{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TDAC27ZWIXRJSDTWYMEGSGR7CV","short_pith_number":"pith:TDAC27ZW","canonical_record":{"source":{"id":"2605.29859","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-28T12:39:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fefae194e8d2b3b1506475722c4ef796cc0d0579857c4fa5782a789c273b3fb7","abstract_canon_sha256":"a2e3b0934a54bb24d614441d6f27f089a9909209a034a429d1a3a3f56dc1a611"},"schema_version":"1.0"},"canonical_sha256":"98c02d7f3645e2990e76c308691a3f156a68ab97c8a99083e7e27f7e55daa01a","source":{"kind":"arxiv","id":"2605.29859","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29859","created_at":"2026-05-29T02:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29859v1","created_at":"2026-05-29T02:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29859","created_at":"2026-05-29T02:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"TDAC27ZWIXRJ","created_at":"2026-05-29T02:05:56Z"},{"alias_kind":"pith_short_16","alias_value":"TDAC27ZWIXRJSDTW","created_at":"2026-05-29T02:05:56Z"},{"alias_kind":"pith_short_8","alias_value":"TDAC27ZW","created_at":"2026-05-29T02:05:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TDAC27ZWIXRJSDTWYMEGSGR7CV","target":"record","payload":{"canonical_record":{"source":{"id":"2605.29859","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-28T12:39:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fefae194e8d2b3b1506475722c4ef796cc0d0579857c4fa5782a789c273b3fb7","abstract_canon_sha256":"a2e3b0934a54bb24d614441d6f27f089a9909209a034a429d1a3a3f56dc1a611"},"schema_version":"1.0"},"canonical_sha256":"98c02d7f3645e2990e76c308691a3f156a68ab97c8a99083e7e27f7e55daa01a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:56.457518Z","signature_b64":"JzUUys4pInJ/HDIMCuG/itKir9TcIMW2yrCw/2rqkmpoBCnrwJN3/bJcREljjvP4/EM2Ihdg/QaM3DHk9D0RCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98c02d7f3645e2990e76c308691a3f156a68ab97c8a99083e7e27f7e55daa01a","last_reissued_at":"2026-05-29T02:05:56.456604Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:56.456604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.29859","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":"2026-05-29T02:05:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yYsyH1awV0p5iih/Ou6Ceei8wKu4GJ7oNdJ6fUP060dFsWM1uWyOaNav3aWx8qTFZhh13H1DxA7iPICN6hOvDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T22:57:50.410290Z"},"content_sha256":"9a577e83df1ac1a9098977fbf3c577323baa0160217ae5b947b475a817cddb35","schema_version":"1.0","event_id":"sha256:9a577e83df1ac1a9098977fbf3c577323baa0160217ae5b947b475a817cddb35"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TDAC27ZWIXRJSDTWYMEGSGR7CV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MELD: Mel-Spectrogram-Based Speech Language Modeling with Discrete Latent Variables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Alexandre Mourachko, Duc Le, Gil Keren, Hao Tang, Jay Mahadeokar, Ozlem Kalinli, Sung-Lin Yeh, Wei Zhou, Zhong Meng","submitted_at":"2026-05-28T12:39:36Z","abstract_excerpt":"Recent speech language models rely on encoders that are optimized separately from autoregressive models. Since these encoders are unaware of the downstream objectives, the extracted representations may not be optimal for downstream tasks. To address this limitation, we introduce a discrete latent variable model on mel spectrograms that jointly optimizes the encoder and the speech language model. Joint optimization not only brings improvements over codec-based and other mel-spectrogram-based baselines on zero-shot Text-to-Speech (TTS) and Speech-to-Text (STT) tasks, but also effectively allevia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29859","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/2605.29859/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":"2026-05-29T02:05:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"By4EG/nWQM4zzQS8/RbZVwrhmTAj6Hx8Lw9Ctbl5zQy7AVAk74WP5tAYqNFUaMaYtfBJUk1GOd3ep3EmCyIrCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T22:57:50.410684Z"},"content_sha256":"0eba9658407ee3f4c850622eec22f84f09a151d07b589b9f65e723794945305d","schema_version":"1.0","event_id":"sha256:0eba9658407ee3f4c850622eec22f84f09a151d07b589b9f65e723794945305d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TDAC27ZWIXRJSDTWYMEGSGR7CV/bundle.json","state_url":"https://pith.science/pith/TDAC27ZWIXRJSDTWYMEGSGR7CV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TDAC27ZWIXRJSDTWYMEGSGR7CV/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":"2026-06-02T22:57:50Z","links":{"resolver":"https://pith.science/pith/TDAC27ZWIXRJSDTWYMEGSGR7CV","bundle":"https://pith.science/pith/TDAC27ZWIXRJSDTWYMEGSGR7CV/bundle.json","state":"https://pith.science/pith/TDAC27ZWIXRJSDTWYMEGSGR7CV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TDAC27ZWIXRJSDTWYMEGSGR7CV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TDAC27ZWIXRJSDTWYMEGSGR7CV","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":"a2e3b0934a54bb24d614441d6f27f089a9909209a034a429d1a3a3f56dc1a611","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-28T12:39:36Z","title_canon_sha256":"fefae194e8d2b3b1506475722c4ef796cc0d0579857c4fa5782a789c273b3fb7"},"schema_version":"1.0","source":{"id":"2605.29859","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29859","created_at":"2026-05-29T02:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29859v1","created_at":"2026-05-29T02:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29859","created_at":"2026-05-29T02:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"TDAC27ZWIXRJ","created_at":"2026-05-29T02:05:56Z"},{"alias_kind":"pith_short_16","alias_value":"TDAC27ZWIXRJSDTW","created_at":"2026-05-29T02:05:56Z"},{"alias_kind":"pith_short_8","alias_value":"TDAC27ZW","created_at":"2026-05-29T02:05:56Z"}],"graph_snapshots":[{"event_id":"sha256:0eba9658407ee3f4c850622eec22f84f09a151d07b589b9f65e723794945305d","target":"graph","created_at":"2026-05-29T02:05:56Z","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/2605.29859/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent speech language models rely on encoders that are optimized separately from autoregressive models. Since these encoders are unaware of the downstream objectives, the extracted representations may not be optimal for downstream tasks. To address this limitation, we introduce a discrete latent variable model on mel spectrograms that jointly optimizes the encoder and the speech language model. Joint optimization not only brings improvements over codec-based and other mel-spectrogram-based baselines on zero-shot Text-to-Speech (TTS) and Speech-to-Text (STT) tasks, but also effectively allevia","authors_text":"Alexandre Mourachko, Duc Le, Gil Keren, Hao Tang, Jay Mahadeokar, Ozlem Kalinli, Sung-Lin Yeh, Wei Zhou, Zhong Meng","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-28T12:39:36Z","title":"MELD: Mel-Spectrogram-Based Speech Language Modeling with Discrete Latent Variables"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29859","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":"sha256:9a577e83df1ac1a9098977fbf3c577323baa0160217ae5b947b475a817cddb35","target":"record","created_at":"2026-05-29T02:05:56Z","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":"a2e3b0934a54bb24d614441d6f27f089a9909209a034a429d1a3a3f56dc1a611","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-28T12:39:36Z","title_canon_sha256":"fefae194e8d2b3b1506475722c4ef796cc0d0579857c4fa5782a789c273b3fb7"},"schema_version":"1.0","source":{"id":"2605.29859","kind":"arxiv","version":1}},"canonical_sha256":"98c02d7f3645e2990e76c308691a3f156a68ab97c8a99083e7e27f7e55daa01a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98c02d7f3645e2990e76c308691a3f156a68ab97c8a99083e7e27f7e55daa01a","first_computed_at":"2026-05-29T02:05:56.456604Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:05:56.456604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JzUUys4pInJ/HDIMCuG/itKir9TcIMW2yrCw/2rqkmpoBCnrwJN3/bJcREljjvP4/EM2Ihdg/QaM3DHk9D0RCA==","signature_status":"signed_v1","signed_at":"2026-05-29T02:05:56.457518Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29859","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a577e83df1ac1a9098977fbf3c577323baa0160217ae5b947b475a817cddb35","sha256:0eba9658407ee3f4c850622eec22f84f09a151d07b589b9f65e723794945305d"],"state_sha256":"fc01505562359ae0a880d0febc65e51cb45b46c682bc7b4b2cef818398104706"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6L+k01Ni42s8Ycrk+TsUnFR7NNUiRHGqDZ6UJUjbJE6pOmcAcfC4cCazxSvzl8vz1yCx2Z5aMsVdzu6eo5AYCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T22:57:50.412990Z","bundle_sha256":"ccfa7b86de4cff723cf551a5670f370c34a7946018547b8b38dcfb9950e0ed52"}}