{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PEKFZF36455P4Q3ZQMZORMENUK","short_pith_number":"pith:PEKFZF36","canonical_record":{"source":{"id":"2408.06474","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-12T20:19:27Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"188c86486167fd45c0ec21ec5a2e715565236d62e4acd2bd187fc62be81036fe","abstract_canon_sha256":"ff741f4b9cf4842d6dc833ec00f0888d1070de07599181f5e4429c4c1332b57f"},"schema_version":"1.0"},"canonical_sha256":"79145c977ee77afe43798332e8b08da2bb44df44a221a7694f8eb3bd443626a4","source":{"kind":"arxiv","id":"2408.06474","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06474","created_at":"2026-07-05T08:54:57Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06474v1","created_at":"2026-07-05T08:54:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06474","created_at":"2026-07-05T08:54:57Z"},{"alias_kind":"pith_short_12","alias_value":"PEKFZF36455P","created_at":"2026-07-05T08:54:57Z"},{"alias_kind":"pith_short_16","alias_value":"PEKFZF36455P4Q3Z","created_at":"2026-07-05T08:54:57Z"},{"alias_kind":"pith_short_8","alias_value":"PEKFZF36","created_at":"2026-07-05T08:54:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PEKFZF36455P4Q3ZQMZORMENUK","target":"record","payload":{"canonical_record":{"source":{"id":"2408.06474","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-12T20:19:27Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"188c86486167fd45c0ec21ec5a2e715565236d62e4acd2bd187fc62be81036fe","abstract_canon_sha256":"ff741f4b9cf4842d6dc833ec00f0888d1070de07599181f5e4429c4c1332b57f"},"schema_version":"1.0"},"canonical_sha256":"79145c977ee77afe43798332e8b08da2bb44df44a221a7694f8eb3bd443626a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:57.444032Z","signature_b64":"1yAtF3UQiVYhaN1KvA3R2FiWKvrMnwV4vV9d3dkBH6NogOfPW8i734wHWQUX+NYxWinnIep/OYwr0UOYd/OzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79145c977ee77afe43798332e8b08da2bb44df44a221a7694f8eb3bd443626a4","last_reissued_at":"2026-07-05T08:54:57.443599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:57.443599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.06474","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":"2026-07-05T08:54:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZB119vdDNfRj5821a9DBXAXZfMl4GKx4QoYHyU6SZhz1dGwrTi/UZFP710Oe5dgbHpI3iO3V7ZQXFd9WJotTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:54:57.233364Z"},"content_sha256":"08726c76e2b4304ad670612ca9ebc05510ed377b21744a68b0d7e729c91d40f1","schema_version":"1.0","event_id":"sha256:08726c76e2b4304ad670612ca9ebc05510ed377b21744a68b0d7e729c91d40f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PEKFZF36455P4Q3ZQMZORMENUK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TOGGL: Transcribing Overlapping Speech with Staggered Labeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chak-Fai Li, Matthew Snover, William Hartmann","submitted_at":"2024-08-12T20:19:27Z","abstract_excerpt":"Transcribing the speech of multiple overlapping speakers typically requires separating the audio into multiple streams and recognizing each one independently. More recent work jointly separates and transcribes, but requires a separate decoding component for each speaker. We propose the TOGGL model to simultaneously transcribe the speech of multiple speakers. The TOGGL model uses special output tokens to attribute the speech to each speaker with only a single decoder. Our approach generalizes beyond two speakers, even when trained only on two-speaker data. We demonstrate superior performance co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06474","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/2408.06474/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":"2026-07-05T08:54:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YVt6I7WpfI4hy90cd2koZwPubYmncWmwLaGV/e3kog0jgK4tspfExgykoyvlBCJmO81/4ZFVFIYX8L0q7Oi4Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:54:57.233891Z"},"content_sha256":"b8361811fe689371c5ecaf37b648b5bc65f4db89977064a1f5ed377b121b04fb","schema_version":"1.0","event_id":"sha256:b8361811fe689371c5ecaf37b648b5bc65f4db89977064a1f5ed377b121b04fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PEKFZF36455P4Q3ZQMZORMENUK/bundle.json","state_url":"https://pith.science/pith/PEKFZF36455P4Q3ZQMZORMENUK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PEKFZF36455P4Q3ZQMZORMENUK/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":"2026-08-15T17:54:57Z","links":{"resolver":"https://pith.science/pith/PEKFZF36455P4Q3ZQMZORMENUK","bundle":"https://pith.science/pith/PEKFZF36455P4Q3ZQMZORMENUK/bundle.json","state":"https://pith.science/pith/PEKFZF36455P4Q3ZQMZORMENUK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PEKFZF36455P4Q3ZQMZORMENUK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PEKFZF36455P4Q3ZQMZORMENUK","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":"ff741f4b9cf4842d6dc833ec00f0888d1070de07599181f5e4429c4c1332b57f","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-12T20:19:27Z","title_canon_sha256":"188c86486167fd45c0ec21ec5a2e715565236d62e4acd2bd187fc62be81036fe"},"schema_version":"1.0","source":{"id":"2408.06474","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06474","created_at":"2026-07-05T08:54:57Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06474v1","created_at":"2026-07-05T08:54:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06474","created_at":"2026-07-05T08:54:57Z"},{"alias_kind":"pith_short_12","alias_value":"PEKFZF36455P","created_at":"2026-07-05T08:54:57Z"},{"alias_kind":"pith_short_16","alias_value":"PEKFZF36455P4Q3Z","created_at":"2026-07-05T08:54:57Z"},{"alias_kind":"pith_short_8","alias_value":"PEKFZF36","created_at":"2026-07-05T08:54:57Z"}],"graph_snapshots":[{"event_id":"sha256:b8361811fe689371c5ecaf37b648b5bc65f4db89977064a1f5ed377b121b04fb","target":"graph","created_at":"2026-07-05T08:54:57Z","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/2408.06474/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transcribing the speech of multiple overlapping speakers typically requires separating the audio into multiple streams and recognizing each one independently. More recent work jointly separates and transcribes, but requires a separate decoding component for each speaker. We propose the TOGGL model to simultaneously transcribe the speech of multiple speakers. The TOGGL model uses special output tokens to attribute the speech to each speaker with only a single decoder. Our approach generalizes beyond two speakers, even when trained only on two-speaker data. We demonstrate superior performance co","authors_text":"Chak-Fai Li, Matthew Snover, William Hartmann","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-12T20:19:27Z","title":"TOGGL: Transcribing Overlapping Speech with Staggered Labeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06474","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":"sha256:08726c76e2b4304ad670612ca9ebc05510ed377b21744a68b0d7e729c91d40f1","target":"record","created_at":"2026-07-05T08:54:57Z","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":"ff741f4b9cf4842d6dc833ec00f0888d1070de07599181f5e4429c4c1332b57f","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-12T20:19:27Z","title_canon_sha256":"188c86486167fd45c0ec21ec5a2e715565236d62e4acd2bd187fc62be81036fe"},"schema_version":"1.0","source":{"id":"2408.06474","kind":"arxiv","version":1}},"canonical_sha256":"79145c977ee77afe43798332e8b08da2bb44df44a221a7694f8eb3bd443626a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79145c977ee77afe43798332e8b08da2bb44df44a221a7694f8eb3bd443626a4","first_computed_at":"2026-07-05T08:54:57.443599Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:54:57.443599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1yAtF3UQiVYhaN1KvA3R2FiWKvrMnwV4vV9d3dkBH6NogOfPW8i734wHWQUX+NYxWinnIep/OYwr0UOYd/OzAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:54:57.444032Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.06474","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08726c76e2b4304ad670612ca9ebc05510ed377b21744a68b0d7e729c91d40f1","sha256:b8361811fe689371c5ecaf37b648b5bc65f4db89977064a1f5ed377b121b04fb"],"state_sha256":"7b3b2345e3027cacec0d4b6000372e24f44979996f6a0385a84468be9a22853f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"46jZGl5AoWMtqLGJvRIqQ4fnMyrYzMciPuiN7qKYDt966XzQODpiAvu3LxxOrA0zIU3huS+Bon2hRpdAjJN2CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T17:54:57.237241Z","bundle_sha256":"9c338b5b918356ac8e55fc45d5a7d9fd550a6253b16a176cd9c84d10535842b2"}}