{"id":"2506.18898","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T17:59:14Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"abb61662fd8d58de87eb161e16270a08b9bf8111918d999ee906701ed179de69","abstract_canon_sha256":"17786d9d17f9cadef8b7a8fb27d4369e10db6c73adb5950a8e1d0dcb73db52cc"},"schema_version":"1.0"},"canonical_sha256":"c0f1c4da37e93d0064583025924d50dc32dc585331f48842ba8b0a1574f9def8","source":{"kind":"arxiv","id":"2506.18898","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18898","created_at":"2026-07-05T11:25:57Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18898v1","created_at":"2026-07-05T11:25:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18898","created_at":"2026-07-05T11:25:57Z"},{"alias_kind":"pith_short_12","alias_value":"YDY4JWRX5E6Q","created_at":"2026-07-05T11:25:57Z"},{"alias_kind":"pith_short_16","alias_value":"YDY4JWRX5E6QAZCY","created_at":"2026-07-05T11:25:57Z"},{"alias_kind":"pith_short_8","alias_value":"YDY4JWRX","created_at":"2026-07-05T11:25:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YDY4JWRX5E6QAZCYGASZETKQ3Q","target":"record","payload":{"canonical_record":{"source":{"id":"2506.18898","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T17:59:14Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"abb61662fd8d58de87eb161e16270a08b9bf8111918d999ee906701ed179de69","abstract_canon_sha256":"17786d9d17f9cadef8b7a8fb27d4369e10db6c73adb5950a8e1d0dcb73db52cc"},"schema_version":"1.0"},"canonical_sha256":"c0f1c4da37e93d0064583025924d50dc32dc585331f48842ba8b0a1574f9def8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:57.782908Z","signature_b64":"ZSjQKTyP+XcyNyQEof3KfNN7Dh1xnau1z+mATS10v4Nt38krnpcGvJHjfMzY3pIPFkNIBFueleSLjRCZaDTvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0f1c4da37e93d0064583025924d50dc32dc585331f48842ba8b0a1574f9def8","last_reissued_at":"2026-07-05T11:25:57.782436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:57.782436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.18898","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":"2026-07-05T11:25:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H4Zld67P0MYMVcwo4OtLkSLb828YMQPWGq2XpbR6Xh5HM8qd+2BltnDHTWQh9yk4VGDKYw8fluAxicMgw9pIBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:31:42.016399Z"},"content_sha256":"5fba793002f8435cb5d3e84617d73544a027e27a4b98effd8e1e50e9dae7d900","schema_version":"1.0","event_id":"sha256:5fba793002f8435cb5d3e84617d73544a027e27a4b98effd8e1e50e9dae7d900"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YDY4JWRX5E6QAZCYGASZETKQ3Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Hanyu Wang, Hao Chen, Hao He, Jiaming Han, Lu Jiang, Qi Zhao, Xiangyu Yue, Yang Zhao, Ziyan Yang","submitted_at":"2025-06-23T17:59:14Z","abstract_excerpt":"This paper presents a multimodal framework that attempts to unify visual understanding and generation within a shared discrete semantic representation. At its core is the Text-Aligned Tokenizer (TA-Tok), which converts images into discrete tokens using a text-aligned codebook projected from a large language model's (LLM) vocabulary. By integrating vision and text into a unified space with an expanded vocabulary, our multimodal LLM, Tar, enables cross-modal input and output through a shared interface, without the need for modality-specific designs. Additionally, we propose scale-adaptive encodi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18898","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/2506.18898/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":"2026-07-05T11:25:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t4RiEcmvQA8F5bBIJTskcD+fibrZveGqzDN2svytCNdUPYUS+8cKbHrn06JtnMDjYxPnjKhfPdu7RP3KuAYrDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:31:42.016933Z"},"content_sha256":"5f14373abadc2607571574bcf9e042accd66897dcf393626ee6cb9ec751238a3","schema_version":"1.0","event_id":"sha256:5f14373abadc2607571574bcf9e042accd66897dcf393626ee6cb9ec751238a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YDY4JWRX5E6QAZCYGASZETKQ3Q/bundle.json","state_url":"https://pith.science/pith/YDY4JWRX5E6QAZCYGASZETKQ3Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YDY4JWRX5E6QAZCYGASZETKQ3Q/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":"2026-08-19T08:31:42Z","links":{"resolver":"https://pith.science/pith/YDY4JWRX5E6QAZCYGASZETKQ3Q","bundle":"https://pith.science/pith/YDY4JWRX5E6QAZCYGASZETKQ3Q/bundle.json","state":"https://pith.science/pith/YDY4JWRX5E6QAZCYGASZETKQ3Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YDY4JWRX5E6QAZCYGASZETKQ3Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YDY4JWRX5E6QAZCYGASZETKQ3Q","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":"17786d9d17f9cadef8b7a8fb27d4369e10db6c73adb5950a8e1d0dcb73db52cc","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T17:59:14Z","title_canon_sha256":"abb61662fd8d58de87eb161e16270a08b9bf8111918d999ee906701ed179de69"},"schema_version":"1.0","source":{"id":"2506.18898","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18898","created_at":"2026-07-05T11:25:57Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18898v1","created_at":"2026-07-05T11:25:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18898","created_at":"2026-07-05T11:25:57Z"},{"alias_kind":"pith_short_12","alias_value":"YDY4JWRX5E6Q","created_at":"2026-07-05T11:25:57Z"},{"alias_kind":"pith_short_16","alias_value":"YDY4JWRX5E6QAZCY","created_at":"2026-07-05T11:25:57Z"},{"alias_kind":"pith_short_8","alias_value":"YDY4JWRX","created_at":"2026-07-05T11:25:57Z"}],"graph_snapshots":[{"event_id":"sha256:5f14373abadc2607571574bcf9e042accd66897dcf393626ee6cb9ec751238a3","target":"graph","created_at":"2026-07-05T11:25:57Z","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/2506.18898/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a multimodal framework that attempts to unify visual understanding and generation within a shared discrete semantic representation. At its core is the Text-Aligned Tokenizer (TA-Tok), which converts images into discrete tokens using a text-aligned codebook projected from a large language model's (LLM) vocabulary. By integrating vision and text into a unified space with an expanded vocabulary, our multimodal LLM, Tar, enables cross-modal input and output through a shared interface, without the need for modality-specific designs. Additionally, we propose scale-adaptive encodi","authors_text":"Hanyu Wang, Hao Chen, Hao He, Jiaming Han, Lu Jiang, Qi Zhao, Xiangyu Yue, Yang Zhao, Ziyan Yang","cross_cats":["cs.AI","cs.CL","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T17:59:14Z","title":"Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18898","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":"sha256:5fba793002f8435cb5d3e84617d73544a027e27a4b98effd8e1e50e9dae7d900","target":"record","created_at":"2026-07-05T11:25:57Z","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":"17786d9d17f9cadef8b7a8fb27d4369e10db6c73adb5950a8e1d0dcb73db52cc","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T17:59:14Z","title_canon_sha256":"abb61662fd8d58de87eb161e16270a08b9bf8111918d999ee906701ed179de69"},"schema_version":"1.0","source":{"id":"2506.18898","kind":"arxiv","version":1}},"canonical_sha256":"c0f1c4da37e93d0064583025924d50dc32dc585331f48842ba8b0a1574f9def8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0f1c4da37e93d0064583025924d50dc32dc585331f48842ba8b0a1574f9def8","first_computed_at":"2026-07-05T11:25:57.782436Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:57.782436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZSjQKTyP+XcyNyQEof3KfNN7Dh1xnau1z+mATS10v4Nt38krnpcGvJHjfMzY3pIPFkNIBFueleSLjRCZaDTvDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:57.782908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.18898","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fba793002f8435cb5d3e84617d73544a027e27a4b98effd8e1e50e9dae7d900","sha256:5f14373abadc2607571574bcf9e042accd66897dcf393626ee6cb9ec751238a3"],"state_sha256":"48eff4bb81d3c9114dfc5fe0a1cd93e8d9da85143da0a36b72da82f53274f158"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YLL+tKWD005to/wzDP+mMFFLVDm4/BpX2jbEk0W3Qb+ITEVrX7iMUOsr0r9BNvtB2mGO6gzgrJqpGoGXXK0zDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T08:31:42.022841Z","bundle_sha256":"1e7b4b605c45682463ca2f59f8753e3cdc14fd40584f033bee0cb96ce4c6208a"}}