{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3NHB2T3PU5H3FEKOVCOMZZ6L6M","short_pith_number":"pith:3NHB2T3P","schema_version":"1.0","canonical_sha256":"db4e1d4f6fa74fb2914ea89ccce7cbf312d5ce8aeb25c77c3e074a15eac9087a","source":{"kind":"arxiv","id":"2512.17648","version":2},"attestation_state":"computed","paper":{"title":"Simulstream: Open-Source Toolkit for Evaluation and Demonstration of Streaming Speech-to-Text Translation Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Luisa Bentivogli, Marco Gaido, Matteo Negri, Mauro Cettolo, Sara Papi","submitted_at":"2025-12-19T14:48:59Z","abstract_excerpt":"Streaming Speech-to-Text Translation (StreamST) requires producing translations concurrently with incoming speech under strict latency constraints, demanding models that balance low latency with high translation quality. Despite rapid progress, evaluation remains fragmented across existing frameworks, which make different assumptions about how systems operate -- for example, whether they process continuous speech or short pre-segmented audio, and whether they support output revision (retranslation) or not (incremental) during decoding. As a result, comparing systems fairly and consistently acr"},"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":"2512.17648","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-19T14:48:59Z","cross_cats_sorted":[],"title_canon_sha256":"d268d4ff2604b9517820bc33dbe9a7ab116aa06a436f79d8d4e4882e19d4b2f7","abstract_canon_sha256":"423a4aa64d927b325154ee1a490103807a43b675e321601910fb72f681828f8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T01:19:50.028291Z","signature_b64":"RqwjrpEZDOPEeyJF615ZOd9Ek9nlGizebbYQBWsXHyYv/LDVz73hjMRb3k5Wyq4Y8Othv05R5Q6ettRqvryWCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db4e1d4f6fa74fb2914ea89ccce7cbf312d5ce8aeb25c77c3e074a15eac9087a","last_reissued_at":"2026-07-09T01:19:50.027743Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T01:19:50.027743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simulstream: Open-Source Toolkit for Evaluation and Demonstration of Streaming Speech-to-Text Translation Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Luisa Bentivogli, Marco Gaido, Matteo Negri, Mauro Cettolo, Sara Papi","submitted_at":"2025-12-19T14:48:59Z","abstract_excerpt":"Streaming Speech-to-Text Translation (StreamST) requires producing translations concurrently with incoming speech under strict latency constraints, demanding models that balance low latency with high translation quality. Despite rapid progress, evaluation remains fragmented across existing frameworks, which make different assumptions about how systems operate -- for example, whether they process continuous speech or short pre-segmented audio, and whether they support output revision (retranslation) or not (incremental) during decoding. As a result, comparing systems fairly and consistently acr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.17648","kind":"arxiv","version":2},"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/2512.17648/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":"2512.17648","created_at":"2026-07-09T01:19:50.027815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.17648v2","created_at":"2026-07-09T01:19:50.027815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.17648","created_at":"2026-07-09T01:19:50.027815+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NHB2T3PU5H3","created_at":"2026-07-09T01:19:50.027815+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NHB2T3PU5H3FEKO","created_at":"2026-07-09T01:19:50.027815+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NHB2T3P","created_at":"2026-07-09T01:19:50.027815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2606.03948","citing_title":"A Pocket Offline Model for Simultaneous Speech Translation as CUNI Submission to IWSLT 2026","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2606.03967","citing_title":"AlignAtt4LLM: Fast AlignAtt for Decoder-Only LLMs at IWSLT 2026 Simultaneous Speech Translation Task","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2606.03241","citing_title":"Benchmarking Speech-to-Speech Translation Models","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3NHB2T3PU5H3FEKOVCOMZZ6L6M","json":"https://pith.science/pith/3NHB2T3PU5H3FEKOVCOMZZ6L6M.json","graph_json":"https://pith.science/api/pith-number/3NHB2T3PU5H3FEKOVCOMZZ6L6M/graph.json","events_json":"https://pith.science/api/pith-number/3NHB2T3PU5H3FEKOVCOMZZ6L6M/events.json","paper":"https://pith.science/paper/3NHB2T3P"},"agent_actions":{"view_html":"https://pith.science/pith/3NHB2T3PU5H3FEKOVCOMZZ6L6M","download_json":"https://pith.science/pith/3NHB2T3PU5H3FEKOVCOMZZ6L6M.json","view_paper":"https://pith.science/paper/3NHB2T3P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.17648&json=true","fetch_graph":"https://pith.science/api/pith-number/3NHB2T3PU5H3FEKOVCOMZZ6L6M/graph.json","fetch_events":"https://pith.science/api/pith-number/3NHB2T3PU5H3FEKOVCOMZZ6L6M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NHB2T3PU5H3FEKOVCOMZZ6L6M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NHB2T3PU5H3FEKOVCOMZZ6L6M/action/storage_attestation","attest_author":"https://pith.science/pith/3NHB2T3PU5H3FEKOVCOMZZ6L6M/action/author_attestation","sign_citation":"https://pith.science/pith/3NHB2T3PU5H3FEKOVCOMZZ6L6M/action/citation_signature","submit_replication":"https://pith.science/pith/3NHB2T3PU5H3FEKOVCOMZZ6L6M/action/replication_record"}},"created_at":"2026-07-09T01:19:50.027815+00:00","updated_at":"2026-07-09T01:19:50.027815+00:00"}