{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Q7F553OJTY4LRRCOFNSA3NSELF","short_pith_number":"pith:Q7F553OJ","canonical_record":{"source":{"id":"2506.12672","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-15T00:37:27Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"aa49c591b788b7729f65ca6d5cad7bc7849766a9911593115b6107a04f474796","abstract_canon_sha256":"72902c90de161925172114e545bde2946b56e3aa1526f23b2f0d4d61cf7e1ada"},"schema_version":"1.0"},"canonical_sha256":"87cbdeedc99e38b8c44e2b640db6445952c860580a724b91e870f754d0ec09f6","source":{"kind":"arxiv","id":"2506.12672","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12672","created_at":"2026-07-05T11:21:57Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12672v1","created_at":"2026-07-05T11:21:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12672","created_at":"2026-07-05T11:21:57Z"},{"alias_kind":"pith_short_12","alias_value":"Q7F553OJTY4L","created_at":"2026-07-05T11:21:57Z"},{"alias_kind":"pith_short_16","alias_value":"Q7F553OJTY4LRRCO","created_at":"2026-07-05T11:21:57Z"},{"alias_kind":"pith_short_8","alias_value":"Q7F553OJ","created_at":"2026-07-05T11:21:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Q7F553OJTY4LRRCOFNSA3NSELF","target":"record","payload":{"canonical_record":{"source":{"id":"2506.12672","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-15T00:37:27Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"aa49c591b788b7729f65ca6d5cad7bc7849766a9911593115b6107a04f474796","abstract_canon_sha256":"72902c90de161925172114e545bde2946b56e3aa1526f23b2f0d4d61cf7e1ada"},"schema_version":"1.0"},"canonical_sha256":"87cbdeedc99e38b8c44e2b640db6445952c860580a724b91e870f754d0ec09f6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:57.235034Z","signature_b64":"0iP9cRQ4RV8/mtiP3z3fjSogk6xZK8mxvpabmy0PpOFO+iNsMLBFwjd/zh6lcmW3gJZEN7aErnrMDVNOBceHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87cbdeedc99e38b8c44e2b640db6445952c860580a724b91e870f754d0ec09f6","last_reissued_at":"2026-07-05T11:21:57.234609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:57.234609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.12672","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":"2026-07-05T11:21:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yvz9N1M/46diqxqrCliOQVA/2m22VhzsgUoP0FZ6bJBY6WRyEXjqwMCAe74nC9D8BQ1da1N11tNSnYmTZoVCCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:18:21.497395Z"},"content_sha256":"6099c1c965485215dd6bff68310d3385310ee011f5fe3d50b46068256bbb15ef","schema_version":"1.0","event_id":"sha256:6099c1c965485215dd6bff68310d3385310ee011f5fe3d50b46068256bbb15ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Q7F553OJTY4LRRCOFNSA3NSELF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SC-SOT: Conditioning the Decoder on Diarized Speaker Information for End-to-End Overlapped Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Sakriani Sakti, Yuta Hirano","submitted_at":"2025-06-15T00:37:27Z","abstract_excerpt":"We propose Speaker-Conditioned Serialized Output Training (SC-SOT), an enhanced SOT-based training for E2E multi-talker ASR. We first probe how SOT handles overlapped speech, and we found the decoder performs implicit speaker separation. We hypothesize this implicit separation is often insufficient due to ambiguous acoustic cues in overlapping regions. To address this, SC-SOT explicitly conditions the decoder on speaker information, providing detailed information about \"who spoke when\". Specifically, we enhance the decoder by incorporating: (1) speaker embeddings, which allow the model to focu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12672","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/2506.12672/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":"2026-07-05T11:21:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cXpjbZNMWNCpixma0KJZ3EZbejxczeg97/axnFKG6MQhV3qB+9XY0I81SATbZ9mxnmb02GeJlo8+ZwCz0qOcAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:18:21.497892Z"},"content_sha256":"d89a41bb9b1587c85a8ecb7f08e45fdd6b1cddc991106eb009a02ef97652d12f","schema_version":"1.0","event_id":"sha256:d89a41bb9b1587c85a8ecb7f08e45fdd6b1cddc991106eb009a02ef97652d12f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q7F553OJTY4LRRCOFNSA3NSELF/bundle.json","state_url":"https://pith.science/pith/Q7F553OJTY4LRRCOFNSA3NSELF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q7F553OJTY4LRRCOFNSA3NSELF/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":"2026-08-09T22:18:21Z","links":{"resolver":"https://pith.science/pith/Q7F553OJTY4LRRCOFNSA3NSELF","bundle":"https://pith.science/pith/Q7F553OJTY4LRRCOFNSA3NSELF/bundle.json","state":"https://pith.science/pith/Q7F553OJTY4LRRCOFNSA3NSELF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q7F553OJTY4LRRCOFNSA3NSELF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Q7F553OJTY4LRRCOFNSA3NSELF","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":"72902c90de161925172114e545bde2946b56e3aa1526f23b2f0d4d61cf7e1ada","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-15T00:37:27Z","title_canon_sha256":"aa49c591b788b7729f65ca6d5cad7bc7849766a9911593115b6107a04f474796"},"schema_version":"1.0","source":{"id":"2506.12672","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12672","created_at":"2026-07-05T11:21:57Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12672v1","created_at":"2026-07-05T11:21:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12672","created_at":"2026-07-05T11:21:57Z"},{"alias_kind":"pith_short_12","alias_value":"Q7F553OJTY4L","created_at":"2026-07-05T11:21:57Z"},{"alias_kind":"pith_short_16","alias_value":"Q7F553OJTY4LRRCO","created_at":"2026-07-05T11:21:57Z"},{"alias_kind":"pith_short_8","alias_value":"Q7F553OJ","created_at":"2026-07-05T11:21:57Z"}],"graph_snapshots":[{"event_id":"sha256:d89a41bb9b1587c85a8ecb7f08e45fdd6b1cddc991106eb009a02ef97652d12f","target":"graph","created_at":"2026-07-05T11:21:57Z","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/2506.12672/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Speaker-Conditioned Serialized Output Training (SC-SOT), an enhanced SOT-based training for E2E multi-talker ASR. We first probe how SOT handles overlapped speech, and we found the decoder performs implicit speaker separation. We hypothesize this implicit separation is often insufficient due to ambiguous acoustic cues in overlapping regions. To address this, SC-SOT explicitly conditions the decoder on speaker information, providing detailed information about \"who spoke when\". Specifically, we enhance the decoder by incorporating: (1) speaker embeddings, which allow the model to focu","authors_text":"Sakriani Sakti, Yuta Hirano","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-15T00:37:27Z","title":"SC-SOT: Conditioning the Decoder on Diarized Speaker Information for End-to-End Overlapped Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12672","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":"sha256:6099c1c965485215dd6bff68310d3385310ee011f5fe3d50b46068256bbb15ef","target":"record","created_at":"2026-07-05T11:21:57Z","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":"72902c90de161925172114e545bde2946b56e3aa1526f23b2f0d4d61cf7e1ada","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-15T00:37:27Z","title_canon_sha256":"aa49c591b788b7729f65ca6d5cad7bc7849766a9911593115b6107a04f474796"},"schema_version":"1.0","source":{"id":"2506.12672","kind":"arxiv","version":1}},"canonical_sha256":"87cbdeedc99e38b8c44e2b640db6445952c860580a724b91e870f754d0ec09f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87cbdeedc99e38b8c44e2b640db6445952c860580a724b91e870f754d0ec09f6","first_computed_at":"2026-07-05T11:21:57.234609Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:57.234609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0iP9cRQ4RV8/mtiP3z3fjSogk6xZK8mxvpabmy0PpOFO+iNsMLBFwjd/zh6lcmW3gJZEN7aErnrMDVNOBceHAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:57.235034Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12672","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6099c1c965485215dd6bff68310d3385310ee011f5fe3d50b46068256bbb15ef","sha256:d89a41bb9b1587c85a8ecb7f08e45fdd6b1cddc991106eb009a02ef97652d12f"],"state_sha256":"0bfc82f9ddc5d5a66cc8e52a53f687b6c902c2359d1f4e81a3a78a5e810e5121"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TnGox2xlrdalasGQxWhjasizKohBOx0saVQUy8EWNfMIUinNj3Q66lQouKhkMxkVga1SrjPYe80VBnobI2pCCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:18:21.501401Z","bundle_sha256":"2007d788b82d1d68ccec311894cac874affff813de305dc21cbba7de400d8107"}}