{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5UENNQPKW57JCIDGHSDN6JSJYL","short_pith_number":"pith:5UENNQPK","canonical_record":{"source":{"id":"2603.10371","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-03-11T03:32:25Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d89ade4c7cf4e8c6a311ae1a686f061a71f6d09b43c2317d055fa2aece0e2657","abstract_canon_sha256":"9b1eb14bb27b9506fa78e584db15a24afe7e7603e4370d8e824a520ad8723816"},"schema_version":"1.0"},"canonical_sha256":"ed08d6c1eab77e9120663c86df2649c2e18c78a6156dacf5076c35a43bfdb193","source":{"kind":"arxiv","id":"2603.10371","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.10371","created_at":"2026-06-25T01:18:37Z"},{"alias_kind":"arxiv_version","alias_value":"2603.10371v2","created_at":"2026-06-25T01:18:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.10371","created_at":"2026-06-25T01:18:37Z"},{"alias_kind":"pith_short_12","alias_value":"5UENNQPKW57J","created_at":"2026-06-25T01:18:37Z"},{"alias_kind":"pith_short_16","alias_value":"5UENNQPKW57JCIDG","created_at":"2026-06-25T01:18:37Z"},{"alias_kind":"pith_short_8","alias_value":"5UENNQPK","created_at":"2026-06-25T01:18:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5UENNQPKW57JCIDGHSDN6JSJYL","target":"record","payload":{"canonical_record":{"source":{"id":"2603.10371","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-03-11T03:32:25Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d89ade4c7cf4e8c6a311ae1a686f061a71f6d09b43c2317d055fa2aece0e2657","abstract_canon_sha256":"9b1eb14bb27b9506fa78e584db15a24afe7e7603e4370d8e824a520ad8723816"},"schema_version":"1.0"},"canonical_sha256":"ed08d6c1eab77e9120663c86df2649c2e18c78a6156dacf5076c35a43bfdb193","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:37.287845Z","signature_b64":"fJos8by4WPw4R27wxJBfkd9pXr7UHUtT5PapmKkm6F4eUpYnzYGTeJcIP5ekLomG4etB6fQEVKmzj5zvdw0NCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed08d6c1eab77e9120663c86df2649c2e18c78a6156dacf5076c35a43bfdb193","last_reissued_at":"2026-06-25T01:18:37.287505Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:37.287505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.10371","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-25T01:18:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kpy8npS/Aul9NOKbT9M+NT0eLrdjKJRekWOKKIG4sHowbAwdujx6yy886vCFOEnkGo9WifFhRAwPM8dPOKJBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T01:34:29.836076Z"},"content_sha256":"ec51371697fd5cd0f2bf87bf26fb5d80c39491c4787c34e400f447f5dd1974ea","schema_version":"1.0","event_id":"sha256:ec51371697fd5cd0f2bf87bf26fb5d80c39491c4787c34e400f447f5dd1974ea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5UENNQPKW57JCIDGHSDN6JSJYL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speech Codec Probing from Semantic and Phonetic Perspectives","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Chang Zeng, Jianbo Ma, Shih-Heng Wang, Shrikanth Narayanan, Tiantian Feng, Xuan Shi","submitted_at":"2026-03-11T03:32:25Z","abstract_excerpt":"Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems. Speech tokenizers are expected to preserve both semantic and acoustic information for downstream understanding and generation tasks. However, emerging evidence suggests that the term \"semantic\" in speech processing does not align with linguistic lexical-semantic, leading to a mismatch between speech and text modality. In this paper, we systematically analyze the information encoded by several widely used speech tokenizers, evaluating their lexical-semantic and phonetic content through t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.10371","kind":"arxiv","version":2},"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/2603.10371/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":"2026-06-25T01:18:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cfhgN9yMtiBG/GrSfvg/RAWAoIO3J+6aFrCP59hOP/bAUKHyJCxFU9iw91CEi/UF0jf4Ht7lCZGSM+qg/D1iCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T01:34:29.836847Z"},"content_sha256":"5d47b457a5fd54e581dfe8a8725496c099be6b421a089ad2f9b057a3bddfcb35","schema_version":"1.0","event_id":"sha256:5d47b457a5fd54e581dfe8a8725496c099be6b421a089ad2f9b057a3bddfcb35"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5UENNQPKW57JCIDGHSDN6JSJYL/bundle.json","state_url":"https://pith.science/pith/5UENNQPKW57JCIDGHSDN6JSJYL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5UENNQPKW57JCIDGHSDN6JSJYL/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":"2026-06-30T01:34:29Z","links":{"resolver":"https://pith.science/pith/5UENNQPKW57JCIDGHSDN6JSJYL","bundle":"https://pith.science/pith/5UENNQPKW57JCIDGHSDN6JSJYL/bundle.json","state":"https://pith.science/pith/5UENNQPKW57JCIDGHSDN6JSJYL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5UENNQPKW57JCIDGHSDN6JSJYL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5UENNQPKW57JCIDGHSDN6JSJYL","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":"9b1eb14bb27b9506fa78e584db15a24afe7e7603e4370d8e824a520ad8723816","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-03-11T03:32:25Z","title_canon_sha256":"d89ade4c7cf4e8c6a311ae1a686f061a71f6d09b43c2317d055fa2aece0e2657"},"schema_version":"1.0","source":{"id":"2603.10371","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.10371","created_at":"2026-06-25T01:18:37Z"},{"alias_kind":"arxiv_version","alias_value":"2603.10371v2","created_at":"2026-06-25T01:18:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.10371","created_at":"2026-06-25T01:18:37Z"},{"alias_kind":"pith_short_12","alias_value":"5UENNQPKW57J","created_at":"2026-06-25T01:18:37Z"},{"alias_kind":"pith_short_16","alias_value":"5UENNQPKW57JCIDG","created_at":"2026-06-25T01:18:37Z"},{"alias_kind":"pith_short_8","alias_value":"5UENNQPK","created_at":"2026-06-25T01:18:37Z"}],"graph_snapshots":[{"event_id":"sha256:5d47b457a5fd54e581dfe8a8725496c099be6b421a089ad2f9b057a3bddfcb35","target":"graph","created_at":"2026-06-25T01:18:37Z","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/2603.10371/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems. Speech tokenizers are expected to preserve both semantic and acoustic information for downstream understanding and generation tasks. However, emerging evidence suggests that the term \"semantic\" in speech processing does not align with linguistic lexical-semantic, leading to a mismatch between speech and text modality. In this paper, we systematically analyze the information encoded by several widely used speech tokenizers, evaluating their lexical-semantic and phonetic content through t","authors_text":"Chang Zeng, Jianbo Ma, Shih-Heng Wang, Shrikanth Narayanan, Tiantian Feng, Xuan Shi","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-03-11T03:32:25Z","title":"Speech Codec Probing from Semantic and Phonetic Perspectives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.10371","kind":"arxiv","version":2},"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:ec51371697fd5cd0f2bf87bf26fb5d80c39491c4787c34e400f447f5dd1974ea","target":"record","created_at":"2026-06-25T01:18:37Z","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":"9b1eb14bb27b9506fa78e584db15a24afe7e7603e4370d8e824a520ad8723816","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-03-11T03:32:25Z","title_canon_sha256":"d89ade4c7cf4e8c6a311ae1a686f061a71f6d09b43c2317d055fa2aece0e2657"},"schema_version":"1.0","source":{"id":"2603.10371","kind":"arxiv","version":2}},"canonical_sha256":"ed08d6c1eab77e9120663c86df2649c2e18c78a6156dacf5076c35a43bfdb193","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed08d6c1eab77e9120663c86df2649c2e18c78a6156dacf5076c35a43bfdb193","first_computed_at":"2026-06-25T01:18:37.287505Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:37.287505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fJos8by4WPw4R27wxJBfkd9pXr7UHUtT5PapmKkm6F4eUpYnzYGTeJcIP5ekLomG4etB6fQEVKmzj5zvdw0NCg==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:37.287845Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.10371","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec51371697fd5cd0f2bf87bf26fb5d80c39491c4787c34e400f447f5dd1974ea","sha256:5d47b457a5fd54e581dfe8a8725496c099be6b421a089ad2f9b057a3bddfcb35"],"state_sha256":"1b5d6e540f5b9bba0e6b67bceb7847cb2e2950df1fdbef80d6eb9eb32cc98c45"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dAx356lOAgVmlEgDFsxcRofXf3o0FbWI/dyYrpUX0SU3cMiyA+BKqglWb29uBY4MvVZj9j2jbNGbPpNvMyCrCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T01:34:29.840532Z","bundle_sha256":"a06868ac61a1ce819c72f0f449f81826c173f91d8d25f7dc300740d42dec2885"}}