{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QCZEL3XUS7Q7VHJOSW5M5OIR34","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":"5478fe25a656c33c634f833ee46832150179eeaa19a06af7aa754bb5ab5440db","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-25T10:04:35Z","title_canon_sha256":"4c51152d792fd253303a01119088bac20ad58f4fcf598667f56f38edaf1b3a6b"},"schema_version":"1.0","source":{"id":"2606.26824","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26824","created_at":"2026-06-26T01:16:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26824v1","created_at":"2026-06-26T01:16:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26824","created_at":"2026-06-26T01:16:00Z"},{"alias_kind":"pith_short_12","alias_value":"QCZEL3XUS7Q7","created_at":"2026-06-26T01:16:00Z"},{"alias_kind":"pith_short_16","alias_value":"QCZEL3XUS7Q7VHJO","created_at":"2026-06-26T01:16:00Z"},{"alias_kind":"pith_short_8","alias_value":"QCZEL3XU","created_at":"2026-06-26T01:16:00Z"}],"graph_snapshots":[{"event_id":"sha256:d5f2a3dc66fc5dfb1679c98a090e2eed9abe6cbf3b5e3d888c02c3c7ba611996","target":"graph","created_at":"2026-06-26T01:16:00Z","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/2606.26824/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning discrete speech representations that preserve similarity across variable-length utterances is central to query-by-example spoken term detection (QbE-STD). While wav2tok introduced CTC-based sequence alignment to enforce token consistency, its tightly coupled clustering and alignment training recipe limits scalability. We propose wav2tok 2.0, a scalable alignment-aware speech tokenizer built on the BEST-STD backbone. wav2tok 2.0 employs staged training, first learning discriminative, speaker-invariant representations via contrastive learning and vector quantization, and then enforcing ","authors_text":"Adhiraj Banerjee, Vipul Arora","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-25T10:04:35Z","title":"wav2tok 2.0: Scalable Audio Tokenization Maintaining Explicit Pairwise Token Alignment for Efficient Audio Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26824","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":"sha256:95723ee7cf8ed62da74eeb544123fd33527a0cf2486f007a22292a7f6d07447b","target":"record","created_at":"2026-06-26T01:16:00Z","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":"5478fe25a656c33c634f833ee46832150179eeaa19a06af7aa754bb5ab5440db","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-25T10:04:35Z","title_canon_sha256":"4c51152d792fd253303a01119088bac20ad58f4fcf598667f56f38edaf1b3a6b"},"schema_version":"1.0","source":{"id":"2606.26824","kind":"arxiv","version":1}},"canonical_sha256":"80b245eef497e1fa9d2e95baceb911df36d3ba8af2feb8ef794f36e7d86dff6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80b245eef497e1fa9d2e95baceb911df36d3ba8af2feb8ef794f36e7d86dff6b","first_computed_at":"2026-06-26T01:16:00.900302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:16:00.900302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cr+maQnaQ/apngmZ7N9yTIN0GScw/vx9pzpGT1ICkKEKuRn5k3+GT5+irBd0GCFeaK9r9pmWGE4AQAjGzn3PAg==","signature_status":"signed_v1","signed_at":"2026-06-26T01:16:00.900697Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.26824","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95723ee7cf8ed62da74eeb544123fd33527a0cf2486f007a22292a7f6d07447b","sha256:d5f2a3dc66fc5dfb1679c98a090e2eed9abe6cbf3b5e3d888c02c3c7ba611996"],"state_sha256":"33da585f48d3373bd47dc0829640856a9b90d9bd84aaf82fac14736e2dd4f2f0"}