{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DIO3CPKCUFIDBDUQCSHVQVQDVH","short_pith_number":"pith:DIO3CPKC","canonical_record":{"source":{"id":"2506.06343","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T09:27:55Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"8dedff2d0cea4b435a9d5e3646f51f6711b2317172cb48a773cc19c8c584e01e","abstract_canon_sha256":"5b5459d2fad10ff02041c0b5faafc2f2355d282beab3c8fbe465cbda9e59eb43"},"schema_version":"1.0"},"canonical_sha256":"1a1db13d42a150308e90148f585603a9e1b084b8be4fb3145e52d771f10f5a05","source":{"kind":"arxiv","id":"2506.06343","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06343","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06343v1","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06343","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"pith_short_12","alias_value":"DIO3CPKCUFID","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"pith_short_16","alias_value":"DIO3CPKCUFIDBDUQ","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"pith_short_8","alias_value":"DIO3CPKC","created_at":"2026-07-05T11:17:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DIO3CPKCUFIDBDUQCSHVQVQDVH","target":"record","payload":{"canonical_record":{"source":{"id":"2506.06343","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T09:27:55Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"8dedff2d0cea4b435a9d5e3646f51f6711b2317172cb48a773cc19c8c584e01e","abstract_canon_sha256":"5b5459d2fad10ff02041c0b5faafc2f2355d282beab3c8fbe465cbda9e59eb43"},"schema_version":"1.0"},"canonical_sha256":"1a1db13d42a150308e90148f585603a9e1b084b8be4fb3145e52d771f10f5a05","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:48.489940Z","signature_b64":"cMM4LIE37p2D07nufZ++lT7ZcKn51Mz1HPtNOnioWO2aQSAzNvueJoWvSs7R6qO05MmVla77Tpx9BbMSw1w2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a1db13d42a150308e90148f585603a9e1b084b8be4fb3145e52d771f10f5a05","last_reissued_at":"2026-07-05T11:17:48.489495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:48.489495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.06343","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:17:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Frlp0WbVISU33GvKGbCuKWaR0y0j+InU2nbT5SDTnLhqm9xczzcD4LRd3NmSxrdlVINm3XBbP3T9UjaOGK0nDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:18:59.173652Z"},"content_sha256":"ff3a88e2a5021e75efc2a2a121bedf18fd4dec4163c6726b3ae6aca0aeb93d9b","schema_version":"1.0","event_id":"sha256:ff3a88e2a5021e75efc2a2a121bedf18fd4dec4163c6726b3ae6aca0aeb93d9b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DIO3CPKCUFIDBDUQCSHVQVQDVH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TESU-LLM: Training Speech-LLMs Without Speech via Unified Encoder Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jong Hwan Ko, Taesoo Kim","submitted_at":"2025-06-01T09:27:55Z","abstract_excerpt":"Recent advances in speech-enabled language models have shown promising results in building intelligent voice assistants. However, most existing approaches rely on large-scale paired speech-text data and extensive computational resources, which pose challenges in terms of scalability and accessibility. In this paper, we present \\textbf{TESU-LLM}, a novel framework that enables training speech-capable language models using only text data. Our key insight is to leverage a unified encoder that maps semantically equivalent text and speech inputs to a shared latent space. By aligning the encoder out"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06343","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/2506.06343/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":"2026-07-05T11:17:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BxJbsTOhXymk6FguF3m6iSyv9P0qC97OZM1A9oNm9kEhsj6hiMCItUNeD1Q7gngV0sc4dqy5DrAgHD8f+UqbDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:18:59.174168Z"},"content_sha256":"96f49029440e899b27d4f08d57ae90cd71ecb64de00032b82305ccb2519645ee","schema_version":"1.0","event_id":"sha256:96f49029440e899b27d4f08d57ae90cd71ecb64de00032b82305ccb2519645ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DIO3CPKCUFIDBDUQCSHVQVQDVH/bundle.json","state_url":"https://pith.science/pith/DIO3CPKCUFIDBDUQCSHVQVQDVH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DIO3CPKCUFIDBDUQCSHVQVQDVH/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":"2026-08-04T10:18:59Z","links":{"resolver":"https://pith.science/pith/DIO3CPKCUFIDBDUQCSHVQVQDVH","bundle":"https://pith.science/pith/DIO3CPKCUFIDBDUQCSHVQVQDVH/bundle.json","state":"https://pith.science/pith/DIO3CPKCUFIDBDUQCSHVQVQDVH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DIO3CPKCUFIDBDUQCSHVQVQDVH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DIO3CPKCUFIDBDUQCSHVQVQDVH","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":"5b5459d2fad10ff02041c0b5faafc2f2355d282beab3c8fbe465cbda9e59eb43","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T09:27:55Z","title_canon_sha256":"8dedff2d0cea4b435a9d5e3646f51f6711b2317172cb48a773cc19c8c584e01e"},"schema_version":"1.0","source":{"id":"2506.06343","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06343","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06343v1","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06343","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"pith_short_12","alias_value":"DIO3CPKCUFID","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"pith_short_16","alias_value":"DIO3CPKCUFIDBDUQ","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"pith_short_8","alias_value":"DIO3CPKC","created_at":"2026-07-05T11:17:48Z"}],"graph_snapshots":[{"event_id":"sha256:96f49029440e899b27d4f08d57ae90cd71ecb64de00032b82305ccb2519645ee","target":"graph","created_at":"2026-07-05T11:17:48Z","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/2506.06343/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in speech-enabled language models have shown promising results in building intelligent voice assistants. However, most existing approaches rely on large-scale paired speech-text data and extensive computational resources, which pose challenges in terms of scalability and accessibility. In this paper, we present \\textbf{TESU-LLM}, a novel framework that enables training speech-capable language models using only text data. Our key insight is to leverage a unified encoder that maps semantically equivalent text and speech inputs to a shared latent space. By aligning the encoder out","authors_text":"Jong Hwan Ko, Taesoo Kim","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T09:27:55Z","title":"TESU-LLM: Training Speech-LLMs Without Speech via Unified Encoder Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06343","kind":"arxiv","version":1},"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:ff3a88e2a5021e75efc2a2a121bedf18fd4dec4163c6726b3ae6aca0aeb93d9b","target":"record","created_at":"2026-07-05T11:17:48Z","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":"5b5459d2fad10ff02041c0b5faafc2f2355d282beab3c8fbe465cbda9e59eb43","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T09:27:55Z","title_canon_sha256":"8dedff2d0cea4b435a9d5e3646f51f6711b2317172cb48a773cc19c8c584e01e"},"schema_version":"1.0","source":{"id":"2506.06343","kind":"arxiv","version":1}},"canonical_sha256":"1a1db13d42a150308e90148f585603a9e1b084b8be4fb3145e52d771f10f5a05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a1db13d42a150308e90148f585603a9e1b084b8be4fb3145e52d771f10f5a05","first_computed_at":"2026-07-05T11:17:48.489495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:48.489495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cMM4LIE37p2D07nufZ++lT7ZcKn51Mz1HPtNOnioWO2aQSAzNvueJoWvSs7R6qO05MmVla77Tpx9BbMSw1w2Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:48.489940Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06343","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff3a88e2a5021e75efc2a2a121bedf18fd4dec4163c6726b3ae6aca0aeb93d9b","sha256:96f49029440e899b27d4f08d57ae90cd71ecb64de00032b82305ccb2519645ee"],"state_sha256":"d94d85c5a8cff20a8ab5769646ee600fdbe1aea95a651adc1a0e891810385f9b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YVMjot0CrgGNFfK1I8ug8LlIkWogao639+fsosTOfRfMJbo46mXf7sps6Bc+irSn63phKZHSSQWVq4g7HwG0AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:18:59.177655Z","bundle_sha256":"48f39fdd20752dc07aeed98050f820f53188caea5021f2a922cb8eb63f915b55"}}