{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RC7AVQLN2R4V5ZQRDPMPVLEQGN","short_pith_number":"pith:RC7AVQLN","canonical_record":{"source":{"id":"2505.24496","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-30T11:47:29Z","cross_cats_sorted":[],"title_canon_sha256":"c0de1c932db804e7233f2ab23a4f960373bd314fd23a72e98c0f9e7d9b7bcdb5","abstract_canon_sha256":"213598f5a90338a76ef0ee9db4ac005dbcd3a2b60b86c04e50351ee5c74e6313"},"schema_version":"1.0"},"canonical_sha256":"88be0ac16dd4795ee6111bd8faac90334489d2c7e1a5ee0b58792b176e0d9846","source":{"kind":"arxiv","id":"2505.24496","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24496","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24496v1","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24496","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"pith_short_12","alias_value":"RC7AVQLN2R4V","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"pith_short_16","alias_value":"RC7AVQLN2R4V5ZQR","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"pith_short_8","alias_value":"RC7AVQLN","created_at":"2026-07-05T11:12:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RC7AVQLN2R4V5ZQRDPMPVLEQGN","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24496","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-30T11:47:29Z","cross_cats_sorted":[],"title_canon_sha256":"c0de1c932db804e7233f2ab23a4f960373bd314fd23a72e98c0f9e7d9b7bcdb5","abstract_canon_sha256":"213598f5a90338a76ef0ee9db4ac005dbcd3a2b60b86c04e50351ee5c74e6313"},"schema_version":"1.0"},"canonical_sha256":"88be0ac16dd4795ee6111bd8faac90334489d2c7e1a5ee0b58792b176e0d9846","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:51.127714Z","signature_b64":"vhQ387IMp3wCuV1b/wDmMBEQB8I5xZgOlcTZ20C1ZZgUyAF7J7PsPVgmd/XjLtLby5IBy6ReLX7w7lv3TKH0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88be0ac16dd4795ee6111bd8faac90334489d2c7e1a5ee0b58792b176e0d9846","last_reissued_at":"2026-07-05T11:12:51.127141Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:51.127141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24496","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":"2026-07-05T11:12:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z32H7S+EC0iD1vqOqU3zBYffYbYF21iULie+hRJ8UkGYN09PVQxq38kobUBwhHVJX9BXbM9qa1LtdofAuFZfAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:22:41.846159Z"},"content_sha256":"46580f2ab2590c4b717159862fcc302a94aa523b99763c5437dfc52168b5d303","schema_version":"1.0","event_id":"sha256:46580f2ab2590c4b717159862fcc302a94aa523b99763c5437dfc52168b5d303"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RC7AVQLN2R4V5ZQRDPMPVLEQGN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speech Token Prediction via Compressed-to-fine Language Modeling for Speech Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Bai Jionghao, Guanrou Yang, Jialong Zuo, Jin Xu, Minghui Fang, Qian Chen, Tao Jin, Weiqin Li, Wenrui Liu, Wen Wang, Xiaoda Yang, Yafeng Chen, Zemin Liu, Zhifang Guo","submitted_at":"2025-05-30T11:47:29Z","abstract_excerpt":"Neural audio codecs, used as speech tokenizers, have demonstrated remarkable potential in the field of speech generation. However, to ensure high-fidelity audio reconstruction, neural audio codecs typically encode audio into long sequences of speech tokens, posing a significant challenge for downstream language models in long-context modeling. We observe that speech token sequences exhibit short-range dependency: due to the monotonic alignment between text and speech in text-to-speech (TTS) tasks, the prediction of the current token primarily relies on its local context, while long-range token"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24496","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/2505.24496/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":"2026-07-05T11:12:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nEAvcDRZZmd9s9DKIdNsYeV0LfjymtRqqWpIs3x3KiEeH+2W7iWi4ne1IRNeXk2BUcbsp7rtwt40ElM44V0xDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:22:41.846729Z"},"content_sha256":"fdc72c9f3b5cd20f84e64e64cc2a8fea3ad1b5a60e01dba05a13eccdad4b2a23","schema_version":"1.0","event_id":"sha256:fdc72c9f3b5cd20f84e64e64cc2a8fea3ad1b5a60e01dba05a13eccdad4b2a23"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RC7AVQLN2R4V5ZQRDPMPVLEQGN/bundle.json","state_url":"https://pith.science/pith/RC7AVQLN2R4V5ZQRDPMPVLEQGN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RC7AVQLN2R4V5ZQRDPMPVLEQGN/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":"2026-08-08T07:22:41Z","links":{"resolver":"https://pith.science/pith/RC7AVQLN2R4V5ZQRDPMPVLEQGN","bundle":"https://pith.science/pith/RC7AVQLN2R4V5ZQRDPMPVLEQGN/bundle.json","state":"https://pith.science/pith/RC7AVQLN2R4V5ZQRDPMPVLEQGN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RC7AVQLN2R4V5ZQRDPMPVLEQGN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RC7AVQLN2R4V5ZQRDPMPVLEQGN","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":"213598f5a90338a76ef0ee9db4ac005dbcd3a2b60b86c04e50351ee5c74e6313","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-30T11:47:29Z","title_canon_sha256":"c0de1c932db804e7233f2ab23a4f960373bd314fd23a72e98c0f9e7d9b7bcdb5"},"schema_version":"1.0","source":{"id":"2505.24496","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24496","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24496v1","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24496","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"pith_short_12","alias_value":"RC7AVQLN2R4V","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"pith_short_16","alias_value":"RC7AVQLN2R4V5ZQR","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"pith_short_8","alias_value":"RC7AVQLN","created_at":"2026-07-05T11:12:51Z"}],"graph_snapshots":[{"event_id":"sha256:fdc72c9f3b5cd20f84e64e64cc2a8fea3ad1b5a60e01dba05a13eccdad4b2a23","target":"graph","created_at":"2026-07-05T11:12:51Z","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/2505.24496/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural audio codecs, used as speech tokenizers, have demonstrated remarkable potential in the field of speech generation. However, to ensure high-fidelity audio reconstruction, neural audio codecs typically encode audio into long sequences of speech tokens, posing a significant challenge for downstream language models in long-context modeling. We observe that speech token sequences exhibit short-range dependency: due to the monotonic alignment between text and speech in text-to-speech (TTS) tasks, the prediction of the current token primarily relies on its local context, while long-range token","authors_text":"Bai Jionghao, Guanrou Yang, Jialong Zuo, Jin Xu, Minghui Fang, Qian Chen, Tao Jin, Weiqin Li, Wenrui Liu, Wen Wang, Xiaoda Yang, Yafeng Chen, Zemin Liu, Zhifang Guo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-30T11:47:29Z","title":"Speech Token Prediction via Compressed-to-fine Language Modeling for Speech Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24496","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":"sha256:46580f2ab2590c4b717159862fcc302a94aa523b99763c5437dfc52168b5d303","target":"record","created_at":"2026-07-05T11:12:51Z","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":"213598f5a90338a76ef0ee9db4ac005dbcd3a2b60b86c04e50351ee5c74e6313","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-30T11:47:29Z","title_canon_sha256":"c0de1c932db804e7233f2ab23a4f960373bd314fd23a72e98c0f9e7d9b7bcdb5"},"schema_version":"1.0","source":{"id":"2505.24496","kind":"arxiv","version":1}},"canonical_sha256":"88be0ac16dd4795ee6111bd8faac90334489d2c7e1a5ee0b58792b176e0d9846","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88be0ac16dd4795ee6111bd8faac90334489d2c7e1a5ee0b58792b176e0d9846","first_computed_at":"2026-07-05T11:12:51.127141Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:51.127141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vhQ387IMp3wCuV1b/wDmMBEQB8I5xZgOlcTZ20C1ZZgUyAF7J7PsPVgmd/XjLtLby5IBy6ReLX7w7lv3TKH0CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:51.127714Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24496","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46580f2ab2590c4b717159862fcc302a94aa523b99763c5437dfc52168b5d303","sha256:fdc72c9f3b5cd20f84e64e64cc2a8fea3ad1b5a60e01dba05a13eccdad4b2a23"],"state_sha256":"97f4c5e61a3770cf0da3e553c5e2fad1364218caf68ec7785d450aa354591fa5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fCmgMN2ya4eF2Jgx1mcC1Ay6YNrUuA43Zco9hJAp5HtwNnp5/ZLMVX562YobtOXJVLBXZVrBhfMaddeFV3tHCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T07:22:41.851717Z","bundle_sha256":"ea583c0c70c1232df8631899e9a45e729565fa8e5d1e4ddab27b38500969b594"}}