{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MRB2LFELIYG3VJTTYE7SMPKT3K","short_pith_number":"pith:MRB2LFEL","schema_version":"1.0","canonical_sha256":"6443a5948b460dbaa673c13f263d53dabbed98b4a236bf236dda6e5de27dd4e4","source":{"kind":"arxiv","id":"2311.06772","version":1},"attestation_state":"computed","paper":{"title":"ChatAnything: Facetime Chat with LLM-Enhanced Personas","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Daquan Zhou, Jiashi Feng, Qibin Hou, Shanghua Gao, Xinbin Yuan, Yilin Zhao, Zhijie Lin","submitted_at":"2023-11-12T08:29:41Z","abstract_excerpt":"In this technical report, we target generating anthropomorphized personas for LLM-based characters in an online manner, including visual appearance, personality and tones, with only text descriptions. To achieve this, we first leverage the in-context learning capability of LLMs for personality generation by carefully designing a set of system prompts. We then propose two novel concepts: the mixture of voices (MoV) and the mixture of diffusers (MoD) for diverse voice and appearance generation. For MoV, we utilize the text-to-speech (TTS) algorithms with a variety of pre-defined tones and select"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2311.06772","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-12T08:29:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6c9bdbe0e96f9e5e4e27ddf8206602dcef866af79e513011dd94260abb51f92f","abstract_canon_sha256":"d79d3b0e6405bc0c76e5cfe99fd350cd9c44a57526dac77b905439d0051c66b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:03.343540Z","signature_b64":"OWKGM716mjSNQ9IHkhAxtI3amJMw+EqX+jrKoyJcPYD/GtCmZNnyLE77/3R+G6ObhAyf8BHCfcdcp6y36CdYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6443a5948b460dbaa673c13f263d53dabbed98b4a236bf236dda6e5de27dd4e4","last_reissued_at":"2026-07-05T07:12:03.343084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:03.343084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChatAnything: Facetime Chat with LLM-Enhanced Personas","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Daquan Zhou, Jiashi Feng, Qibin Hou, Shanghua Gao, Xinbin Yuan, Yilin Zhao, Zhijie Lin","submitted_at":"2023-11-12T08:29:41Z","abstract_excerpt":"In this technical report, we target generating anthropomorphized personas for LLM-based characters in an online manner, including visual appearance, personality and tones, with only text descriptions. To achieve this, we first leverage the in-context learning capability of LLMs for personality generation by carefully designing a set of system prompts. We then propose two novel concepts: the mixture of voices (MoV) and the mixture of diffusers (MoD) for diverse voice and appearance generation. For MoV, we utilize the text-to-speech (TTS) algorithms with a variety of pre-defined tones and select"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06772","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/2311.06772/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.06772","created_at":"2026-07-05T07:12:03.343140+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.06772v1","created_at":"2026-07-05T07:12:03.343140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06772","created_at":"2026-07-05T07:12:03.343140+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRB2LFELIYG3","created_at":"2026-07-05T07:12:03.343140+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRB2LFELIYG3VJTT","created_at":"2026-07-05T07:12:03.343140+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRB2LFEL","created_at":"2026-07-05T07:12:03.343140+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.09209","citing_title":"JoyVASA: Portrait and Animal Image Animation with Diffusion-Based Audio-Driven Facial Dynamics and Head Motion Generation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MRB2LFELIYG3VJTTYE7SMPKT3K","json":"https://pith.science/pith/MRB2LFELIYG3VJTTYE7SMPKT3K.json","graph_json":"https://pith.science/api/pith-number/MRB2LFELIYG3VJTTYE7SMPKT3K/graph.json","events_json":"https://pith.science/api/pith-number/MRB2LFELIYG3VJTTYE7SMPKT3K/events.json","paper":"https://pith.science/paper/MRB2LFEL"},"agent_actions":{"view_html":"https://pith.science/pith/MRB2LFELIYG3VJTTYE7SMPKT3K","download_json":"https://pith.science/pith/MRB2LFELIYG3VJTTYE7SMPKT3K.json","view_paper":"https://pith.science/paper/MRB2LFEL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.06772&json=true","fetch_graph":"https://pith.science/api/pith-number/MRB2LFELIYG3VJTTYE7SMPKT3K/graph.json","fetch_events":"https://pith.science/api/pith-number/MRB2LFELIYG3VJTTYE7SMPKT3K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRB2LFELIYG3VJTTYE7SMPKT3K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRB2LFELIYG3VJTTYE7SMPKT3K/action/storage_attestation","attest_author":"https://pith.science/pith/MRB2LFELIYG3VJTTYE7SMPKT3K/action/author_attestation","sign_citation":"https://pith.science/pith/MRB2LFELIYG3VJTTYE7SMPKT3K/action/citation_signature","submit_replication":"https://pith.science/pith/MRB2LFELIYG3VJTTYE7SMPKT3K/action/replication_record"}},"created_at":"2026-07-05T07:12:03.343140+00:00","updated_at":"2026-07-05T07:12:03.343140+00:00"}