{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:72JWBN34NGDST6NS4X4YRLCVZH","short_pith_number":"pith:72JWBN34","canonical_record":{"source":{"id":"2402.12226","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T15:33:10Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"1feb306d48308873e1370d24b96d409d83cb81c65c3d221c491b2d371e43891c","abstract_canon_sha256":"1c41e3946a7dbcc5034d9d947b54a6a92a3c4c375cee096ed7770def7ba71de1"},"schema_version":"1.0"},"canonical_sha256":"fe9360b77c698729f9b2e5f988ac55c9f827ff855e673c7cbf36869a85b87146","source":{"kind":"arxiv","id":"2402.12226","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12226","created_at":"2026-07-05T12:05:59Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12226v5","created_at":"2026-07-05T12:05:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12226","created_at":"2026-07-05T12:05:59Z"},{"alias_kind":"pith_short_12","alias_value":"72JWBN34NGDS","created_at":"2026-07-05T12:05:59Z"},{"alias_kind":"pith_short_16","alias_value":"72JWBN34NGDST6NS","created_at":"2026-07-05T12:05:59Z"},{"alias_kind":"pith_short_8","alias_value":"72JWBN34","created_at":"2026-07-05T12:05:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:72JWBN34NGDST6NS4X4YRLCVZH","target":"record","payload":{"canonical_record":{"source":{"id":"2402.12226","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T15:33:10Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"1feb306d48308873e1370d24b96d409d83cb81c65c3d221c491b2d371e43891c","abstract_canon_sha256":"1c41e3946a7dbcc5034d9d947b54a6a92a3c4c375cee096ed7770def7ba71de1"},"schema_version":"1.0"},"canonical_sha256":"fe9360b77c698729f9b2e5f988ac55c9f827ff855e673c7cbf36869a85b87146","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:59.169470Z","signature_b64":"0LkSrXvoWGx7r/qIWCpJN6EOOrjnKgqX4rCDtmI1aM+lE1GX1DqwuMGQowUHboAZgnR3Q9ok1f7hIw0RDrhBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe9360b77c698729f9b2e5f988ac55c9f827ff855e673c7cbf36869a85b87146","last_reissued_at":"2026-07-05T12:05:59.168877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:59.168877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.12226","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:05:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LHJPb1wWCYfSvkfOctwMAtMiFYJXF8oEyUuPeLANyo0eUw9q3LXsSwIpx/czsQDkFIIxbrRYcxsYLhI0GC24CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T23:46:49.771925Z"},"content_sha256":"05d20aef24216c66239472b5bed11fbe2cd30b6d10e651bb3a6310c889cef10c","schema_version":"1.0","event_id":"sha256:05d20aef24216c66239472b5bed11fbe2cd30b6d10e651bb3a6310c889cef10c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:72JWBN34NGDST6NS4X4YRLCVZH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dong Zhang, Ge Zhang, Hang Yan, Jiasheng Ye, Jie Fu, Junqi Dai, Jun Zhan, Linyang Li, Ruibin Yuan, Tao Gui, Tianxiang Sun, Xin Zhang, Xipeng Qiu, Yu-Gang Jiang, Yunhua Zhou, Zhigeng Liu","submitted_at":"2024-02-19T15:33:10Z","abstract_excerpt":"We introduce AnyGPT, an any-to-any multimodal language model that utilizes discrete representations for the unified processing of various modalities, including speech, text, images, and music. AnyGPT can be trained stably without any alterations to the current large language model (LLM) architecture or training paradigms. Instead, it relies exclusively on data-level preprocessing, facilitating the seamless integration of new modalities into LLMs, akin to the incorporation of new languages. We build a multimodal text-centric dataset for multimodal alignment pre-training. Utilizing generative mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12226","kind":"arxiv","version":5},"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/2402.12226/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":"2026-07-05T12:05:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6YMUbKBWeDXjiy622m5MEqu6alZLoLthWEELCxXH1zWmzruSXjcweD4QVHtvD52jPt600st8s2gV6Q/kNI0mCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T23:46:49.772477Z"},"content_sha256":"1db3fd7cb8edf5a27bcd89034bb74c915ae191228486290eb2806f8b00b4c900","schema_version":"1.0","event_id":"sha256:1db3fd7cb8edf5a27bcd89034bb74c915ae191228486290eb2806f8b00b4c900"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/72JWBN34NGDST6NS4X4YRLCVZH/bundle.json","state_url":"https://pith.science/pith/72JWBN34NGDST6NS4X4YRLCVZH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/72JWBN34NGDST6NS4X4YRLCVZH/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":"2026-07-31T23:46:49Z","links":{"resolver":"https://pith.science/pith/72JWBN34NGDST6NS4X4YRLCVZH","bundle":"https://pith.science/pith/72JWBN34NGDST6NS4X4YRLCVZH/bundle.json","state":"https://pith.science/pith/72JWBN34NGDST6NS4X4YRLCVZH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/72JWBN34NGDST6NS4X4YRLCVZH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:72JWBN34NGDST6NS4X4YRLCVZH","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":"1c41e3946a7dbcc5034d9d947b54a6a92a3c4c375cee096ed7770def7ba71de1","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T15:33:10Z","title_canon_sha256":"1feb306d48308873e1370d24b96d409d83cb81c65c3d221c491b2d371e43891c"},"schema_version":"1.0","source":{"id":"2402.12226","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12226","created_at":"2026-07-05T12:05:59Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12226v5","created_at":"2026-07-05T12:05:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12226","created_at":"2026-07-05T12:05:59Z"},{"alias_kind":"pith_short_12","alias_value":"72JWBN34NGDS","created_at":"2026-07-05T12:05:59Z"},{"alias_kind":"pith_short_16","alias_value":"72JWBN34NGDST6NS","created_at":"2026-07-05T12:05:59Z"},{"alias_kind":"pith_short_8","alias_value":"72JWBN34","created_at":"2026-07-05T12:05:59Z"}],"graph_snapshots":[{"event_id":"sha256:1db3fd7cb8edf5a27bcd89034bb74c915ae191228486290eb2806f8b00b4c900","target":"graph","created_at":"2026-07-05T12:05:59Z","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/2402.12226/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce AnyGPT, an any-to-any multimodal language model that utilizes discrete representations for the unified processing of various modalities, including speech, text, images, and music. AnyGPT can be trained stably without any alterations to the current large language model (LLM) architecture or training paradigms. Instead, it relies exclusively on data-level preprocessing, facilitating the seamless integration of new modalities into LLMs, akin to the incorporation of new languages. We build a multimodal text-centric dataset for multimodal alignment pre-training. Utilizing generative mo","authors_text":"Dong Zhang, Ge Zhang, Hang Yan, Jiasheng Ye, Jie Fu, Junqi Dai, Jun Zhan, Linyang Li, Ruibin Yuan, Tao Gui, Tianxiang Sun, Xin Zhang, Xipeng Qiu, Yu-Gang Jiang, Yunhua Zhou, Zhigeng Liu","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T15:33:10Z","title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12226","kind":"arxiv","version":5},"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":"sha256:05d20aef24216c66239472b5bed11fbe2cd30b6d10e651bb3a6310c889cef10c","target":"record","created_at":"2026-07-05T12:05:59Z","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":"1c41e3946a7dbcc5034d9d947b54a6a92a3c4c375cee096ed7770def7ba71de1","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T15:33:10Z","title_canon_sha256":"1feb306d48308873e1370d24b96d409d83cb81c65c3d221c491b2d371e43891c"},"schema_version":"1.0","source":{"id":"2402.12226","kind":"arxiv","version":5}},"canonical_sha256":"fe9360b77c698729f9b2e5f988ac55c9f827ff855e673c7cbf36869a85b87146","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe9360b77c698729f9b2e5f988ac55c9f827ff855e673c7cbf36869a85b87146","first_computed_at":"2026-07-05T12:05:59.168877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:59.168877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0LkSrXvoWGx7r/qIWCpJN6EOOrjnKgqX4rCDtmI1aM+lE1GX1DqwuMGQowUHboAZgnR3Q9ok1f7hIw0RDrhBAw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:59.169470Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12226","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05d20aef24216c66239472b5bed11fbe2cd30b6d10e651bb3a6310c889cef10c","sha256:1db3fd7cb8edf5a27bcd89034bb74c915ae191228486290eb2806f8b00b4c900"],"state_sha256":"4ed0306e48c6bf59ef1b393df280655e7e3be2fafbdc8b5705b7f12c2a147cb3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ITw5suo5ZOmHFJxgZZ0aClnHLdTsfRCSMniwI+BXKqEtimNw5BfXaPOHt2ed59D4D0wEvIryZcmmuVEoOFBCDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T23:46:49.776606Z","bundle_sha256":"4531c20dce8720d6d5db76b07638fb0966204961f5a69e9d73eaa0e324f6b4b0"}}