{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DH3ATXRFVUIWYIXO4FOF4FG5DS","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":"0453270c30d5cda02202d431dd06c0162d53922506f2d162a5426e1d0945de2c","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-20T07:03:49Z","title_canon_sha256":"ad4167d5f5f5b7054bd183be56815591be15cc558b26e8677792d9eb11dde24d"},"schema_version":"1.0","source":{"id":"2410.15316","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15316","created_at":"2026-07-05T10:44:18Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15316v3","created_at":"2026-07-05T10:44:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15316","created_at":"2026-07-05T10:44:18Z"},{"alias_kind":"pith_short_12","alias_value":"DH3ATXRFVUIW","created_at":"2026-07-05T10:44:18Z"},{"alias_kind":"pith_short_16","alias_value":"DH3ATXRFVUIWYIXO","created_at":"2026-07-05T10:44:18Z"},{"alias_kind":"pith_short_8","alias_value":"DH3ATXRF","created_at":"2026-07-05T10:44:18Z"}],"graph_snapshots":[{"event_id":"sha256:79125b3174f7454235d898950cb36453f303afdd0c246c0f90ab190936287e7e","target":"graph","created_at":"2026-07-05T10:44:18Z","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/2410.15316/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alan Dao (Gia Tuan Dao), Dinh Bach Vu, Huy Hoang Ha","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-20T07:03:49Z","title":"Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15316","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":"sha256:2b2b3680606273f934cb83478b556409ff64676906528782f0949e5d33f77185","target":"record","created_at":"2026-07-05T10:44:18Z","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":"0453270c30d5cda02202d431dd06c0162d53922506f2d162a5426e1d0945de2c","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-20T07:03:49Z","title_canon_sha256":"ad4167d5f5f5b7054bd183be56815591be15cc558b26e8677792d9eb11dde24d"},"schema_version":"1.0","source":{"id":"2410.15316","kind":"arxiv","version":3}},"canonical_sha256":"19f609de25ad116c22eee15c5e14dd1c9e640b58a208339b3163d09a3dbd8bfb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19f609de25ad116c22eee15c5e14dd1c9e640b58a208339b3163d09a3dbd8bfb","first_computed_at":"2026-07-05T10:44:18.619108Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:18.619108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0CF8lGMpj9/OYEAbNnTIWzAMktvIzpevzK1Aabp1BlX3F76qJDN8OfVBlcF4+rkBcLD/tyGDoce/TPoy8ek3DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:18.619734Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.15316","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b2b3680606273f934cb83478b556409ff64676906528782f0949e5d33f77185","sha256:79125b3174f7454235d898950cb36453f303afdd0c246c0f90ab190936287e7e"],"state_sha256":"69f512c78007c0da43efd062b17febe1131908d6a3b61252257353545252ff40"}