{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QCZEL3XUS7Q7VHJOSW5M5OIR34","short_pith_number":"pith:QCZEL3XU","canonical_record":{"source":{"id":"2606.26824","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-25T10:04:35Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"4c51152d792fd253303a01119088bac20ad58f4fcf598667f56f38edaf1b3a6b","abstract_canon_sha256":"5478fe25a656c33c634f833ee46832150179eeaa19a06af7aa754bb5ab5440db"},"schema_version":"1.0"},"canonical_sha256":"80b245eef497e1fa9d2e95baceb911df36d3ba8af2feb8ef794f36e7d86dff6b","source":{"kind":"arxiv","id":"2606.26824","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QCZEL3XUS7Q7VHJOSW5M5OIR34","target":"record","payload":{"canonical_record":{"source":{"id":"2606.26824","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-25T10:04:35Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"4c51152d792fd253303a01119088bac20ad58f4fcf598667f56f38edaf1b3a6b","abstract_canon_sha256":"5478fe25a656c33c634f833ee46832150179eeaa19a06af7aa754bb5ab5440db"},"schema_version":"1.0"},"canonical_sha256":"80b245eef497e1fa9d2e95baceb911df36d3ba8af2feb8ef794f36e7d86dff6b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:16:00.900697Z","signature_b64":"Cr+maQnaQ/apngmZ7N9yTIN0GScw/vx9pzpGT1ICkKEKuRn5k3+GT5+irBd0GCFeaK9r9pmWGE4AQAjGzn3PAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80b245eef497e1fa9d2e95baceb911df36d3ba8af2feb8ef794f36e7d86dff6b","last_reissued_at":"2026-06-26T01:16:00.900302Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:16:00.900302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.26824","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":"2026-06-26T01:16:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z2luIxfqH+JUgwtnxUQw0lvgPNu/56cucfNaFU2FSHyI8TSu/Ij2o+cbyHLiihaZnzhOs1QbtuKMm5oNb5pEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:06:57.274880Z"},"content_sha256":"95723ee7cf8ed62da74eeb544123fd33527a0cf2486f007a22292a7f6d07447b","schema_version":"1.0","event_id":"sha256:95723ee7cf8ed62da74eeb544123fd33527a0cf2486f007a22292a7f6d07447b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QCZEL3XUS7Q7VHJOSW5M5OIR34","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"wav2tok 2.0: Scalable Audio Tokenization Maintaining Explicit Pairwise Token Alignment for Efficient Audio Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Adhiraj Banerjee, Vipul Arora","submitted_at":"2026-06-25T10:04:35Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26824","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/2606.26824/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":"2026-06-26T01:16:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hHIa0/WNG7kDtrwLN8eaVPRuejCD6v85OtE3ZcNTRoypJxRYqZO12fVuCsMvhVQa0ZNO7Nc4G/1lSzThz/nuBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:06:57.275483Z"},"content_sha256":"d5f2a3dc66fc5dfb1679c98a090e2eed9abe6cbf3b5e3d888c02c3c7ba611996","schema_version":"1.0","event_id":"sha256:d5f2a3dc66fc5dfb1679c98a090e2eed9abe6cbf3b5e3d888c02c3c7ba611996"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QCZEL3XUS7Q7VHJOSW5M5OIR34/bundle.json","state_url":"https://pith.science/pith/QCZEL3XUS7Q7VHJOSW5M5OIR34/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QCZEL3XUS7Q7VHJOSW5M5OIR34/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":"2026-07-05T09:06:57Z","links":{"resolver":"https://pith.science/pith/QCZEL3XUS7Q7VHJOSW5M5OIR34","bundle":"https://pith.science/pith/QCZEL3XUS7Q7VHJOSW5M5OIR34/bundle.json","state":"https://pith.science/pith/QCZEL3XUS7Q7VHJOSW5M5OIR34/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QCZEL3XUS7Q7VHJOSW5M5OIR34/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qcmFbWxHniTXWUr1yR3LLaNX6QEaRtB2C/V1qIo/iw54IxJdcf6JfI5kE8y9Ocm+eOUmPZvjzH35w7aAzUfVCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T09:06:57.278019Z","bundle_sha256":"2dd21d0fd7c93be359839664376ea8887e3cb132c278ff81969605f175cfecd1"}}