{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6URWBCXS3WRRR7RPPQR4US56A3","short_pith_number":"pith:6URWBCXS","canonical_record":{"source":{"id":"2306.16398","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-28T17:44:30Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"3e33f538fc2a82f197f519abe8d6d27191da430e9e927e166a2763872b8995b2","abstract_canon_sha256":"b0af337daec52025774b939ead39a49f09995fdb81613dd4a5ea46861e86433b"},"schema_version":"1.0"},"canonical_sha256":"f523608af2dda318fe2f7c23ca4bbe06f78a84db3758fb82c66a12e511eeec37","source":{"kind":"arxiv","id":"2306.16398","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.16398","created_at":"2026-07-05T06:25:55Z"},{"alias_kind":"arxiv_version","alias_value":"2306.16398v1","created_at":"2026-07-05T06:25:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.16398","created_at":"2026-07-05T06:25:55Z"},{"alias_kind":"pith_short_12","alias_value":"6URWBCXS3WRR","created_at":"2026-07-05T06:25:55Z"},{"alias_kind":"pith_short_16","alias_value":"6URWBCXS3WRRR7RP","created_at":"2026-07-05T06:25:55Z"},{"alias_kind":"pith_short_8","alias_value":"6URWBCXS","created_at":"2026-07-05T06:25:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6URWBCXS3WRRR7RPPQR4US56A3","target":"record","payload":{"canonical_record":{"source":{"id":"2306.16398","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-28T17:44:30Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"3e33f538fc2a82f197f519abe8d6d27191da430e9e927e166a2763872b8995b2","abstract_canon_sha256":"b0af337daec52025774b939ead39a49f09995fdb81613dd4a5ea46861e86433b"},"schema_version":"1.0"},"canonical_sha256":"f523608af2dda318fe2f7c23ca4bbe06f78a84db3758fb82c66a12e511eeec37","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:25:55.670356Z","signature_b64":"t/gAxx2AHGyfpDtDZkF0U8gmD7HTc2Ay90tQFkL3ripZ8YS2OyWNJdVrwk3l0pytOgahVfdDNxXpqIpPsEhmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f523608af2dda318fe2f7c23ca4bbe06f78a84db3758fb82c66a12e511eeec37","last_reissued_at":"2026-07-05T06:25:55.669880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:25:55.669880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.16398","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":"2026-07-05T06:25:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SoFes1gC5tb5plWZXOTdZqbuKVSRktpg5i0nnCOtolv/HthQrDXeGxMTrvBVafqGWf6GbtwsEVBUZ2Uki/v/Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:09:54.844492Z"},"content_sha256":"a15ab60bad39137234fae644de0c8b15641517d8205938b7c025ef16b8337ba3","schema_version":"1.0","event_id":"sha256:a15ab60bad39137234fae644de0c8b15641517d8205938b7c025ef16b8337ba3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6URWBCXS3WRRR7RPPQR4US56A3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cascaded encoders for fine-tuning ASR models on overlapped speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Olivier Siohan, Oscar Chang, Richard Rose","submitted_at":"2023-06-28T17:44:30Z","abstract_excerpt":"Multi-talker speech recognition (MT-ASR) has been shown to improve ASR performance on speech containing overlapping utterances from more than one speaker. Multi-talker models have typically been trained from scratch using simulated or actual overlapping speech datasets. On the other hand, the trend in ASR has been to train foundation models using massive datasets collected from a wide variety of task domains. Given the scale of these models and their ability to generalize well across a variety of domains, it makes sense to consider scenarios where a foundation model is augmented with multi-tal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.16398","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/2306.16398/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":"2026-07-05T06:25:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"57t1kVXsSrXlX9KydFrJq4Ou3EH4vsDhtaOBLeY2zxdKPtdtHKcBpl+QGng5K6veeIwG10Cy0x7/HA1g/VYBBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:09:54.845424Z"},"content_sha256":"b4e89dff5f53d413d4fe76d7867a3d3bb2433b52ebff5ccc7273b5dcf4963066","schema_version":"1.0","event_id":"sha256:b4e89dff5f53d413d4fe76d7867a3d3bb2433b52ebff5ccc7273b5dcf4963066"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6URWBCXS3WRRR7RPPQR4US56A3/bundle.json","state_url":"https://pith.science/pith/6URWBCXS3WRRR7RPPQR4US56A3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6URWBCXS3WRRR7RPPQR4US56A3/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":"2026-08-17T22:09:54Z","links":{"resolver":"https://pith.science/pith/6URWBCXS3WRRR7RPPQR4US56A3","bundle":"https://pith.science/pith/6URWBCXS3WRRR7RPPQR4US56A3/bundle.json","state":"https://pith.science/pith/6URWBCXS3WRRR7RPPQR4US56A3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6URWBCXS3WRRR7RPPQR4US56A3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6URWBCXS3WRRR7RPPQR4US56A3","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":"b0af337daec52025774b939ead39a49f09995fdb81613dd4a5ea46861e86433b","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-28T17:44:30Z","title_canon_sha256":"3e33f538fc2a82f197f519abe8d6d27191da430e9e927e166a2763872b8995b2"},"schema_version":"1.0","source":{"id":"2306.16398","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.16398","created_at":"2026-07-05T06:25:55Z"},{"alias_kind":"arxiv_version","alias_value":"2306.16398v1","created_at":"2026-07-05T06:25:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.16398","created_at":"2026-07-05T06:25:55Z"},{"alias_kind":"pith_short_12","alias_value":"6URWBCXS3WRR","created_at":"2026-07-05T06:25:55Z"},{"alias_kind":"pith_short_16","alias_value":"6URWBCXS3WRRR7RP","created_at":"2026-07-05T06:25:55Z"},{"alias_kind":"pith_short_8","alias_value":"6URWBCXS","created_at":"2026-07-05T06:25:55Z"}],"graph_snapshots":[{"event_id":"sha256:b4e89dff5f53d413d4fe76d7867a3d3bb2433b52ebff5ccc7273b5dcf4963066","target":"graph","created_at":"2026-07-05T06:25:55Z","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/2306.16398/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-talker speech recognition (MT-ASR) has been shown to improve ASR performance on speech containing overlapping utterances from more than one speaker. Multi-talker models have typically been trained from scratch using simulated or actual overlapping speech datasets. On the other hand, the trend in ASR has been to train foundation models using massive datasets collected from a wide variety of task domains. Given the scale of these models and their ability to generalize well across a variety of domains, it makes sense to consider scenarios where a foundation model is augmented with multi-tal","authors_text":"Olivier Siohan, Oscar Chang, Richard Rose","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-28T17:44:30Z","title":"Cascaded encoders for fine-tuning ASR models on overlapped speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.16398","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:a15ab60bad39137234fae644de0c8b15641517d8205938b7c025ef16b8337ba3","target":"record","created_at":"2026-07-05T06:25:55Z","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":"b0af337daec52025774b939ead39a49f09995fdb81613dd4a5ea46861e86433b","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-28T17:44:30Z","title_canon_sha256":"3e33f538fc2a82f197f519abe8d6d27191da430e9e927e166a2763872b8995b2"},"schema_version":"1.0","source":{"id":"2306.16398","kind":"arxiv","version":1}},"canonical_sha256":"f523608af2dda318fe2f7c23ca4bbe06f78a84db3758fb82c66a12e511eeec37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f523608af2dda318fe2f7c23ca4bbe06f78a84db3758fb82c66a12e511eeec37","first_computed_at":"2026-07-05T06:25:55.669880Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:25:55.669880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t/gAxx2AHGyfpDtDZkF0U8gmD7HTc2Ay90tQFkL3ripZ8YS2OyWNJdVrwk3l0pytOgahVfdDNxXpqIpPsEhmCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:25:55.670356Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.16398","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a15ab60bad39137234fae644de0c8b15641517d8205938b7c025ef16b8337ba3","sha256:b4e89dff5f53d413d4fe76d7867a3d3bb2433b52ebff5ccc7273b5dcf4963066"],"state_sha256":"b11336848eccd9153ffbbedf10b1b9101c165e04a34732a57466ff606c30a2f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B8vFChEFYyjylLHp5ioPSSHhvHzkjXzLHEeVUiwee1NVLzs0IzruVWkPtR+z/JRcQRuhxoo43OML02X4va9oBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T22:09:54.851397Z","bundle_sha256":"a6e810e63e73cd9060ce1f99868315bcf02c00a504309a045d94eea610901aff"}}