{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UR6G73GXEYEFRIZLONAXUDINEL","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":"3a4f9305312fdaf349d38d032809cfb6e4d635aed636b44d2a156be42cec05c1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-11T06:06:02Z","title_canon_sha256":"411394ffcb6e7454eacfc08c140d5b28f99e83d4fe511ccd06db1ee9ac6f140e"},"schema_version":"1.0","source":{"id":"2606.12940","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12940","created_at":"2026-06-12T01:09:35Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12940v1","created_at":"2026-06-12T01:09:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12940","created_at":"2026-06-12T01:09:35Z"},{"alias_kind":"pith_short_12","alias_value":"UR6G73GXEYEF","created_at":"2026-06-12T01:09:35Z"},{"alias_kind":"pith_short_16","alias_value":"UR6G73GXEYEFRIZL","created_at":"2026-06-12T01:09:35Z"},{"alias_kind":"pith_short_8","alias_value":"UR6G73GX","created_at":"2026-06-12T01:09:35Z"}],"graph_snapshots":[{"event_id":"sha256:200aa71688e425afefcfa4f7cc52dd2bea4fabfe4643a24c39d3a9ed286a0094","target":"graph","created_at":"2026-06-12T01:09:35Z","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/2606.12940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural speech codecs based on Vector-Quantized VAEs (VQ-VAEs) are core audio tokenizers for speech LLMs, yet their reconstruction fidelity is bottlenecked by quantization error. Modifying the quantizer or increasing model capacity are common fixes, but they complicate downstream language modeling. Our core idea is to align the decoder's internal feature manifolds when processing both the quantized tokens and their original continuous embeddings, using a lightweight feature-mapping loss. This requires minimal training overhead and no inference-time changes. Applied to XCodec2, self-guidance imp","authors_text":"Hui Wang, Jingran Xie, Xiang Li, Yixuan Zhou, Zhiyong Wu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-11T06:06:02Z","title":"Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12940","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":"sha256:4025bff2434e058421d5c0b9f06b3ca83b99310c42135ef83201d5ae4ddb25a8","target":"record","created_at":"2026-06-12T01:09:35Z","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":"3a4f9305312fdaf349d38d032809cfb6e4d635aed636b44d2a156be42cec05c1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-11T06:06:02Z","title_canon_sha256":"411394ffcb6e7454eacfc08c140d5b28f99e83d4fe511ccd06db1ee9ac6f140e"},"schema_version":"1.0","source":{"id":"2606.12940","kind":"arxiv","version":1}},"canonical_sha256":"a47c6fecd7260858a32b73417a0d0d22e2c28502398dbac13dc4c2313213127a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a47c6fecd7260858a32b73417a0d0d22e2c28502398dbac13dc4c2313213127a","first_computed_at":"2026-06-12T01:09:35.054103Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:09:35.054103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V1pezdQ7hng8RZ1O8tFOAVmWkv+hW6ba/h70lDADT67J0sPRBVhgPescjsi+wR5zkOSjP2Dw0Ro9p8BUi5GGBg==","signature_status":"signed_v1","signed_at":"2026-06-12T01:09:35.054505Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12940","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4025bff2434e058421d5c0b9f06b3ca83b99310c42135ef83201d5ae4ddb25a8","sha256:200aa71688e425afefcfa4f7cc52dd2bea4fabfe4643a24c39d3a9ed286a0094"],"state_sha256":"7b28d5f29f58e32941a09c6be3b1db594d86f1574b765d1c180249fe349e2dad"}