{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SRW6G7JEUGFSKC2U7UAL5PSEXQ","short_pith_number":"pith:SRW6G7JE","canonical_record":{"source":{"id":"2409.02384","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T02:20:59Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"810ea42fbd72ca1fd2058c7c452b9ef1a56de619f063c1de7acb6b2b52973a3e","abstract_canon_sha256":"dc0025757c48c4ce054f8a6ff344db92483ecb52b1791f12afae11a64ff248d6"},"schema_version":"1.0"},"canonical_sha256":"946de37d24a18b250b54fd00bebe44bc35693d861788c6d4a1af847f5d153eeb","source":{"kind":"arxiv","id":"2409.02384","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.02384","created_at":"2026-07-05T09:02:46Z"},{"alias_kind":"arxiv_version","alias_value":"2409.02384v1","created_at":"2026-07-05T09:02:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02384","created_at":"2026-07-05T09:02:46Z"},{"alias_kind":"pith_short_12","alias_value":"SRW6G7JEUGFS","created_at":"2026-07-05T09:02:46Z"},{"alias_kind":"pith_short_16","alias_value":"SRW6G7JEUGFSKC2U","created_at":"2026-07-05T09:02:46Z"},{"alias_kind":"pith_short_8","alias_value":"SRW6G7JE","created_at":"2026-07-05T09:02:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SRW6G7JEUGFSKC2U7UAL5PSEXQ","target":"record","payload":{"canonical_record":{"source":{"id":"2409.02384","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T02:20:59Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"810ea42fbd72ca1fd2058c7c452b9ef1a56de619f063c1de7acb6b2b52973a3e","abstract_canon_sha256":"dc0025757c48c4ce054f8a6ff344db92483ecb52b1791f12afae11a64ff248d6"},"schema_version":"1.0"},"canonical_sha256":"946de37d24a18b250b54fd00bebe44bc35693d861788c6d4a1af847f5d153eeb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:46.578360Z","signature_b64":"UGALpLDvaVG/zE1l5aFOhmMu/+mHIFMsdwy5YXx1fX30vl5/53u3gJ4Byc+ql34uBM5VCwPhWluO7LWBKV3CCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"946de37d24a18b250b54fd00bebe44bc35693d861788c6d4a1af847f5d153eeb","last_reissued_at":"2026-07-05T09:02:46.577804Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:46.577804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.02384","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":"2026-07-05T09:02:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sx9wI1LmUozsEhwgQj+cjG+wpmDwYDzftgIa72PAGBT1r564/OGyHDx87NeLn9I86+h7cJMfwb/8bPbQVkBGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-23T08:08:28.196730Z"},"content_sha256":"cb05f370c3a6f1b583c0ddc8d507ee51ff08eeb73d94070fd17cadf2da8ffed1","schema_version":"1.0","event_id":"sha256:cb05f370c3a6f1b583c0ddc8d507ee51ff08eeb73d94070fd17cadf2da8ffed1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SRW6G7JEUGFSKC2U7UAL5PSEXQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"STAB: Speech Tokenizer Assessment Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Andrew Rosenberg, Ankur Bapna, Bhuvana Ramabhadran, Chulayuth Asawaroengchai, Harman Singh, Kartik Audhkhasi, Shikhar Bharadwaj, Shikhar Vashishth, Sriram Ganapathy","submitted_at":"2024-09-04T02:20:59Z","abstract_excerpt":"Representing speech as discrete tokens provides a framework for transforming speech into a format that closely resembles text, thus enabling the use of speech as an input to the widely successful large language models (LLMs). Currently, while several speech tokenizers have been proposed, there is ambiguity regarding the properties that are desired from a tokenizer for specific downstream tasks and its overall generalizability. Evaluating the performance of tokenizers across different downstream tasks is a computationally intensive effort that poses challenges for scalability. To circumvent thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02384","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/2409.02384/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":"2026-07-05T09:02:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hAWXDChqGWyaJbQaXuzRM4XozjBFBWBC2/Wd6Zxwi/anE0ycPPAAPGe3A8VdZYfhu+OP4JlhDQvD1JZxS+43DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-23T08:08:28.197113Z"},"content_sha256":"ad9a67f606e687a9980c46fb02539eb7a3be58b3e8b27907c009c9301403b61a","schema_version":"1.0","event_id":"sha256:ad9a67f606e687a9980c46fb02539eb7a3be58b3e8b27907c009c9301403b61a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SRW6G7JEUGFSKC2U7UAL5PSEXQ/bundle.json","state_url":"https://pith.science/pith/SRW6G7JEUGFSKC2U7UAL5PSEXQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SRW6G7JEUGFSKC2U7UAL5PSEXQ/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":"2026-07-23T08:08:28Z","links":{"resolver":"https://pith.science/pith/SRW6G7JEUGFSKC2U7UAL5PSEXQ","bundle":"https://pith.science/pith/SRW6G7JEUGFSKC2U7UAL5PSEXQ/bundle.json","state":"https://pith.science/pith/SRW6G7JEUGFSKC2U7UAL5PSEXQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SRW6G7JEUGFSKC2U7UAL5PSEXQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SRW6G7JEUGFSKC2U7UAL5PSEXQ","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":"dc0025757c48c4ce054f8a6ff344db92483ecb52b1791f12afae11a64ff248d6","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T02:20:59Z","title_canon_sha256":"810ea42fbd72ca1fd2058c7c452b9ef1a56de619f063c1de7acb6b2b52973a3e"},"schema_version":"1.0","source":{"id":"2409.02384","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.02384","created_at":"2026-07-05T09:02:46Z"},{"alias_kind":"arxiv_version","alias_value":"2409.02384v1","created_at":"2026-07-05T09:02:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02384","created_at":"2026-07-05T09:02:46Z"},{"alias_kind":"pith_short_12","alias_value":"SRW6G7JEUGFS","created_at":"2026-07-05T09:02:46Z"},{"alias_kind":"pith_short_16","alias_value":"SRW6G7JEUGFSKC2U","created_at":"2026-07-05T09:02:46Z"},{"alias_kind":"pith_short_8","alias_value":"SRW6G7JE","created_at":"2026-07-05T09:02:46Z"}],"graph_snapshots":[{"event_id":"sha256:ad9a67f606e687a9980c46fb02539eb7a3be58b3e8b27907c009c9301403b61a","target":"graph","created_at":"2026-07-05T09:02:46Z","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/2409.02384/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Representing speech as discrete tokens provides a framework for transforming speech into a format that closely resembles text, thus enabling the use of speech as an input to the widely successful large language models (LLMs). Currently, while several speech tokenizers have been proposed, there is ambiguity regarding the properties that are desired from a tokenizer for specific downstream tasks and its overall generalizability. Evaluating the performance of tokenizers across different downstream tasks is a computationally intensive effort that poses challenges for scalability. To circumvent thi","authors_text":"Andrew Rosenberg, Ankur Bapna, Bhuvana Ramabhadran, Chulayuth Asawaroengchai, Harman Singh, Kartik Audhkhasi, Shikhar Bharadwaj, Shikhar Vashishth, Sriram Ganapathy","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T02:20:59Z","title":"STAB: Speech Tokenizer Assessment Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02384","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:cb05f370c3a6f1b583c0ddc8d507ee51ff08eeb73d94070fd17cadf2da8ffed1","target":"record","created_at":"2026-07-05T09:02:46Z","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":"dc0025757c48c4ce054f8a6ff344db92483ecb52b1791f12afae11a64ff248d6","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T02:20:59Z","title_canon_sha256":"810ea42fbd72ca1fd2058c7c452b9ef1a56de619f063c1de7acb6b2b52973a3e"},"schema_version":"1.0","source":{"id":"2409.02384","kind":"arxiv","version":1}},"canonical_sha256":"946de37d24a18b250b54fd00bebe44bc35693d861788c6d4a1af847f5d153eeb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"946de37d24a18b250b54fd00bebe44bc35693d861788c6d4a1af847f5d153eeb","first_computed_at":"2026-07-05T09:02:46.577804Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:02:46.577804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UGALpLDvaVG/zE1l5aFOhmMu/+mHIFMsdwy5YXx1fX30vl5/53u3gJ4Byc+ql34uBM5VCwPhWluO7LWBKV3CCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:02:46.578360Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.02384","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb05f370c3a6f1b583c0ddc8d507ee51ff08eeb73d94070fd17cadf2da8ffed1","sha256:ad9a67f606e687a9980c46fb02539eb7a3be58b3e8b27907c009c9301403b61a"],"state_sha256":"bcac2cc41175d0253f221889f765b755feb4c83a38ab2e46c77985218e13ef85"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lAP1FTVWVXrSt4l7SZuiF5C9d9niem2HOn6MymCakPwyL2QidMvVUh5gbqKT0YSFxdN2vlqqsMNzgiiwPi5wCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-23T08:08:28.199338Z","bundle_sha256":"c7eafd7cd52cd9564d60816786483715331ccefae8385c9d820de5bd773bec93"}}