{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DH3ATXRFVUIWYIXO4FOF4FG5DS","short_pith_number":"pith:DH3ATXRF","schema_version":"1.0","canonical_sha256":"19f609de25ad116c22eee15c5e14dd1c9e640b58a208339b3163d09a3dbd8bfb","source":{"kind":"arxiv","id":"2410.15316","version":3},"attestation_state":"computed","paper":{"title":"Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alan Dao (Gia Tuan Dao), Dinh Bach Vu, Huy Hoang Ha","submitted_at":"2024-10-20T07:03:49Z","abstract_excerpt":"Large Language Models (LLMs) have revolutionized natural language processing, but their application to speech-based tasks remains challenging due to the complexities of integrating audio and text modalities. This paper introduces Ichigo, a mixed-modal model that seamlessly processes interleaved sequences of speech and text. Utilizing a tokenized early-fusion approach, Ichigo quantizes speech into discrete tokens and employs a uniform transformer-based architecture for both speech and text modalities. This method enables joint reasoning and generation across modalities without the need for sepa"},"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":"2410.15316","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-20T07:03:49Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"ad4167d5f5f5b7054bd183be56815591be15cc558b26e8677792d9eb11dde24d","abstract_canon_sha256":"0453270c30d5cda02202d431dd06c0162d53922506f2d162a5426e1d0945de2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:18.619734Z","signature_b64":"0CF8lGMpj9/OYEAbNnTIWzAMktvIzpevzK1Aabp1BlX3F76qJDN8OfVBlcF4+rkBcLD/tyGDoce/TPoy8ek3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19f609de25ad116c22eee15c5e14dd1c9e640b58a208339b3163d09a3dbd8bfb","last_reissued_at":"2026-07-05T10:44:18.619108Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:18.619108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alan Dao (Gia Tuan Dao), Dinh Bach Vu, Huy Hoang Ha","submitted_at":"2024-10-20T07:03:49Z","abstract_excerpt":"Large Language Models (LLMs) have revolutionized natural language processing, but their application to speech-based tasks remains challenging due to the complexities of integrating audio and text modalities. This paper introduces Ichigo, a mixed-modal model that seamlessly processes interleaved sequences of speech and text. Utilizing a tokenized early-fusion approach, Ichigo quantizes speech into discrete tokens and employs a uniform transformer-based architecture for both speech and text modalities. This method enables joint reasoning and generation across modalities without the need for sepa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15316","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/2410.15316/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":"2410.15316","created_at":"2026-07-05T10:44:18.619227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.15316v3","created_at":"2026-07-05T10:44:18.619227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15316","created_at":"2026-07-05T10:44:18.619227+00:00"},{"alias_kind":"pith_short_12","alias_value":"DH3ATXRFVUIW","created_at":"2026-07-05T10:44:18.619227+00:00"},{"alias_kind":"pith_short_16","alias_value":"DH3ATXRFVUIWYIXO","created_at":"2026-07-05T10:44:18.619227+00:00"},{"alias_kind":"pith_short_8","alias_value":"DH3ATXRF","created_at":"2026-07-05T10:44:18.619227+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DH3ATXRFVUIWYIXO4FOF4FG5DS","json":"https://pith.science/pith/DH3ATXRFVUIWYIXO4FOF4FG5DS.json","graph_json":"https://pith.science/api/pith-number/DH3ATXRFVUIWYIXO4FOF4FG5DS/graph.json","events_json":"https://pith.science/api/pith-number/DH3ATXRFVUIWYIXO4FOF4FG5DS/events.json","paper":"https://pith.science/paper/DH3ATXRF"},"agent_actions":{"view_html":"https://pith.science/pith/DH3ATXRFVUIWYIXO4FOF4FG5DS","download_json":"https://pith.science/pith/DH3ATXRFVUIWYIXO4FOF4FG5DS.json","view_paper":"https://pith.science/paper/DH3ATXRF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.15316&json=true","fetch_graph":"https://pith.science/api/pith-number/DH3ATXRFVUIWYIXO4FOF4FG5DS/graph.json","fetch_events":"https://pith.science/api/pith-number/DH3ATXRFVUIWYIXO4FOF4FG5DS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DH3ATXRFVUIWYIXO4FOF4FG5DS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DH3ATXRFVUIWYIXO4FOF4FG5DS/action/storage_attestation","attest_author":"https://pith.science/pith/DH3ATXRFVUIWYIXO4FOF4FG5DS/action/author_attestation","sign_citation":"https://pith.science/pith/DH3ATXRFVUIWYIXO4FOF4FG5DS/action/citation_signature","submit_replication":"https://pith.science/pith/DH3ATXRFVUIWYIXO4FOF4FG5DS/action/replication_record"}},"created_at":"2026-07-05T10:44:18.619227+00:00","updated_at":"2026-07-05T10:44:18.619227+00:00"}