{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SINRYP3HQYJ6Q32BWYTOZ7PJFN","short_pith_number":"pith:SINRYP3H","canonical_record":{"source":{"id":"1907.05337","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-09T00:23:22Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"23aea9c07bd725fa7422c91eccdc20b8bb1c3867c620403b44bb3ec3b5556a29","abstract_canon_sha256":"6d3696e880e4de03f95199d3ac2dc3ed07782568c071ea73ae72b136e0b0e2c8"},"schema_version":"1.0"},"canonical_sha256":"921b1c3f678613e86f41b626ecfde92b7af669e2ce256742216f379317f45d90","source":{"kind":"arxiv","id":"1907.05337","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.05337","created_at":"2026-05-17T23:40:50Z"},{"alias_kind":"arxiv_version","alias_value":"1907.05337v1","created_at":"2026-05-17T23:40:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05337","created_at":"2026-05-17T23:40:50Z"},{"alias_kind":"pith_short_12","alias_value":"SINRYP3HQYJ6","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SINRYP3HQYJ6Q32B","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SINRYP3H","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SINRYP3HQYJ6Q32BWYTOZ7PJFN","target":"record","payload":{"canonical_record":{"source":{"id":"1907.05337","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-09T00:23:22Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"23aea9c07bd725fa7422c91eccdc20b8bb1c3867c620403b44bb3ec3b5556a29","abstract_canon_sha256":"6d3696e880e4de03f95199d3ac2dc3ed07782568c071ea73ae72b136e0b0e2c8"},"schema_version":"1.0"},"canonical_sha256":"921b1c3f678613e86f41b626ecfde92b7af669e2ce256742216f379317f45d90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:50.679886Z","signature_b64":"qjiCzP3QJ3vMf45hWPOjGDE2MF+DWHbcorZ6GpOyyTTkvId8SasqfHIEM+pWSJCkJ+emC725UCLvqxErmoW+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"921b1c3f678613e86f41b626ecfde92b7af669e2ce256742216f379317f45d90","last_reissued_at":"2026-05-17T23:40:50.679208Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:50.679208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.05337","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":"2026-05-17T23:40:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cZyDW3oQ6jJ9jJVaqz1jPWjvbDVdEeqS/9gaGj4AMOLHzVTfzeR0l0lwybnqzSmVWJnM59gZ2qvNS1QIfNjvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:41:18.359982Z"},"content_sha256":"4389beb167ca1dc994b6d5e524e3ebc631ec4186d8041babbeafba599aa30f4e","schema_version":"1.0","event_id":"sha256:4389beb167ca1dc994b6d5e524e3ebc631ec4186d8041babbeafba599aa30f4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SINRYP3HQYJ6Q32BWYTOZ7PJFN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Joint Speech Recognition and Speaker Diarization via Sequence Transduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hagen Soltau, Izhak Shafran, Laurent El Shafey","submitted_at":"2019-07-09T00:23:22Z","abstract_excerpt":"Speech applications dealing with conversations require not only recognizing the spoken words, but also determining who spoke when. The task of assigning words to speakers is typically addressed by merging the outputs of two separate systems, namely, an automatic speech recognition (ASR) system and a speaker diarization (SD) system. The two systems are trained independently with different objective functions. Often the SD systems operate directly on the acoustics and are not constrained to respect word boundaries and this deficiency is overcome in an ad hoc manner. Motivated by recent advances "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.05337","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":""},"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":"2026-05-17T23:40:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"glToI7sY609YQzyKGj/TC/2l2jmfVGJPc+NZsTOGwyJ1D9cVpm9fnXtBqut/ND5NZwZqmHnZdwB0rjbx9QQiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:41:18.360641Z"},"content_sha256":"972bb19ef1d95b7ec02b7a995f007f898fda6c09c8a231a4c40d7a1ffecc1a87","schema_version":"1.0","event_id":"sha256:972bb19ef1d95b7ec02b7a995f007f898fda6c09c8a231a4c40d7a1ffecc1a87"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SINRYP3HQYJ6Q32BWYTOZ7PJFN/bundle.json","state_url":"https://pith.science/pith/SINRYP3HQYJ6Q32BWYTOZ7PJFN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SINRYP3HQYJ6Q32BWYTOZ7PJFN/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":"2026-05-25T16:41:18Z","links":{"resolver":"https://pith.science/pith/SINRYP3HQYJ6Q32BWYTOZ7PJFN","bundle":"https://pith.science/pith/SINRYP3HQYJ6Q32BWYTOZ7PJFN/bundle.json","state":"https://pith.science/pith/SINRYP3HQYJ6Q32BWYTOZ7PJFN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SINRYP3HQYJ6Q32BWYTOZ7PJFN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SINRYP3HQYJ6Q32BWYTOZ7PJFN","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":"6d3696e880e4de03f95199d3ac2dc3ed07782568c071ea73ae72b136e0b0e2c8","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-09T00:23:22Z","title_canon_sha256":"23aea9c07bd725fa7422c91eccdc20b8bb1c3867c620403b44bb3ec3b5556a29"},"schema_version":"1.0","source":{"id":"1907.05337","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.05337","created_at":"2026-05-17T23:40:50Z"},{"alias_kind":"arxiv_version","alias_value":"1907.05337v1","created_at":"2026-05-17T23:40:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05337","created_at":"2026-05-17T23:40:50Z"},{"alias_kind":"pith_short_12","alias_value":"SINRYP3HQYJ6","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SINRYP3HQYJ6Q32B","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SINRYP3H","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:972bb19ef1d95b7ec02b7a995f007f898fda6c09c8a231a4c40d7a1ffecc1a87","target":"graph","created_at":"2026-05-17T23:40:50Z","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"},"paper":{"abstract_excerpt":"Speech applications dealing with conversations require not only recognizing the spoken words, but also determining who spoke when. The task of assigning words to speakers is typically addressed by merging the outputs of two separate systems, namely, an automatic speech recognition (ASR) system and a speaker diarization (SD) system. The two systems are trained independently with different objective functions. Often the SD systems operate directly on the acoustics and are not constrained to respect word boundaries and this deficiency is overcome in an ad hoc manner. Motivated by recent advances ","authors_text":"Hagen Soltau, Izhak Shafran, Laurent El Shafey","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-09T00:23:22Z","title":"Joint Speech Recognition and Speaker Diarization via Sequence Transduction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.05337","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":"sha256:4389beb167ca1dc994b6d5e524e3ebc631ec4186d8041babbeafba599aa30f4e","target":"record","created_at":"2026-05-17T23:40:50Z","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":"6d3696e880e4de03f95199d3ac2dc3ed07782568c071ea73ae72b136e0b0e2c8","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-09T00:23:22Z","title_canon_sha256":"23aea9c07bd725fa7422c91eccdc20b8bb1c3867c620403b44bb3ec3b5556a29"},"schema_version":"1.0","source":{"id":"1907.05337","kind":"arxiv","version":1}},"canonical_sha256":"921b1c3f678613e86f41b626ecfde92b7af669e2ce256742216f379317f45d90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"921b1c3f678613e86f41b626ecfde92b7af669e2ce256742216f379317f45d90","first_computed_at":"2026-05-17T23:40:50.679208Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:50.679208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qjiCzP3QJ3vMf45hWPOjGDE2MF+DWHbcorZ6GpOyyTTkvId8SasqfHIEM+pWSJCkJ+emC725UCLvqxErmoW+CA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:50.679886Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.05337","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4389beb167ca1dc994b6d5e524e3ebc631ec4186d8041babbeafba599aa30f4e","sha256:972bb19ef1d95b7ec02b7a995f007f898fda6c09c8a231a4c40d7a1ffecc1a87"],"state_sha256":"feaaaa01795c67ed63a2810af5f3e20ff6084c676882d61b7cdd4ecec4c68a4d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2WrbCag2lZoLVyU1k3/jefi84pdVsl4bzRn+C59q+pYPnML2p48ewa6+D4F0dJqMe6GrkPXt72gkGu7Y5eHhAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T16:41:18.364545Z","bundle_sha256":"9768e146b367300f4c4f23cb07dc9bbf4dc0f360e14001ceb1e3079d18826992"}}