{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3LLCW3RU7OII42EK6VBWAAKECW","short_pith_number":"pith:3LLCW3RU","canonical_record":{"source":{"id":"2606.13095","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-11T09:25:14Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"91d6016943e15c5caae12ca4751860e199e6fdf7d0a09b3456c9682889d020e9","abstract_canon_sha256":"599ef2e1a0bd0739d3df75d8e2c4ac2035cacd1e5bdc3f2d6fe8e49d0f158225"},"schema_version":"1.0"},"canonical_sha256":"dad62b6e34fb908e688af54360014415ab662015aa1386bbb82838c64f05b579","source":{"kind":"arxiv","id":"2606.13095","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.13095","created_at":"2026-06-12T01:09:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.13095v1","created_at":"2026-06-12T01:09:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13095","created_at":"2026-06-12T01:09:39Z"},{"alias_kind":"pith_short_12","alias_value":"3LLCW3RU7OII","created_at":"2026-06-12T01:09:39Z"},{"alias_kind":"pith_short_16","alias_value":"3LLCW3RU7OII42EK","created_at":"2026-06-12T01:09:39Z"},{"alias_kind":"pith_short_8","alias_value":"3LLCW3RU","created_at":"2026-06-12T01:09:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3LLCW3RU7OII42EK6VBWAAKECW","target":"record","payload":{"canonical_record":{"source":{"id":"2606.13095","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-11T09:25:14Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"91d6016943e15c5caae12ca4751860e199e6fdf7d0a09b3456c9682889d020e9","abstract_canon_sha256":"599ef2e1a0bd0739d3df75d8e2c4ac2035cacd1e5bdc3f2d6fe8e49d0f158225"},"schema_version":"1.0"},"canonical_sha256":"dad62b6e34fb908e688af54360014415ab662015aa1386bbb82838c64f05b579","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:39.891747Z","signature_b64":"0dcd32rlPuiyQDt3sUKZrwWyZosJU0NAKMhN3wtyKkV63Gg9mh3t8QspQoW6q/sdrvvCtXug1xnBVu4lCFP6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dad62b6e34fb908e688af54360014415ab662015aa1386bbb82838c64f05b579","last_reissued_at":"2026-06-12T01:09:39.891110Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:39.891110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.13095","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":"2026-06-12T01:09:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qF6g7OvTJ3IIss4KWkHEbzKoXDJACx/MlWHgwyNzwmDiYjJsoW7gcYQL3sNSyhEB+s/FIneYWNnJiyvs4YvbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T16:57:12.106633Z"},"content_sha256":"e164748bf98e9763d25a7545e74a0b25d9248f15b9b8e27f22b137c990a18188","schema_version":"1.0","event_id":"sha256:e164748bf98e9763d25a7545e74a0b25d9248f15b9b8e27f22b137c990a18188"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3LLCW3RU7OII42EK6VBWAAKECW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Balancing ASR and diarization in end-to-end LLMs for multi-talker speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dandan Tu, Longshuai Xiao, Mengtian Li, Naijun Zheng, Sanli Tian, Yuke Lin, Zhiwei Lin","submitted_at":"2026-06-11T09:25:14Z","abstract_excerpt":"Multi-talker speech recognition is often addressed by combining automatic speech recognition (ASR) and speaker diarization in a pipeline system. Recently, LLM-based approaches have shown promise by jointly modeling semantic and speaker information, but they typically require large-scale multi-talker corpora that are costly to annotate. In this paper, we investigate how to efficiently train an LLM-based system with limited real-recorded data while maintaining high accuracy in speaker attribution. We propose several strategies: (1) a dual-encoder architecture to extract semantic and speaker feat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13095","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/2606.13095/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":"2026-06-12T01:09:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b/gbDD+QFbps9OHzW7A+uzaHlZcR/3/vNZkFMdnnQIx2itDl40CAKuDGITg4OvlD4d2KHdUO7cz2CD5HaTf7AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T16:57:12.107144Z"},"content_sha256":"7a101b74498a0d2ff6e92c231ab6be615c0ebbcdedc1efc1dff284528a3ecbf6","schema_version":"1.0","event_id":"sha256:7a101b74498a0d2ff6e92c231ab6be615c0ebbcdedc1efc1dff284528a3ecbf6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3LLCW3RU7OII42EK6VBWAAKECW/bundle.json","state_url":"https://pith.science/pith/3LLCW3RU7OII42EK6VBWAAKECW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3LLCW3RU7OII42EK6VBWAAKECW/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":"2026-06-30T16:57:12Z","links":{"resolver":"https://pith.science/pith/3LLCW3RU7OII42EK6VBWAAKECW","bundle":"https://pith.science/pith/3LLCW3RU7OII42EK6VBWAAKECW/bundle.json","state":"https://pith.science/pith/3LLCW3RU7OII42EK6VBWAAKECW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3LLCW3RU7OII42EK6VBWAAKECW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3LLCW3RU7OII42EK6VBWAAKECW","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":"599ef2e1a0bd0739d3df75d8e2c4ac2035cacd1e5bdc3f2d6fe8e49d0f158225","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-11T09:25:14Z","title_canon_sha256":"91d6016943e15c5caae12ca4751860e199e6fdf7d0a09b3456c9682889d020e9"},"schema_version":"1.0","source":{"id":"2606.13095","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.13095","created_at":"2026-06-12T01:09:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.13095v1","created_at":"2026-06-12T01:09:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13095","created_at":"2026-06-12T01:09:39Z"},{"alias_kind":"pith_short_12","alias_value":"3LLCW3RU7OII","created_at":"2026-06-12T01:09:39Z"},{"alias_kind":"pith_short_16","alias_value":"3LLCW3RU7OII42EK","created_at":"2026-06-12T01:09:39Z"},{"alias_kind":"pith_short_8","alias_value":"3LLCW3RU","created_at":"2026-06-12T01:09:39Z"}],"graph_snapshots":[{"event_id":"sha256:7a101b74498a0d2ff6e92c231ab6be615c0ebbcdedc1efc1dff284528a3ecbf6","target":"graph","created_at":"2026-06-12T01:09:39Z","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/2606.13095/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-talker speech recognition is often addressed by combining automatic speech recognition (ASR) and speaker diarization in a pipeline system. Recently, LLM-based approaches have shown promise by jointly modeling semantic and speaker information, but they typically require large-scale multi-talker corpora that are costly to annotate. In this paper, we investigate how to efficiently train an LLM-based system with limited real-recorded data while maintaining high accuracy in speaker attribution. We propose several strategies: (1) a dual-encoder architecture to extract semantic and speaker feat","authors_text":"Dandan Tu, Longshuai Xiao, Mengtian Li, Naijun Zheng, Sanli Tian, Yuke Lin, Zhiwei Lin","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-11T09:25:14Z","title":"Balancing ASR and diarization in end-to-end LLMs for multi-talker speech recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13095","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:e164748bf98e9763d25a7545e74a0b25d9248f15b9b8e27f22b137c990a18188","target":"record","created_at":"2026-06-12T01:09:39Z","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":"599ef2e1a0bd0739d3df75d8e2c4ac2035cacd1e5bdc3f2d6fe8e49d0f158225","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-11T09:25:14Z","title_canon_sha256":"91d6016943e15c5caae12ca4751860e199e6fdf7d0a09b3456c9682889d020e9"},"schema_version":"1.0","source":{"id":"2606.13095","kind":"arxiv","version":1}},"canonical_sha256":"dad62b6e34fb908e688af54360014415ab662015aa1386bbb82838c64f05b579","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dad62b6e34fb908e688af54360014415ab662015aa1386bbb82838c64f05b579","first_computed_at":"2026-06-12T01:09:39.891110Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:09:39.891110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0dcd32rlPuiyQDt3sUKZrwWyZosJU0NAKMhN3wtyKkV63Gg9mh3t8QspQoW6q/sdrvvCtXug1xnBVu4lCFP6DA==","signature_status":"signed_v1","signed_at":"2026-06-12T01:09:39.891747Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.13095","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e164748bf98e9763d25a7545e74a0b25d9248f15b9b8e27f22b137c990a18188","sha256:7a101b74498a0d2ff6e92c231ab6be615c0ebbcdedc1efc1dff284528a3ecbf6"],"state_sha256":"52549d02e01fc0919d1818c397f180872a5323cb1dfb776e3444b7b356b3dbd2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nZTi5wtR9tBYPoT+f3BLNhBE1HgGoD0L9WvI3rmwrDVQBuKkANBXMLXIQjPw2GVBRa4+2xeDUdtnJumYQJzdDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T16:57:12.109831Z","bundle_sha256":"b9d41cc74e418e98616405e66797beab17a7e923f22e2054732bf90dfca1ec9f"}}