{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:STOSFASJOV4MMSUBO7G3V3VXI2","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":"05d27527b394dca938bbc810568f38200713c06f7fdde6e465377be755acdc3d","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-11-12T07:30:29Z","title_canon_sha256":"2fd2ca08170e400bd67d7d8f00bfbba9c6aa2bd23ed217e12a7502ec00131a56"},"schema_version":"1.0","source":{"id":"2411.07607","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07607","created_at":"2026-07-05T09:56:02Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07607v2","created_at":"2026-07-05T09:56:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07607","created_at":"2026-07-05T09:56:02Z"},{"alias_kind":"pith_short_12","alias_value":"STOSFASJOV4M","created_at":"2026-07-05T09:56:02Z"},{"alias_kind":"pith_short_16","alias_value":"STOSFASJOV4MMSUB","created_at":"2026-07-05T09:56:02Z"},{"alias_kind":"pith_short_8","alias_value":"STOSFASJ","created_at":"2026-07-05T09:56:02Z"}],"graph_snapshots":[{"event_id":"sha256:5978e39b4bce958d83d59bf376281359b38ee3ec2fd6f76b2f229e4257f28a77","target":"graph","created_at":"2026-07-05T09:56:02Z","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/2411.07607/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"CTC compressor can be an effective approach to integrate audio encoders to decoder-only models, which has gained growing interest for different speech applications. In this work, we propose a novel CTC compressor based joint speech and text training (CJST) framework for decoder-only ASR. CJST matches speech and text modalities from both directions by exploring a simple modality adaptor and several features of the CTC compressor, including sequence compression, on-the-fly forced peaky alignment and CTC class embeddings. Experimental results on the Librispeech and TED-LIUM2 corpora show that the","authors_text":"Jay Mahadeokar, Junteng Jia, Leda Sari, Ozlem Kalinli, Wei Zhou","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-11-12T07:30:29Z","title":"CJST: CTC Compressor based Joint Speech and Text Training for Decoder-Only ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07607","kind":"arxiv","version":2},"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":"sha256:35367249ab3d60a889da91e11c87f704d8941ce9843ea9f01b150e364f1e0503","target":"record","created_at":"2026-07-05T09:56:02Z","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":"05d27527b394dca938bbc810568f38200713c06f7fdde6e465377be755acdc3d","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-11-12T07:30:29Z","title_canon_sha256":"2fd2ca08170e400bd67d7d8f00bfbba9c6aa2bd23ed217e12a7502ec00131a56"},"schema_version":"1.0","source":{"id":"2411.07607","kind":"arxiv","version":2}},"canonical_sha256":"94dd2282497578c64a8177cdbaeeb7468fd4162e9c52e4cffcfbbc740f32df39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94dd2282497578c64a8177cdbaeeb7468fd4162e9c52e4cffcfbbc740f32df39","first_computed_at":"2026-07-05T09:56:02.295428Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:02.295428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vj+Vkai6ubbQGtbyBlM4RjL4GIXkbmm6UumD4G9HQPW84agmFgswufXF9Zp8KhRBSl+r6UEZuWogZbkrufj2CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:02.296018Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.07607","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35367249ab3d60a889da91e11c87f704d8941ce9843ea9f01b150e364f1e0503","sha256:5978e39b4bce958d83d59bf376281359b38ee3ec2fd6f76b2f229e4257f28a77"],"state_sha256":"68af8d4c4a94e21e1a84bfba364a0755b829a1955a3046968b884bb2b51899fd"}