{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:L7FLC2N3UEHYPTAO54JRRKVMZF","short_pith_number":"pith:L7FLC2N3","schema_version":"1.0","canonical_sha256":"5fcab169bba10f87cc0eef1318aaacc94ffe3e3200990904cb9e88fd5c06e3cf","source":{"kind":"arxiv","id":"2203.03543","version":1},"attestation_state":"computed","paper":{"title":"RNN Transducers for Nested Named Entity Recognition with constraints on alignment for long sequences","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hagen Soltau, Izhak Shafran, Laurent El Shafey, Mingqiu Wang","submitted_at":"2022-02-08T05:38:20Z","abstract_excerpt":"Popular solutions to Named Entity Recognition (NER) include conditional random fields, sequence-to-sequence models, or utilizing the question-answering framework. However, they are not suitable for nested and overlapping spans with large ontologies and for predicting the position of the entities. To fill this gap, we introduce a new model for NER task -- an RNN transducer (RNN-T). These models are trained using paired input and output sequences without explicitly specifying the alignment between them, similar to other seq-to-seq models. RNN-T models learn the alignment using a loss function th"},"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":"2203.03543","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-08T05:38:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a7442378446d48e8761ae1f54c6ae4278f0712d138cb663f8e4be046e1e09888","abstract_canon_sha256":"d0dd5940caed12daa711ac898987b123eafef6a88fa34556ea64c80498c755aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:35.365074Z","signature_b64":"22jBvHDkFk6fTaT55NtqyloVn4vS2YqW8A/3IrAcyiX2MJt6YinwWbu7uyBDL1fi0xGqA+N9f7+52ZGf+UVyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fcab169bba10f87cc0eef1318aaacc94ffe3e3200990904cb9e88fd5c06e3cf","last_reissued_at":"2026-07-05T04:02:35.364630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:35.364630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RNN Transducers for Nested Named Entity Recognition with constraints on alignment for long sequences","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hagen Soltau, Izhak Shafran, Laurent El Shafey, Mingqiu Wang","submitted_at":"2022-02-08T05:38:20Z","abstract_excerpt":"Popular solutions to Named Entity Recognition (NER) include conditional random fields, sequence-to-sequence models, or utilizing the question-answering framework. However, they are not suitable for nested and overlapping spans with large ontologies and for predicting the position of the entities. To fill this gap, we introduce a new model for NER task -- an RNN transducer (RNN-T). These models are trained using paired input and output sequences without explicitly specifying the alignment between them, similar to other seq-to-seq models. RNN-T models learn the alignment using a loss function th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.03543","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/2203.03543/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":"2203.03543","created_at":"2026-07-05T04:02:35.364700+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.03543v1","created_at":"2026-07-05T04:02:35.364700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.03543","created_at":"2026-07-05T04:02:35.364700+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7FLC2N3UEHY","created_at":"2026-07-05T04:02:35.364700+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7FLC2N3UEHYPTAO","created_at":"2026-07-05T04:02:35.364700+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7FLC2N3","created_at":"2026-07-05T04:02:35.364700+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/L7FLC2N3UEHYPTAO54JRRKVMZF","json":"https://pith.science/pith/L7FLC2N3UEHYPTAO54JRRKVMZF.json","graph_json":"https://pith.science/api/pith-number/L7FLC2N3UEHYPTAO54JRRKVMZF/graph.json","events_json":"https://pith.science/api/pith-number/L7FLC2N3UEHYPTAO54JRRKVMZF/events.json","paper":"https://pith.science/paper/L7FLC2N3"},"agent_actions":{"view_html":"https://pith.science/pith/L7FLC2N3UEHYPTAO54JRRKVMZF","download_json":"https://pith.science/pith/L7FLC2N3UEHYPTAO54JRRKVMZF.json","view_paper":"https://pith.science/paper/L7FLC2N3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.03543&json=true","fetch_graph":"https://pith.science/api/pith-number/L7FLC2N3UEHYPTAO54JRRKVMZF/graph.json","fetch_events":"https://pith.science/api/pith-number/L7FLC2N3UEHYPTAO54JRRKVMZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7FLC2N3UEHYPTAO54JRRKVMZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7FLC2N3UEHYPTAO54JRRKVMZF/action/storage_attestation","attest_author":"https://pith.science/pith/L7FLC2N3UEHYPTAO54JRRKVMZF/action/author_attestation","sign_citation":"https://pith.science/pith/L7FLC2N3UEHYPTAO54JRRKVMZF/action/citation_signature","submit_replication":"https://pith.science/pith/L7FLC2N3UEHYPTAO54JRRKVMZF/action/replication_record"}},"created_at":"2026-07-05T04:02:35.364700+00:00","updated_at":"2026-07-05T04:02:35.364700+00:00"}