{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6TVDCNE545HJEWG25OM3NX4QHI","short_pith_number":"pith:6TVDCNE5","canonical_record":{"source":{"id":"2409.08805","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-13T13:13:39Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"eea243680588d073f96c8c57c43477dae5b07d4f894c8c75fbf28c114ef11b0e","abstract_canon_sha256":"a3fec95e7f846d8d02f86259b459b3ab0ee514f434e68aa2a07ccd2c72f27751"},"schema_version":"1.0"},"canonical_sha256":"f4ea31349de74e9258daeb99b6df903a3c6e162ae8574980910b5e3e8f5c50e7","source":{"kind":"arxiv","id":"2409.08805","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08805","created_at":"2026-07-05T09:06:48Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08805v1","created_at":"2026-07-05T09:06:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08805","created_at":"2026-07-05T09:06:48Z"},{"alias_kind":"pith_short_12","alias_value":"6TVDCNE545HJ","created_at":"2026-07-05T09:06:48Z"},{"alias_kind":"pith_short_16","alias_value":"6TVDCNE545HJEWG2","created_at":"2026-07-05T09:06:48Z"},{"alias_kind":"pith_short_8","alias_value":"6TVDCNE5","created_at":"2026-07-05T09:06:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6TVDCNE545HJEWG25OM3NX4QHI","target":"record","payload":{"canonical_record":{"source":{"id":"2409.08805","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-13T13:13:39Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"eea243680588d073f96c8c57c43477dae5b07d4f894c8c75fbf28c114ef11b0e","abstract_canon_sha256":"a3fec95e7f846d8d02f86259b459b3ab0ee514f434e68aa2a07ccd2c72f27751"},"schema_version":"1.0"},"canonical_sha256":"f4ea31349de74e9258daeb99b6df903a3c6e162ae8574980910b5e3e8f5c50e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:48.003417Z","signature_b64":"8tLBuNERUhGoP2GZ/cMS/pjb+NFQCPdvGjQqN9AGO4HiMdKM26m1YFmHc+5nyoJN6MF+lB9llpk3bcKhILkUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4ea31349de74e9258daeb99b6df903a3c6e162ae8574980910b5e3e8f5c50e7","last_reissued_at":"2026-07-05T09:06:48.002935Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:48.002935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.08805","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":"2026-07-05T09:06:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KQ/cGgj1tQIHH7RdwAKP+xzI0S2FQnQu+doQSPD+wIJUGwM/rC2iMQnlZd5TxKSUeYh0wvg670eL+Hsof3b8DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:52:16.500921Z"},"content_sha256":"0a132cb2510a5ac2f00136ff94f2d39e3fbb587566882340f96f80b3bdb9661c","schema_version":"1.0","event_id":"sha256:0a132cb2510a5ac2f00136ff94f2d39e3fbb587566882340f96f80b3bdb9661c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6TVDCNE545HJEWG25OM3NX4QHI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring SSL Discrete Tokens for Multilingual ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Daxin Tan, Dingdong Wang, Huimeng Wang, Mingyu Cui, Xiao Chen, Xie Chen, Xunying Liu, Yifan Yang","submitted_at":"2024-09-13T13:13:39Z","abstract_excerpt":"With the advancement of Self-supervised Learning (SSL) in speech-related tasks, there has been growing interest in utilizing discrete tokens generated by SSL for automatic speech recognition (ASR), as they offer faster processing techniques. However, previous studies primarily focused on multilingual ASR with Fbank features or English ASR with discrete tokens, leaving a gap in adapting discrete tokens for multilingual ASR scenarios. This study presents a comprehensive comparison of discrete tokens generated by various leading SSL models across multiple language domains. We aim to explore the p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08805","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/2409.08805/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":"2026-07-05T09:06:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gFUoKjoyFnXkIW5Xwexia99NAzLmzK1ufJ7Povo9Dimnggu/dTCOn+hOCkWFVDSkGmXbn57UBPqAJxU0DeBXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:52:16.501578Z"},"content_sha256":"1758bc7c2ef157c0b11e6530db9e033c27d3b0af0ea234e2d334d8084f66fda7","schema_version":"1.0","event_id":"sha256:1758bc7c2ef157c0b11e6530db9e033c27d3b0af0ea234e2d334d8084f66fda7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6TVDCNE545HJEWG25OM3NX4QHI/bundle.json","state_url":"https://pith.science/pith/6TVDCNE545HJEWG25OM3NX4QHI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6TVDCNE545HJEWG25OM3NX4QHI/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":"2026-08-17T22:52:16Z","links":{"resolver":"https://pith.science/pith/6TVDCNE545HJEWG25OM3NX4QHI","bundle":"https://pith.science/pith/6TVDCNE545HJEWG25OM3NX4QHI/bundle.json","state":"https://pith.science/pith/6TVDCNE545HJEWG25OM3NX4QHI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6TVDCNE545HJEWG25OM3NX4QHI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6TVDCNE545HJEWG25OM3NX4QHI","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":"a3fec95e7f846d8d02f86259b459b3ab0ee514f434e68aa2a07ccd2c72f27751","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-13T13:13:39Z","title_canon_sha256":"eea243680588d073f96c8c57c43477dae5b07d4f894c8c75fbf28c114ef11b0e"},"schema_version":"1.0","source":{"id":"2409.08805","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08805","created_at":"2026-07-05T09:06:48Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08805v1","created_at":"2026-07-05T09:06:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08805","created_at":"2026-07-05T09:06:48Z"},{"alias_kind":"pith_short_12","alias_value":"6TVDCNE545HJ","created_at":"2026-07-05T09:06:48Z"},{"alias_kind":"pith_short_16","alias_value":"6TVDCNE545HJEWG2","created_at":"2026-07-05T09:06:48Z"},{"alias_kind":"pith_short_8","alias_value":"6TVDCNE5","created_at":"2026-07-05T09:06:48Z"}],"graph_snapshots":[{"event_id":"sha256:1758bc7c2ef157c0b11e6530db9e033c27d3b0af0ea234e2d334d8084f66fda7","target":"graph","created_at":"2026-07-05T09:06:48Z","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/2409.08805/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the advancement of Self-supervised Learning (SSL) in speech-related tasks, there has been growing interest in utilizing discrete tokens generated by SSL for automatic speech recognition (ASR), as they offer faster processing techniques. However, previous studies primarily focused on multilingual ASR with Fbank features or English ASR with discrete tokens, leaving a gap in adapting discrete tokens for multilingual ASR scenarios. This study presents a comprehensive comparison of discrete tokens generated by various leading SSL models across multiple language domains. We aim to explore the p","authors_text":"Daxin Tan, Dingdong Wang, Huimeng Wang, Mingyu Cui, Xiao Chen, Xie Chen, Xunying Liu, Yifan Yang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-13T13:13:39Z","title":"Exploring SSL Discrete Tokens for Multilingual ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08805","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":"sha256:0a132cb2510a5ac2f00136ff94f2d39e3fbb587566882340f96f80b3bdb9661c","target":"record","created_at":"2026-07-05T09:06:48Z","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":"a3fec95e7f846d8d02f86259b459b3ab0ee514f434e68aa2a07ccd2c72f27751","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-13T13:13:39Z","title_canon_sha256":"eea243680588d073f96c8c57c43477dae5b07d4f894c8c75fbf28c114ef11b0e"},"schema_version":"1.0","source":{"id":"2409.08805","kind":"arxiv","version":1}},"canonical_sha256":"f4ea31349de74e9258daeb99b6df903a3c6e162ae8574980910b5e3e8f5c50e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4ea31349de74e9258daeb99b6df903a3c6e162ae8574980910b5e3e8f5c50e7","first_computed_at":"2026-07-05T09:06:48.002935Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:06:48.002935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8tLBuNERUhGoP2GZ/cMS/pjb+NFQCPdvGjQqN9AGO4HiMdKM26m1YFmHc+5nyoJN6MF+lB9llpk3bcKhILkUBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:06:48.003417Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.08805","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a132cb2510a5ac2f00136ff94f2d39e3fbb587566882340f96f80b3bdb9661c","sha256:1758bc7c2ef157c0b11e6530db9e033c27d3b0af0ea234e2d334d8084f66fda7"],"state_sha256":"9a7a014433b14c59cf9a52a837e9e46eba1a46b34b56d257dac95028f240be8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cAZq16BWGslvoniOL6mJwRrEj/Snp5FIiC4o0PE3GB4HU9wHftFyarIWvgMFUHiJaYFO6ekHd5paiSWdmXKWAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T22:52:16.506715Z","bundle_sha256":"a2adc560f8e3ad566f4a12d8e73ca4109c37c3eba4bd56d531bac934c9df1f17"}}