{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OVQSJZ72X2KBCAOG4K5MZNSGQO","short_pith_number":"pith:OVQSJZ72","canonical_record":{"source":{"id":"2309.11384","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-20T15:10:12Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"9d85d1e75d33dc3f4efd9d66e7e10420409238c2ba5a6a4f1b898ad3d801911c","abstract_canon_sha256":"8300c4ae00f010b320e6fb1aed1d413c2384e9640a8e1b37b594e8010fbff724"},"schema_version":"1.0"},"canonical_sha256":"756124e7fabe941101c6e2baccb6468386dd1211bd33a7cedd8a76d246ecd6a8","source":{"kind":"arxiv","id":"2309.11384","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.11384","created_at":"2026-07-05T09:25:33Z"},{"alias_kind":"arxiv_version","alias_value":"2309.11384v1","created_at":"2026-07-05T09:25:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11384","created_at":"2026-07-05T09:25:33Z"},{"alias_kind":"pith_short_12","alias_value":"OVQSJZ72X2KB","created_at":"2026-07-05T09:25:33Z"},{"alias_kind":"pith_short_16","alias_value":"OVQSJZ72X2KBCAOG","created_at":"2026-07-05T09:25:33Z"},{"alias_kind":"pith_short_8","alias_value":"OVQSJZ72","created_at":"2026-07-05T09:25:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OVQSJZ72X2KBCAOG4K5MZNSGQO","target":"record","payload":{"canonical_record":{"source":{"id":"2309.11384","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-20T15:10:12Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"9d85d1e75d33dc3f4efd9d66e7e10420409238c2ba5a6a4f1b898ad3d801911c","abstract_canon_sha256":"8300c4ae00f010b320e6fb1aed1d413c2384e9640a8e1b37b594e8010fbff724"},"schema_version":"1.0"},"canonical_sha256":"756124e7fabe941101c6e2baccb6468386dd1211bd33a7cedd8a76d246ecd6a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:33.618504Z","signature_b64":"QeX54R0BgATaS1MdplIai6nc6G6WkQ7GxoV+WvKqGkZzBi/Jfo2QIZMj5yLfvP/X3fynFA1BS6euQ0rGCA0OCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"756124e7fabe941101c6e2baccb6468386dd1211bd33a7cedd8a76d246ecd6a8","last_reissued_at":"2026-07-05T09:25:33.617981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:33.617981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.11384","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":"2026-07-05T09:25:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ar3C9IfbC7c2Z37EoS9emlSi3RZsQwCI0e/p934TJgmpPkjb6Kj6epPJ29fmhbINRiSLciRyDujA+s7oCIJaCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T23:44:43.422842Z"},"content_sha256":"e6be133efe05ba7815d64e805c3c0302eb1e58bb96de2e74ac441017af95feb4","schema_version":"1.0","event_id":"sha256:e6be133efe05ba7815d64e805c3c0302eb1e58bb96de2e74ac441017af95feb4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OVQSJZ72X2KBCAOG4K5MZNSGQO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Long-Form End-to-End Speech Translation via Latent Alignment Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ond\\v{r}ej Bojar, Peter Pol\\'ak","submitted_at":"2023-09-20T15:10:12Z","abstract_excerpt":"Current simultaneous speech translation models can process audio only up to a few seconds long. Contemporary datasets provide an oracle segmentation into sentences based on human-annotated transcripts and translations. However, the segmentation into sentences is not available in the real world. Current speech segmentation approaches either offer poor segmentation quality or have to trade latency for quality. In this paper, we propose a novel segmentation approach for a low-latency end-to-end speech translation. We leverage the existing speech translation encoder-decoder architecture with ST CT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11384","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/2309.11384/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":"2026-07-05T09:25:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4+rOew31rF91uGsbcV4oAmfgjatwUtrmj65Cv6tpGIl1hu8JtdlX+fTjCxcV9kDJWmMXD01kNcYNEKpm7LPmDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T23:44:43.423136Z"},"content_sha256":"68ad4941403383025b5da7481903e0e1204a1b04b0761668fd5a0f87dd9294df","schema_version":"1.0","event_id":"sha256:68ad4941403383025b5da7481903e0e1204a1b04b0761668fd5a0f87dd9294df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OVQSJZ72X2KBCAOG4K5MZNSGQO/bundle.json","state_url":"https://pith.science/pith/OVQSJZ72X2KBCAOG4K5MZNSGQO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OVQSJZ72X2KBCAOG4K5MZNSGQO/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":"2026-07-31T23:44:43Z","links":{"resolver":"https://pith.science/pith/OVQSJZ72X2KBCAOG4K5MZNSGQO","bundle":"https://pith.science/pith/OVQSJZ72X2KBCAOG4K5MZNSGQO/bundle.json","state":"https://pith.science/pith/OVQSJZ72X2KBCAOG4K5MZNSGQO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OVQSJZ72X2KBCAOG4K5MZNSGQO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OVQSJZ72X2KBCAOG4K5MZNSGQO","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":"8300c4ae00f010b320e6fb1aed1d413c2384e9640a8e1b37b594e8010fbff724","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-20T15:10:12Z","title_canon_sha256":"9d85d1e75d33dc3f4efd9d66e7e10420409238c2ba5a6a4f1b898ad3d801911c"},"schema_version":"1.0","source":{"id":"2309.11384","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.11384","created_at":"2026-07-05T09:25:33Z"},{"alias_kind":"arxiv_version","alias_value":"2309.11384v1","created_at":"2026-07-05T09:25:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11384","created_at":"2026-07-05T09:25:33Z"},{"alias_kind":"pith_short_12","alias_value":"OVQSJZ72X2KB","created_at":"2026-07-05T09:25:33Z"},{"alias_kind":"pith_short_16","alias_value":"OVQSJZ72X2KBCAOG","created_at":"2026-07-05T09:25:33Z"},{"alias_kind":"pith_short_8","alias_value":"OVQSJZ72","created_at":"2026-07-05T09:25:33Z"}],"graph_snapshots":[{"event_id":"sha256:68ad4941403383025b5da7481903e0e1204a1b04b0761668fd5a0f87dd9294df","target":"graph","created_at":"2026-07-05T09:25:33Z","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/2309.11384/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current simultaneous speech translation models can process audio only up to a few seconds long. Contemporary datasets provide an oracle segmentation into sentences based on human-annotated transcripts and translations. However, the segmentation into sentences is not available in the real world. Current speech segmentation approaches either offer poor segmentation quality or have to trade latency for quality. In this paper, we propose a novel segmentation approach for a low-latency end-to-end speech translation. We leverage the existing speech translation encoder-decoder architecture with ST CT","authors_text":"Ond\\v{r}ej Bojar, Peter Pol\\'ak","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-20T15:10:12Z","title":"Long-Form End-to-End Speech Translation via Latent Alignment Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11384","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:e6be133efe05ba7815d64e805c3c0302eb1e58bb96de2e74ac441017af95feb4","target":"record","created_at":"2026-07-05T09:25:33Z","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":"8300c4ae00f010b320e6fb1aed1d413c2384e9640a8e1b37b594e8010fbff724","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-20T15:10:12Z","title_canon_sha256":"9d85d1e75d33dc3f4efd9d66e7e10420409238c2ba5a6a4f1b898ad3d801911c"},"schema_version":"1.0","source":{"id":"2309.11384","kind":"arxiv","version":1}},"canonical_sha256":"756124e7fabe941101c6e2baccb6468386dd1211bd33a7cedd8a76d246ecd6a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"756124e7fabe941101c6e2baccb6468386dd1211bd33a7cedd8a76d246ecd6a8","first_computed_at":"2026-07-05T09:25:33.617981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:33.617981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QeX54R0BgATaS1MdplIai6nc6G6WkQ7GxoV+WvKqGkZzBi/Jfo2QIZMj5yLfvP/X3fynFA1BS6euQ0rGCA0OCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:33.618504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.11384","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6be133efe05ba7815d64e805c3c0302eb1e58bb96de2e74ac441017af95feb4","sha256:68ad4941403383025b5da7481903e0e1204a1b04b0761668fd5a0f87dd9294df"],"state_sha256":"f642d781646f8a5638d1e4883e2202e4a57b61ff794b2daa766a33874ee6fa29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rYx7rCCovx55gZWHu70DiFxocfVZG+cZFxMltYSPgDN6OBYc768Aaf2DxcaJVKOBlt59kQolodd62dsklxFtBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T23:44:43.426260Z","bundle_sha256":"0855aaf5b59db1a42ffbd673ff4e429fe90f4eddf4a6261f45a231a8335d5cca"}}