{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EUPBRWCQBFBM7KVA6EZF7663DN","short_pith_number":"pith:EUPBRWCQ","canonical_record":{"source":{"id":"2305.04160","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-07T02:25:42Z","cross_cats_sorted":["cs.AI","cs.CV","eess.AS"],"title_canon_sha256":"e587d00dbe443d84c80acc02be3cacd64773008540c7a9c325d74595214d4336","abstract_canon_sha256":"6e9e413e7ff8a04d29714d2fb11485fa9e151ec57c6b3b991cc62ad20a2f49e3"},"schema_version":"1.0"},"canonical_sha256":"251e18d8500942cfaaa0f1325ffbdb1b5e19b6846f5d1ab249036b4404503bb9","source":{"kind":"arxiv","id":"2305.04160","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.04160","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"arxiv_version","alias_value":"2305.04160v3","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.04160","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"pith_short_12","alias_value":"EUPBRWCQBFBM","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"pith_short_16","alias_value":"EUPBRWCQBFBM7KVA","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"pith_short_8","alias_value":"EUPBRWCQ","created_at":"2026-07-05T06:12:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EUPBRWCQBFBM7KVA6EZF7663DN","target":"record","payload":{"canonical_record":{"source":{"id":"2305.04160","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-07T02:25:42Z","cross_cats_sorted":["cs.AI","cs.CV","eess.AS"],"title_canon_sha256":"e587d00dbe443d84c80acc02be3cacd64773008540c7a9c325d74595214d4336","abstract_canon_sha256":"6e9e413e7ff8a04d29714d2fb11485fa9e151ec57c6b3b991cc62ad20a2f49e3"},"schema_version":"1.0"},"canonical_sha256":"251e18d8500942cfaaa0f1325ffbdb1b5e19b6846f5d1ab249036b4404503bb9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:02.501037Z","signature_b64":"vHj+qgjLD7iZ1bq0W5SJ8utiV/jCJi2IQs5hzQC+6JfVvQEK/iYyZunj1pQcQVNhcXLR7PdnxJ0KhhdapLTgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"251e18d8500942cfaaa0f1325ffbdb1b5e19b6846f5d1ab249036b4404503bb9","last_reissued_at":"2026-07-05T06:12:02.500696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:02.500696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.04160","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:12:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AkpdyHSESf8ddWjOowmkCxePOuISxtz22kzr/0FUvYFa0GiAOq1fnN0S4J5AEbG7ioVI1jwXImtsjGJy9PVgBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:49:48.308970Z"},"content_sha256":"d2074434e26cf11e7545a0487ba58eda1764d5a54f11979d4319f106acfa4302","schema_version":"1.0","event_id":"sha256:d2074434e26cf11e7545a0487ba58eda1764d5a54f11979d4319f106acfa4302"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EUPBRWCQBFBM7KVA6EZF7663DN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bo Xu, Feilong Chen, Haozhi Zhao, Jing Shi, Minglun Han, Qingyang Zhang, Shuang Xu","submitted_at":"2023-05-07T02:25:42Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable language abilities. GPT-4, based on advanced LLMs, exhibits extraordinary multimodal capabilities beyond previous visual language models. We attribute this to the use of more advanced LLMs compared with previous multimodal models. Unfortunately, the model architecture and training strategies of GPT-4 are unknown. To endow LLMs with multimodal capabilities, we propose X-LLM, which converts Multi-modalities (images, speech, videos) into foreign languages using X2L interfaces and inputs them into a large Language model (ChatGLM). Specifica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.04160","kind":"arxiv","version":3},"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/2305.04160/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":"2026-07-05T06:12:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sml60wslMNJ0rR+XPF7jHf45PzneJ9XvbQIAOh7FrdMOjmb4zcto4F+0CXMvuQYsLbRusFaR2NNlO5lJ2u48DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:49:48.309500Z"},"content_sha256":"5a592e1e9e91828af773d42c99a31b481d6e15379f42c75e8d102854ac06a97e","schema_version":"1.0","event_id":"sha256:5a592e1e9e91828af773d42c99a31b481d6e15379f42c75e8d102854ac06a97e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EUPBRWCQBFBM7KVA6EZF7663DN/bundle.json","state_url":"https://pith.science/pith/EUPBRWCQBFBM7KVA6EZF7663DN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EUPBRWCQBFBM7KVA6EZF7663DN/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":"2026-08-10T12:49:48Z","links":{"resolver":"https://pith.science/pith/EUPBRWCQBFBM7KVA6EZF7663DN","bundle":"https://pith.science/pith/EUPBRWCQBFBM7KVA6EZF7663DN/bundle.json","state":"https://pith.science/pith/EUPBRWCQBFBM7KVA6EZF7663DN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EUPBRWCQBFBM7KVA6EZF7663DN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EUPBRWCQBFBM7KVA6EZF7663DN","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":"6e9e413e7ff8a04d29714d2fb11485fa9e151ec57c6b3b991cc62ad20a2f49e3","cross_cats_sorted":["cs.AI","cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-07T02:25:42Z","title_canon_sha256":"e587d00dbe443d84c80acc02be3cacd64773008540c7a9c325d74595214d4336"},"schema_version":"1.0","source":{"id":"2305.04160","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.04160","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"arxiv_version","alias_value":"2305.04160v3","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.04160","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"pith_short_12","alias_value":"EUPBRWCQBFBM","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"pith_short_16","alias_value":"EUPBRWCQBFBM7KVA","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"pith_short_8","alias_value":"EUPBRWCQ","created_at":"2026-07-05T06:12:02Z"}],"graph_snapshots":[{"event_id":"sha256:5a592e1e9e91828af773d42c99a31b481d6e15379f42c75e8d102854ac06a97e","target":"graph","created_at":"2026-07-05T06:12:02Z","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/2305.04160/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable language abilities. GPT-4, based on advanced LLMs, exhibits extraordinary multimodal capabilities beyond previous visual language models. We attribute this to the use of more advanced LLMs compared with previous multimodal models. Unfortunately, the model architecture and training strategies of GPT-4 are unknown. To endow LLMs with multimodal capabilities, we propose X-LLM, which converts Multi-modalities (images, speech, videos) into foreign languages using X2L interfaces and inputs them into a large Language model (ChatGLM). Specifica","authors_text":"Bo Xu, Feilong Chen, Haozhi Zhao, Jing Shi, Minglun Han, Qingyang Zhang, Shuang Xu","cross_cats":["cs.AI","cs.CV","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-07T02:25:42Z","title":"X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.04160","kind":"arxiv","version":3},"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:d2074434e26cf11e7545a0487ba58eda1764d5a54f11979d4319f106acfa4302","target":"record","created_at":"2026-07-05T06:12:02Z","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":"6e9e413e7ff8a04d29714d2fb11485fa9e151ec57c6b3b991cc62ad20a2f49e3","cross_cats_sorted":["cs.AI","cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-07T02:25:42Z","title_canon_sha256":"e587d00dbe443d84c80acc02be3cacd64773008540c7a9c325d74595214d4336"},"schema_version":"1.0","source":{"id":"2305.04160","kind":"arxiv","version":3}},"canonical_sha256":"251e18d8500942cfaaa0f1325ffbdb1b5e19b6846f5d1ab249036b4404503bb9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"251e18d8500942cfaaa0f1325ffbdb1b5e19b6846f5d1ab249036b4404503bb9","first_computed_at":"2026-07-05T06:12:02.500696Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:02.500696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vHj+qgjLD7iZ1bq0W5SJ8utiV/jCJi2IQs5hzQC+6JfVvQEK/iYyZunj1pQcQVNhcXLR7PdnxJ0KhhdapLTgCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:02.501037Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.04160","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2074434e26cf11e7545a0487ba58eda1764d5a54f11979d4319f106acfa4302","sha256:5a592e1e9e91828af773d42c99a31b481d6e15379f42c75e8d102854ac06a97e"],"state_sha256":"54bea6d0e68bac5374d3d4f1820364e278e66053902260778aea240d908706d9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"earCBizcJLVKo7FCTySsmWx4JHK6ZI2Mo6aeIn0AsQMckZTngiq8zWXYFA+dmGM2sT3nrO4P/ZXFU6nyd+txCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:49:48.317574Z","bundle_sha256":"ac947961fd30a05b576f7f6a5c38e0cde49f0529373b6026a7608cfeff152b06"}}