{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PN3FT5ZERLV2UJDMYAFJPI53AB","short_pith_number":"pith:PN3FT5ZE","canonical_record":{"source":{"id":"2505.15333","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T10:05:25Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"64fcb3b4d219e0827cfdda3fa689fd914d2bd6c0c88ad91b79f59f52dded60da","abstract_canon_sha256":"e3e4638c20aea34cafcb27ceda7b1665916f800dfc580a08a3bfe977b25d258f"},"schema_version":"1.0"},"canonical_sha256":"7b7659f7248aebaa246cc00a97a3bb0047dcbf4647a9fc5dde7ff74733a14610","source":{"kind":"arxiv","id":"2505.15333","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15333","created_at":"2026-07-05T11:06:43Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15333v1","created_at":"2026-07-05T11:06:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15333","created_at":"2026-07-05T11:06:43Z"},{"alias_kind":"pith_short_12","alias_value":"PN3FT5ZERLV2","created_at":"2026-07-05T11:06:43Z"},{"alias_kind":"pith_short_16","alias_value":"PN3FT5ZERLV2UJDM","created_at":"2026-07-05T11:06:43Z"},{"alias_kind":"pith_short_8","alias_value":"PN3FT5ZE","created_at":"2026-07-05T11:06:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PN3FT5ZERLV2UJDMYAFJPI53AB","target":"record","payload":{"canonical_record":{"source":{"id":"2505.15333","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T10:05:25Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"64fcb3b4d219e0827cfdda3fa689fd914d2bd6c0c88ad91b79f59f52dded60da","abstract_canon_sha256":"e3e4638c20aea34cafcb27ceda7b1665916f800dfc580a08a3bfe977b25d258f"},"schema_version":"1.0"},"canonical_sha256":"7b7659f7248aebaa246cc00a97a3bb0047dcbf4647a9fc5dde7ff74733a14610","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:43.939273Z","signature_b64":"0xzOsBh/Tauvz0U9+wShdJYoGhiLnCh2Sjh0hnADM26k+1BOoYXDQTJB1l1Ge4zcbTlWr11nx/iSpHcocnYwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b7659f7248aebaa246cc00a97a3bb0047dcbf4647a9fc5dde7ff74733a14610","last_reissued_at":"2026-07-05T11:06:43.938798Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:43.938798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.15333","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":"2026-07-05T11:06:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q1icvd9P+whQLAbDNjOOQwn/5CpCKd8iOPovIKPHJNiYcdjQXZFQ9IqTDHKDA0VDmUr7JMSt6G8oKLcwJAs2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:13:43.103934Z"},"content_sha256":"a436b14753bddb1a32d5ad1a6f5460f810556d8d2605d4aed8811a297b78c0e0","schema_version":"1.0","event_id":"sha256:a436b14753bddb1a32d5ad1a6f5460f810556d8d2605d4aed8811a297b78c0e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PN3FT5ZERLV2UJDMYAFJPI53AB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Benyou Wang, Jingbo Zhu, Kaiqi Kou, Peizhuo Liu, Tong Xiao, Weiqiao Shan, Xiangnan Ma, Yuhao Zhang, Yuxin Huang, Zhengtao Yu","submitted_at":"2025-05-21T10:05:25Z","abstract_excerpt":"The success of building textless speech-to-speech translation (S2ST) models has attracted much attention. However, S2ST still faces two main challenges: 1) extracting linguistic features for various speech signals, called cross-modal (CM), and 2) learning alignment of difference languages in long sequences, called cross-lingual (CL). We propose the unit language to overcome the two modeling challenges. The unit language can be considered a text-like representation format, constructed using $n$-gram language modeling. We implement multi-task learning to utilize the unit language in guiding the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15333","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/2505.15333/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":"2026-07-05T11:06:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t+f3LoR3qqAYphzkbeYV2IHPxR4jE5oTx9mBYYQ+9BCAfVcbXPTI5rOLfiqyFddgiURjNZzVeCL+l7ZKwNYCBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:13:43.104500Z"},"content_sha256":"0b56d40017a66b195281a163f2b1041d03cea2e808376fc4388574f86c70e487","schema_version":"1.0","event_id":"sha256:0b56d40017a66b195281a163f2b1041d03cea2e808376fc4388574f86c70e487"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PN3FT5ZERLV2UJDMYAFJPI53AB/bundle.json","state_url":"https://pith.science/pith/PN3FT5ZERLV2UJDMYAFJPI53AB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PN3FT5ZERLV2UJDMYAFJPI53AB/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":"2026-08-08T09:13:43Z","links":{"resolver":"https://pith.science/pith/PN3FT5ZERLV2UJDMYAFJPI53AB","bundle":"https://pith.science/pith/PN3FT5ZERLV2UJDMYAFJPI53AB/bundle.json","state":"https://pith.science/pith/PN3FT5ZERLV2UJDMYAFJPI53AB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PN3FT5ZERLV2UJDMYAFJPI53AB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PN3FT5ZERLV2UJDMYAFJPI53AB","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":"e3e4638c20aea34cafcb27ceda7b1665916f800dfc580a08a3bfe977b25d258f","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T10:05:25Z","title_canon_sha256":"64fcb3b4d219e0827cfdda3fa689fd914d2bd6c0c88ad91b79f59f52dded60da"},"schema_version":"1.0","source":{"id":"2505.15333","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15333","created_at":"2026-07-05T11:06:43Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15333v1","created_at":"2026-07-05T11:06:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15333","created_at":"2026-07-05T11:06:43Z"},{"alias_kind":"pith_short_12","alias_value":"PN3FT5ZERLV2","created_at":"2026-07-05T11:06:43Z"},{"alias_kind":"pith_short_16","alias_value":"PN3FT5ZERLV2UJDM","created_at":"2026-07-05T11:06:43Z"},{"alias_kind":"pith_short_8","alias_value":"PN3FT5ZE","created_at":"2026-07-05T11:06:43Z"}],"graph_snapshots":[{"event_id":"sha256:0b56d40017a66b195281a163f2b1041d03cea2e808376fc4388574f86c70e487","target":"graph","created_at":"2026-07-05T11:06:43Z","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/2505.15333/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of building textless speech-to-speech translation (S2ST) models has attracted much attention. However, S2ST still faces two main challenges: 1) extracting linguistic features for various speech signals, called cross-modal (CM), and 2) learning alignment of difference languages in long sequences, called cross-lingual (CL). We propose the unit language to overcome the two modeling challenges. The unit language can be considered a text-like representation format, constructed using $n$-gram language modeling. We implement multi-task learning to utilize the unit language in guiding the ","authors_text":"Benyou Wang, Jingbo Zhu, Kaiqi Kou, Peizhuo Liu, Tong Xiao, Weiqiao Shan, Xiangnan Ma, Yuhao Zhang, Yuxin Huang, Zhengtao Yu","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T10:05:25Z","title":"Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15333","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:a436b14753bddb1a32d5ad1a6f5460f810556d8d2605d4aed8811a297b78c0e0","target":"record","created_at":"2026-07-05T11:06:43Z","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":"e3e4638c20aea34cafcb27ceda7b1665916f800dfc580a08a3bfe977b25d258f","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T10:05:25Z","title_canon_sha256":"64fcb3b4d219e0827cfdda3fa689fd914d2bd6c0c88ad91b79f59f52dded60da"},"schema_version":"1.0","source":{"id":"2505.15333","kind":"arxiv","version":1}},"canonical_sha256":"7b7659f7248aebaa246cc00a97a3bb0047dcbf4647a9fc5dde7ff74733a14610","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b7659f7248aebaa246cc00a97a3bb0047dcbf4647a9fc5dde7ff74733a14610","first_computed_at":"2026-07-05T11:06:43.938798Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:43.938798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0xzOsBh/Tauvz0U9+wShdJYoGhiLnCh2Sjh0hnADM26k+1BOoYXDQTJB1l1Ge4zcbTlWr11nx/iSpHcocnYwBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:43.939273Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15333","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a436b14753bddb1a32d5ad1a6f5460f810556d8d2605d4aed8811a297b78c0e0","sha256:0b56d40017a66b195281a163f2b1041d03cea2e808376fc4388574f86c70e487"],"state_sha256":"13d5eacc5f1c2d6d44a1d2303812913dbe314e7a69b632e58c4b90a571c3c33e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AmZe1Ult0N5nU/2s3J5UvTgMG3ngrxiKwpGi9DALojtZRQKL/AcAtczP/pT6ptNXQEWBd2uZUU62qxXgezoLBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:13:43.108850Z","bundle_sha256":"75542dcb0b13c3d5067b6db834479ad900bb9b3b7873ccf50ce0072ec40942fb"}}