{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CORWJTDGKAKXS3OLEVAPQLW6VF","short_pith_number":"pith:CORWJTDG","schema_version":"1.0","canonical_sha256":"13a364cc665015796dcb2540f82edea97cdf111cca6ccac1083c6ab60b5ab91c","source":{"kind":"arxiv","id":"2503.22051","version":1},"attestation_state":"computed","paper":{"title":"Non-Monotonic Attention-based Read/Write Policy Learning for Simultaneous Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Christian Fuegen, Frank Seide, Jachym Kolar, Niko Moritz, Rastislav Rabatin, Ruiming Xie, Simone Merello, Zeeshan Ahmed, Zhe Liu","submitted_at":"2025-03-28T00:00:33Z","abstract_excerpt":"Simultaneous or streaming machine translation generates translation while reading the input stream. These systems face a quality/latency trade-off, aiming to achieve high translation quality similar to non-streaming models with minimal latency. We propose an approach that efficiently manages this trade-off. By enhancing a pretrained non-streaming model, which was trained with a seq2seq mechanism and represents the upper bound in quality, we convert it into a streaming model by utilizing the alignment between source and target tokens. This alignment is used to learn a read/write decision bounda"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.22051","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-28T00:00:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0d31c5ffdc337fc41db1b9f3934db122d789c5f0b5d3da0aeff2a809eead3e43","abstract_canon_sha256":"bb1ce7250b7dc4c302bc0c2e5f4f58194ed6cdc9ff1923c38e985c1ddff451b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:46.468222Z","signature_b64":"0CAa/+7MqWMHEeDlOHndOqi9zdVShFsP1DtsHsac1rEg/8wmBm68+OFx5pVr+jTmA1srutgdJ6lROJ/nTv+9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13a364cc665015796dcb2540f82edea97cdf111cca6ccac1083c6ab60b5ab91c","last_reissued_at":"2026-07-05T10:40:46.467730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:46.467730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-Monotonic Attention-based Read/Write Policy Learning for Simultaneous Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Christian Fuegen, Frank Seide, Jachym Kolar, Niko Moritz, Rastislav Rabatin, Ruiming Xie, Simone Merello, Zeeshan Ahmed, Zhe Liu","submitted_at":"2025-03-28T00:00:33Z","abstract_excerpt":"Simultaneous or streaming machine translation generates translation while reading the input stream. These systems face a quality/latency trade-off, aiming to achieve high translation quality similar to non-streaming models with minimal latency. We propose an approach that efficiently manages this trade-off. By enhancing a pretrained non-streaming model, which was trained with a seq2seq mechanism and represents the upper bound in quality, we convert it into a streaming model by utilizing the alignment between source and target tokens. This alignment is used to learn a read/write decision bounda"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22051","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/2503.22051/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2503.22051","created_at":"2026-07-05T10:40:46.467793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.22051v1","created_at":"2026-07-05T10:40:46.467793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22051","created_at":"2026-07-05T10:40:46.467793+00:00"},{"alias_kind":"pith_short_12","alias_value":"CORWJTDGKAKX","created_at":"2026-07-05T10:40:46.467793+00:00"},{"alias_kind":"pith_short_16","alias_value":"CORWJTDGKAKXS3OL","created_at":"2026-07-05T10:40:46.467793+00:00"},{"alias_kind":"pith_short_8","alias_value":"CORWJTDG","created_at":"2026-07-05T10:40:46.467793+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CORWJTDGKAKXS3OLEVAPQLW6VF","json":"https://pith.science/pith/CORWJTDGKAKXS3OLEVAPQLW6VF.json","graph_json":"https://pith.science/api/pith-number/CORWJTDGKAKXS3OLEVAPQLW6VF/graph.json","events_json":"https://pith.science/api/pith-number/CORWJTDGKAKXS3OLEVAPQLW6VF/events.json","paper":"https://pith.science/paper/CORWJTDG"},"agent_actions":{"view_html":"https://pith.science/pith/CORWJTDGKAKXS3OLEVAPQLW6VF","download_json":"https://pith.science/pith/CORWJTDGKAKXS3OLEVAPQLW6VF.json","view_paper":"https://pith.science/paper/CORWJTDG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.22051&json=true","fetch_graph":"https://pith.science/api/pith-number/CORWJTDGKAKXS3OLEVAPQLW6VF/graph.json","fetch_events":"https://pith.science/api/pith-number/CORWJTDGKAKXS3OLEVAPQLW6VF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CORWJTDGKAKXS3OLEVAPQLW6VF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CORWJTDGKAKXS3OLEVAPQLW6VF/action/storage_attestation","attest_author":"https://pith.science/pith/CORWJTDGKAKXS3OLEVAPQLW6VF/action/author_attestation","sign_citation":"https://pith.science/pith/CORWJTDGKAKXS3OLEVAPQLW6VF/action/citation_signature","submit_replication":"https://pith.science/pith/CORWJTDGKAKXS3OLEVAPQLW6VF/action/replication_record"}},"created_at":"2026-07-05T10:40:46.467793+00:00","updated_at":"2026-07-05T10:40:46.467793+00:00"}