{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QPVGYJV3NGVMMHVKXGBS6EF3S5","short_pith_number":"pith:QPVGYJV3","schema_version":"1.0","canonical_sha256":"83ea6c26bb69aac61eaab9832f10bb975cc64976471a532eb66a9a2856f68243","source":{"kind":"arxiv","id":"2505.14470","version":2},"attestation_state":"computed","paper":{"title":"PAST: Phonetic-Acoustic Speech Tokenizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Nadav Har-Tuv, Or Tal, Yossi Adi","submitted_at":"2025-05-20T15:05:14Z","abstract_excerpt":"We present PAST, a novel end-to-end framework that jointly models phonetic information alongside signal reconstruction, eliminating the need for external pretrained models. Unlike previous approaches that rely on pretrained self-supervised models, PAST employs supervised phonetic data, directly integrating domain knowledge into the tokenization process via auxiliary tasks. Additionally, we introduce a streamable, causal variant of PAST, enabling real-time speech applications. Results demonstrate that PAST surpasses existing evaluated baseline tokenizers across common evaluation metrics, includ"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.14470","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-20T15:05:14Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"98cb4e68eb483a72ba885448cbc5803f1ad9f545946500b6379c6a0359e779f0","abstract_canon_sha256":"ed5f0085908e8861e37fb1334a3a6fd89c68743c3825db75c94b87a7b9ba3498"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:46.765757Z","signature_b64":"E99A7Gbm/2J7axWGKyb+6beBdrLG26N0bNcSq+Sqq+SPf+hTFPAXF6mFDN79fk+2hHdWV9Cqk3EvCekcL322CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83ea6c26bb69aac61eaab9832f10bb975cc64976471a532eb66a9a2856f68243","last_reissued_at":"2026-07-05T11:15:46.765109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:46.765109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PAST: Phonetic-Acoustic Speech Tokenizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Nadav Har-Tuv, Or Tal, Yossi Adi","submitted_at":"2025-05-20T15:05:14Z","abstract_excerpt":"We present PAST, a novel end-to-end framework that jointly models phonetic information alongside signal reconstruction, eliminating the need for external pretrained models. Unlike previous approaches that rely on pretrained self-supervised models, PAST employs supervised phonetic data, directly integrating domain knowledge into the tokenization process via auxiliary tasks. Additionally, we introduce a streamable, causal variant of PAST, enabling real-time speech applications. Results demonstrate that PAST surpasses existing evaluated baseline tokenizers across common evaluation metrics, includ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14470","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/2505.14470/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.14470","created_at":"2026-07-05T11:15:46.765187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14470v2","created_at":"2026-07-05T11:15:46.765187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14470","created_at":"2026-07-05T11:15:46.765187+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPVGYJV3NGVM","created_at":"2026-07-05T11:15:46.765187+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPVGYJV3NGVMMHVK","created_at":"2026-07-05T11:15:46.765187+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPVGYJV3","created_at":"2026-07-05T11:15:46.765187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11631","citing_title":"Benchmarking Neural Speech Compression from a Rate-Distortion Perspective","ref_index":77,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QPVGYJV3NGVMMHVKXGBS6EF3S5","json":"https://pith.science/pith/QPVGYJV3NGVMMHVKXGBS6EF3S5.json","graph_json":"https://pith.science/api/pith-number/QPVGYJV3NGVMMHVKXGBS6EF3S5/graph.json","events_json":"https://pith.science/api/pith-number/QPVGYJV3NGVMMHVKXGBS6EF3S5/events.json","paper":"https://pith.science/paper/QPVGYJV3"},"agent_actions":{"view_html":"https://pith.science/pith/QPVGYJV3NGVMMHVKXGBS6EF3S5","download_json":"https://pith.science/pith/QPVGYJV3NGVMMHVKXGBS6EF3S5.json","view_paper":"https://pith.science/paper/QPVGYJV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14470&json=true","fetch_graph":"https://pith.science/api/pith-number/QPVGYJV3NGVMMHVKXGBS6EF3S5/graph.json","fetch_events":"https://pith.science/api/pith-number/QPVGYJV3NGVMMHVKXGBS6EF3S5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPVGYJV3NGVMMHVKXGBS6EF3S5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPVGYJV3NGVMMHVKXGBS6EF3S5/action/storage_attestation","attest_author":"https://pith.science/pith/QPVGYJV3NGVMMHVKXGBS6EF3S5/action/author_attestation","sign_citation":"https://pith.science/pith/QPVGYJV3NGVMMHVKXGBS6EF3S5/action/citation_signature","submit_replication":"https://pith.science/pith/QPVGYJV3NGVMMHVKXGBS6EF3S5/action/replication_record"}},"created_at":"2026-07-05T11:15:46.765187+00:00","updated_at":"2026-07-05T11:15:46.765187+00:00"}