{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CQQYATJYTH2WY77CVHWE3EJTBB","short_pith_number":"pith:CQQYATJY","canonical_record":{"source":{"id":"2412.08635","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T18:57:32Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"c37ccd10a51f8ed295e04a840bd93f8922b5c1f88f6074f7f6ca99bb81e8370c","abstract_canon_sha256":"0da9c442da0c0a0586222eabf01d697ec202e07056eb2b6f950b87a39bc517c4"},"schema_version":"1.0"},"canonical_sha256":"1421804d3899f56c7fe2a9ec4d9133087a4ac768f6cb4d7a2070e9a975644383","source":{"kind":"arxiv","id":"2412.08635","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08635","created_at":"2026-07-05T09:47:52Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08635v1","created_at":"2026-07-05T09:47:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08635","created_at":"2026-07-05T09:47:52Z"},{"alias_kind":"pith_short_12","alias_value":"CQQYATJYTH2W","created_at":"2026-07-05T09:47:52Z"},{"alias_kind":"pith_short_16","alias_value":"CQQYATJYTH2WY77C","created_at":"2026-07-05T09:47:52Z"},{"alias_kind":"pith_short_8","alias_value":"CQQYATJY","created_at":"2026-07-05T09:47:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CQQYATJYTH2WY77CVHWE3EJTBB","target":"record","payload":{"canonical_record":{"source":{"id":"2412.08635","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T18:57:32Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"c37ccd10a51f8ed295e04a840bd93f8922b5c1f88f6074f7f6ca99bb81e8370c","abstract_canon_sha256":"0da9c442da0c0a0586222eabf01d697ec202e07056eb2b6f950b87a39bc517c4"},"schema_version":"1.0"},"canonical_sha256":"1421804d3899f56c7fe2a9ec4d9133087a4ac768f6cb4d7a2070e9a975644383","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:52.642954Z","signature_b64":"e60hBV0CuQyxeKPTXsbBUIBVCP6ezZqUP56PdZcex5iIFSWZxahAPFdK+FHuSnsh+yY7DgRRQq6x+620NMXBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1421804d3899f56c7fe2a9ec4d9133087a4ac768f6cb4d7a2070e9a975644383","last_reissued_at":"2026-07-05T09:47:52.642454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:52.642454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.08635","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":"2026-07-05T09:47:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1qy3oZSD7jNKyxBPMty3slWf75WG6B9i2jaVcheG7jnWMv5BXCmSf4ZycF1rVV2xoWB5XRHbvwtMtS6r+nawBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:27:04.771286Z"},"content_sha256":"2ae92c7c006ac02d4553062881dada3bdabf000ba4a5d3bd6a03de3edbb21376","schema_version":"1.0","event_id":"sha256:2ae92c7c006ac02d4553062881dada3bdabf000ba4a5d3bd6a03de3edbb21376"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CQQYATJYTH2WY77CVHWE3EJTBB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Latent Language Modeling with Next-Token Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Furu Wei, Hangbo Bao, Jianyong Wang, Li Dong, Shaohan Huang, Wenhui Wang, Yutao Sun, Zhiliang Peng","submitted_at":"2024-12-11T18:57:32Z","abstract_excerpt":"Multimodal generative models require a unified approach to handle both discrete data (e.g., text and code) and continuous data (e.g., image, audio, video). In this work, we propose Latent Language Modeling (LatentLM), which seamlessly integrates continuous and discrete data using causal Transformers. Specifically, we employ a variational autoencoder (VAE) to represent continuous data as latent vectors and introduce next-token diffusion for autoregressive generation of these vectors. Additionally, we develop $\\sigma$-VAE to address the challenges of variance collapse, which is crucial for autor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08635","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/2412.08635/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":"2026-07-05T09:47:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZYImOOd7+/gt6uUa5hlZDmNepBFR7WDnXUmRtLApMyacq4EbaW0iTRFjEmghdk6KPc/g6UnwNSJKe2WcAgN0Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:27:04.771682Z"},"content_sha256":"b010c4e49d6638c0e8ee775aaa3e431ede840470c77c300a7720c7ad256510e4","schema_version":"1.0","event_id":"sha256:b010c4e49d6638c0e8ee775aaa3e431ede840470c77c300a7720c7ad256510e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CQQYATJYTH2WY77CVHWE3EJTBB/bundle.json","state_url":"https://pith.science/pith/CQQYATJYTH2WY77CVHWE3EJTBB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CQQYATJYTH2WY77CVHWE3EJTBB/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":"2026-07-07T12:27:04Z","links":{"resolver":"https://pith.science/pith/CQQYATJYTH2WY77CVHWE3EJTBB","bundle":"https://pith.science/pith/CQQYATJYTH2WY77CVHWE3EJTBB/bundle.json","state":"https://pith.science/pith/CQQYATJYTH2WY77CVHWE3EJTBB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CQQYATJYTH2WY77CVHWE3EJTBB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CQQYATJYTH2WY77CVHWE3EJTBB","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":"0da9c442da0c0a0586222eabf01d697ec202e07056eb2b6f950b87a39bc517c4","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T18:57:32Z","title_canon_sha256":"c37ccd10a51f8ed295e04a840bd93f8922b5c1f88f6074f7f6ca99bb81e8370c"},"schema_version":"1.0","source":{"id":"2412.08635","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08635","created_at":"2026-07-05T09:47:52Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08635v1","created_at":"2026-07-05T09:47:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08635","created_at":"2026-07-05T09:47:52Z"},{"alias_kind":"pith_short_12","alias_value":"CQQYATJYTH2W","created_at":"2026-07-05T09:47:52Z"},{"alias_kind":"pith_short_16","alias_value":"CQQYATJYTH2WY77C","created_at":"2026-07-05T09:47:52Z"},{"alias_kind":"pith_short_8","alias_value":"CQQYATJY","created_at":"2026-07-05T09:47:52Z"}],"graph_snapshots":[{"event_id":"sha256:b010c4e49d6638c0e8ee775aaa3e431ede840470c77c300a7720c7ad256510e4","target":"graph","created_at":"2026-07-05T09:47:52Z","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/2412.08635/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal generative models require a unified approach to handle both discrete data (e.g., text and code) and continuous data (e.g., image, audio, video). In this work, we propose Latent Language Modeling (LatentLM), which seamlessly integrates continuous and discrete data using causal Transformers. Specifically, we employ a variational autoencoder (VAE) to represent continuous data as latent vectors and introduce next-token diffusion for autoregressive generation of these vectors. Additionally, we develop $\\sigma$-VAE to address the challenges of variance collapse, which is crucial for autor","authors_text":"Furu Wei, Hangbo Bao, Jianyong Wang, Li Dong, Shaohan Huang, Wenhui Wang, Yutao Sun, Zhiliang Peng","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T18:57:32Z","title":"Multimodal Latent Language Modeling with Next-Token Diffusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08635","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":"sha256:2ae92c7c006ac02d4553062881dada3bdabf000ba4a5d3bd6a03de3edbb21376","target":"record","created_at":"2026-07-05T09:47:52Z","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":"0da9c442da0c0a0586222eabf01d697ec202e07056eb2b6f950b87a39bc517c4","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T18:57:32Z","title_canon_sha256":"c37ccd10a51f8ed295e04a840bd93f8922b5c1f88f6074f7f6ca99bb81e8370c"},"schema_version":"1.0","source":{"id":"2412.08635","kind":"arxiv","version":1}},"canonical_sha256":"1421804d3899f56c7fe2a9ec4d9133087a4ac768f6cb4d7a2070e9a975644383","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1421804d3899f56c7fe2a9ec4d9133087a4ac768f6cb4d7a2070e9a975644383","first_computed_at":"2026-07-05T09:47:52.642454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:52.642454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e60hBV0CuQyxeKPTXsbBUIBVCP6ezZqUP56PdZcex5iIFSWZxahAPFdK+FHuSnsh+yY7DgRRQq6x+620NMXBAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:52.642954Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08635","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ae92c7c006ac02d4553062881dada3bdabf000ba4a5d3bd6a03de3edbb21376","sha256:b010c4e49d6638c0e8ee775aaa3e431ede840470c77c300a7720c7ad256510e4"],"state_sha256":"af20169addd37b2cd5ea87c6347a21e44a9c60d5b1d2e4e75205941142c20653"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zEp+B/CnBKZwvalPJAxAkA3wt/XwVBNYur8nBKmGYqKx+CCcVWF+8o1i8c406yT04m2F6punuy4G684oG6RHBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:27:04.773609Z","bundle_sha256":"f95d143c78c5c5201097f15c751dd3a82b644760feec2d4c5556f0a80ceadedf"}}