{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7NQAQYZSRGHOZ6N47TFOSCRLMP","short_pith_number":"pith:7NQAQYZS","schema_version":"1.0","canonical_sha256":"fb60086332898eecf9bcfccae90a2b63c428aa1ee1970df5bd8c2af8063af517","source":{"kind":"arxiv","id":"2607.01865","version":1},"attestation_state":"computed","paper":{"title":"Neural Audio Codec with Adjustable Token Temporal Resolution Using Sampling-Frequency-Independent Convolutional Layers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Kanami Imamura, Tomohiko Nakamura, Wataru Nakata, Yuki Saito","submitted_at":"2026-07-02T08:20:03Z","abstract_excerpt":"Discrete tokens obtained from neural audio codecs (NACs) have been used as compact representations in audio generation and understanding models. In such token-based systems, token temporal resolution (TTR), defined as the time interval between adjacent token frames, is important because it controls the trade-off between representing rapid acoustic events and reducing token-sequence length. However, most NACs are trained at a single TTR and require separate training for each TTR. This paper proposes a mechanism that enables a single NAC to operate at multiple TTRs using sampling-frequency-indep"},"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":"2607.01865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-02T08:20:03Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"3588c7903587f737abb920a81b7cd7831a313174cd9c66ae0dafc3da44c63577","abstract_canon_sha256":"85dc32963af0cdeb0e3f346fb6f14afbf86499b2a30c6e6dae04f5aa398a6d60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:32.028026Z","signature_b64":"5gwp1c0w6weADuQBSPCZEzi7bNygdNwT/Q/BvPoxlsnBNTIw46yIiEewfSVA2qOlPduX3Bof8rRFEtuwG0vjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb60086332898eecf9bcfccae90a2b63c428aa1ee1970df5bd8c2af8063af517","last_reissued_at":"2026-07-03T01:17:32.027652Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:32.027652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Audio Codec with Adjustable Token Temporal Resolution Using Sampling-Frequency-Independent Convolutional Layers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Kanami Imamura, Tomohiko Nakamura, Wataru Nakata, Yuki Saito","submitted_at":"2026-07-02T08:20:03Z","abstract_excerpt":"Discrete tokens obtained from neural audio codecs (NACs) have been used as compact representations in audio generation and understanding models. In such token-based systems, token temporal resolution (TTR), defined as the time interval between adjacent token frames, is important because it controls the trade-off between representing rapid acoustic events and reducing token-sequence length. However, most NACs are trained at a single TTR and require separate training for each TTR. This paper proposes a mechanism that enables a single NAC to operate at multiple TTRs using sampling-frequency-indep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01865","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/2607.01865/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":"2607.01865","created_at":"2026-07-03T01:17:32.027710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01865v1","created_at":"2026-07-03T01:17:32.027710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01865","created_at":"2026-07-03T01:17:32.027710+00:00"},{"alias_kind":"pith_short_12","alias_value":"7NQAQYZSRGHO","created_at":"2026-07-03T01:17:32.027710+00:00"},{"alias_kind":"pith_short_16","alias_value":"7NQAQYZSRGHOZ6N4","created_at":"2026-07-03T01:17:32.027710+00:00"},{"alias_kind":"pith_short_8","alias_value":"7NQAQYZS","created_at":"2026-07-03T01:17:32.027710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.01865","citing_title":"Neural Audio Codec with Adjustable Token Temporal Resolution Using Sampling-Frequency-Independent Convolutional Layers","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7NQAQYZSRGHOZ6N47TFOSCRLMP","json":"https://pith.science/pith/7NQAQYZSRGHOZ6N47TFOSCRLMP.json","graph_json":"https://pith.science/api/pith-number/7NQAQYZSRGHOZ6N47TFOSCRLMP/graph.json","events_json":"https://pith.science/api/pith-number/7NQAQYZSRGHOZ6N47TFOSCRLMP/events.json","paper":"https://pith.science/paper/7NQAQYZS"},"agent_actions":{"view_html":"https://pith.science/pith/7NQAQYZSRGHOZ6N47TFOSCRLMP","download_json":"https://pith.science/pith/7NQAQYZSRGHOZ6N47TFOSCRLMP.json","view_paper":"https://pith.science/paper/7NQAQYZS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01865&json=true","fetch_graph":"https://pith.science/api/pith-number/7NQAQYZSRGHOZ6N47TFOSCRLMP/graph.json","fetch_events":"https://pith.science/api/pith-number/7NQAQYZSRGHOZ6N47TFOSCRLMP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7NQAQYZSRGHOZ6N47TFOSCRLMP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7NQAQYZSRGHOZ6N47TFOSCRLMP/action/storage_attestation","attest_author":"https://pith.science/pith/7NQAQYZSRGHOZ6N47TFOSCRLMP/action/author_attestation","sign_citation":"https://pith.science/pith/7NQAQYZSRGHOZ6N47TFOSCRLMP/action/citation_signature","submit_replication":"https://pith.science/pith/7NQAQYZSRGHOZ6N47TFOSCRLMP/action/replication_record"}},"created_at":"2026-07-03T01:17:32.027710+00:00","updated_at":"2026-07-03T01:17:32.027710+00:00"}