{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KOIBEEX3S34ZB5YVC5ZTMDIACX","short_pith_number":"pith:KOIBEEX3","canonical_record":{"source":{"id":"2607.26350","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-28T23:46:37Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"08e799553bb32e09c3e70ce02320b8f52b82d569e3491239500875e9c006ad59","abstract_canon_sha256":"107da409bf77d989d29acf4d301f098c5b62584936c943d72ae0e9fb47b9d9c1"},"schema_version":"1.0"},"canonical_sha256":"53901212fb96f990f7151773360d0015c31946e41d1a91ebe0e497fd3a52fea3","source":{"kind":"arxiv","id":"2607.26350","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26350","created_at":"2026-07-30T01:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26350v1","created_at":"2026-07-30T01:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26350","created_at":"2026-07-30T01:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"KOIBEEX3S34Z","created_at":"2026-07-30T01:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"KOIBEEX3S34ZB5YV","created_at":"2026-07-30T01:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"KOIBEEX3","created_at":"2026-07-30T01:18:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KOIBEEX3S34ZB5YVC5ZTMDIACX","target":"record","payload":{"canonical_record":{"source":{"id":"2607.26350","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-28T23:46:37Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"08e799553bb32e09c3e70ce02320b8f52b82d569e3491239500875e9c006ad59","abstract_canon_sha256":"107da409bf77d989d29acf4d301f098c5b62584936c943d72ae0e9fb47b9d9c1"},"schema_version":"1.0"},"canonical_sha256":"53901212fb96f990f7151773360d0015c31946e41d1a91ebe0e497fd3a52fea3","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53901212fb96f990f7151773360d0015c31946e41d1a91ebe0e497fd3a52fea3","last_reissued_at":"2026-07-30T01:18:08.718627Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:18:08.718627Z"},"source_kind":"arxiv","source_id":"2607.26350","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":"2026-07-30T01:18:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qQxoHN2GdcABbqdAVO9AHnh1BDab0962NrU2xjHBDao0m9O4EyA/xT/rjrOqCr5qGNrMDe4EhWVYG3Lx5D1RBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:08:43.955771Z"},"content_sha256":"68aed1d71271ff2c50de038812c8230f6c8dc1a810fefb3d813642dcb3a78c70","schema_version":"1.0","event_id":"sha256:68aed1d71271ff2c50de038812c8230f6c8dc1a810fefb3d813642dcb3a78c70"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KOIBEEX3S34ZB5YVC5ZTMDIACX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"Daigo Takizawa, Samuele Cornell, Satoru Fukayama, Shinji Watanabe, Tomohiko Nakamura, William Chen","submitted_at":"2026-07-28T23:46:37Z","abstract_excerpt":"Neural audio codecs (NACs) have become popular for obtaining speech representations as discrete tokens. Beyond compression, discrete tokens can be used to train self-supervised learning (SSL) models. Such models, referred to as codec-based SSL models, reduce data storage and computational cost, enabling scalable SSL pre-training. However, their language sensitivity remains unclear. When the language changes, codec-based SSL models may require retraining, which undermines their efficiency. In this paper, we present a systematic analysis of language sensitivity by varying either the NAC training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26350","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/2607.26350/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":"2026-07-30T01:18:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Psbcnt421ND58tNwB/uYuT4IkWDh2rU03dT/fS8DLa1Mly8XthBJSUbKNenFTUrV0F4y9juTnysUNMphRhtAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:08:43.956691Z"},"content_sha256":"e7a9d1a7ddf6f98de54a17acd28377e6144eb4f056c79ad27e119488bb738e8d","schema_version":"1.0","event_id":"sha256:e7a9d1a7ddf6f98de54a17acd28377e6144eb4f056c79ad27e119488bb738e8d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KOIBEEX3S34ZB5YVC5ZTMDIACX/bundle.json","state_url":"https://pith.science/pith/KOIBEEX3S34ZB5YVC5ZTMDIACX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KOIBEEX3S34ZB5YVC5ZTMDIACX/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":"2026-08-05T07:08:43Z","links":{"resolver":"https://pith.science/pith/KOIBEEX3S34ZB5YVC5ZTMDIACX","bundle":"https://pith.science/pith/KOIBEEX3S34ZB5YVC5ZTMDIACX/bundle.json","state":"https://pith.science/pith/KOIBEEX3S34ZB5YVC5ZTMDIACX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KOIBEEX3S34ZB5YVC5ZTMDIACX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KOIBEEX3S34ZB5YVC5ZTMDIACX","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":"107da409bf77d989d29acf4d301f098c5b62584936c943d72ae0e9fb47b9d9c1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-28T23:46:37Z","title_canon_sha256":"08e799553bb32e09c3e70ce02320b8f52b82d569e3491239500875e9c006ad59"},"schema_version":"1.0","source":{"id":"2607.26350","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26350","created_at":"2026-07-30T01:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26350v1","created_at":"2026-07-30T01:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26350","created_at":"2026-07-30T01:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"KOIBEEX3S34Z","created_at":"2026-07-30T01:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"KOIBEEX3S34ZB5YV","created_at":"2026-07-30T01:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"KOIBEEX3","created_at":"2026-07-30T01:18:08Z"}],"graph_snapshots":[{"event_id":"sha256:e7a9d1a7ddf6f98de54a17acd28377e6144eb4f056c79ad27e119488bb738e8d","target":"graph","created_at":"2026-07-30T01:18:08Z","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/2607.26350/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural audio codecs (NACs) have become popular for obtaining speech representations as discrete tokens. Beyond compression, discrete tokens can be used to train self-supervised learning (SSL) models. Such models, referred to as codec-based SSL models, reduce data storage and computational cost, enabling scalable SSL pre-training. However, their language sensitivity remains unclear. When the language changes, codec-based SSL models may require retraining, which undermines their efficiency. In this paper, we present a systematic analysis of language sensitivity by varying either the NAC training","authors_text":"Daigo Takizawa, Samuele Cornell, Satoru Fukayama, Shinji Watanabe, Tomohiko Nakamura, William Chen","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-28T23:46:37Z","title":"Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26350","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":"sha256:68aed1d71271ff2c50de038812c8230f6c8dc1a810fefb3d813642dcb3a78c70","target":"record","created_at":"2026-07-30T01:18:08Z","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":"107da409bf77d989d29acf4d301f098c5b62584936c943d72ae0e9fb47b9d9c1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-28T23:46:37Z","title_canon_sha256":"08e799553bb32e09c3e70ce02320b8f52b82d569e3491239500875e9c006ad59"},"schema_version":"1.0","source":{"id":"2607.26350","kind":"arxiv","version":1}},"canonical_sha256":"53901212fb96f990f7151773360d0015c31946e41d1a91ebe0e497fd3a52fea3","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53901212fb96f990f7151773360d0015c31946e41d1a91ebe0e497fd3a52fea3","first_computed_at":"2026-07-30T01:18:08.718627Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:18:08.718627Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26350","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68aed1d71271ff2c50de038812c8230f6c8dc1a810fefb3d813642dcb3a78c70","sha256:e7a9d1a7ddf6f98de54a17acd28377e6144eb4f056c79ad27e119488bb738e8d"],"state_sha256":"35140ddbcdc630d62034d95d661d2f2a3acc08a0c2c566ebf03ef0f483899e77"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nVxurl+UN8SU9UY+8mybXc4jg69jJOlMeFZrj7gm6RYch13Ey2I9CXSs3qEpGTpK0qOtTKDukOsypHenjNhGCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:08:43.973154Z","bundle_sha256":"4a0b06262beb67f45bac98fa14b76198d2d8c32be543e1b9fb67e8087172503b"}}