{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FCZTB7D6CLX7UIKQXSI556T4CA","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":"ef80cb93f3c954f57a1cb5a013371a9592aa3ce31f1b9e1d323f93441411dcc8","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-09-02T12:14:41Z","title_canon_sha256":"f110adb23e5ad8ae6107f903537e139457abd9259eb3777bd53f9149e0ae0fb8"},"schema_version":"1.0","source":{"id":"2509.02244","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02244","created_at":"2026-07-05T12:03:34Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02244v1","created_at":"2026-07-05T12:03:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02244","created_at":"2026-07-05T12:03:34Z"},{"alias_kind":"pith_short_12","alias_value":"FCZTB7D6CLX7","created_at":"2026-07-05T12:03:34Z"},{"alias_kind":"pith_short_16","alias_value":"FCZTB7D6CLX7UIKQ","created_at":"2026-07-05T12:03:34Z"},{"alias_kind":"pith_short_8","alias_value":"FCZTB7D6","created_at":"2026-07-05T12:03:34Z"}],"graph_snapshots":[{"event_id":"sha256:0a61e66b1b9123097d22f7c0dac355bdb43e6a600280c4520d0bc31879ff37bb","target":"graph","created_at":"2026-07-05T12:03:34Z","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/2509.02244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a neural speech codec that challenges the need for complex residual vector quantization (RVQ) stacks by introducing a simpler, single-stage quantization approach. Our method operates directly on the mel-spectrogram, treating it as a 2D data and quantizing non-overlapping 4x4 patches into a single, shared codebook. This patchwise design simplifies the architecture, enables low-latency streaming, and yields a discrete latent grid. To ensure high-fidelity synthesis, we employ a late-stage adversarial fine-tuning for the VQ-VAE and train a HiFi-GAN vocoder from scratch on the codec's re","authors_text":"Luis Felipe Chary, Miguel Arjona Ramirez","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-09-02T12:14:41Z","title":"Spectrogram Patch Codec: A 2D Block-Quantized VQ-VAE and HiFi-GAN for Neural Speech Coding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02244","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":"sha256:2cc0dc2dc744d5197dc08ae72c3d2733222b73f14d6e7dafd38e816e2801988c","target":"record","created_at":"2026-07-05T12:03:34Z","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":"ef80cb93f3c954f57a1cb5a013371a9592aa3ce31f1b9e1d323f93441411dcc8","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-09-02T12:14:41Z","title_canon_sha256":"f110adb23e5ad8ae6107f903537e139457abd9259eb3777bd53f9149e0ae0fb8"},"schema_version":"1.0","source":{"id":"2509.02244","kind":"arxiv","version":1}},"canonical_sha256":"28b330fc7e12effa2150bc91defa7c1011805e89289c51507dcbfbb501262090","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28b330fc7e12effa2150bc91defa7c1011805e89289c51507dcbfbb501262090","first_computed_at":"2026-07-05T12:03:34.647069Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:34.647069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KT+11eejNOvFkCcUHHRQhQlO+h3UQfNTeV78Mj3K11qVu09dyoLl98oXVsWQZwVYHFxKqge+5QdQ0V8rPuSTAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:34.647422Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.02244","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2cc0dc2dc744d5197dc08ae72c3d2733222b73f14d6e7dafd38e816e2801988c","sha256:0a61e66b1b9123097d22f7c0dac355bdb43e6a600280c4520d0bc31879ff37bb"],"state_sha256":"35c80074f4716b823502f334da456d1d032f03858838747824910b3b90e65209"}