{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YTLL2KQXN2BBMWRMAGCFUFGQBA","short_pith_number":"pith:YTLL2KQX","schema_version":"1.0","canonical_sha256":"c4d6bd2a176e82165a2c01845a14d00805bea8124a1bb6e3363352f8ed0a49ad","source":{"kind":"arxiv","id":"2102.02080","version":2},"attestation_state":"computed","paper":{"title":"Top-down Discourse Parsing via Sequence Labelling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fajri Koto, Jey Han Lau, Timothy Baldwin","submitted_at":"2021-02-03T14:30:21Z","abstract_excerpt":"We introduce a top-down approach to discourse parsing that is conceptually simpler than its predecessors (Kobayashi et al., 2020; Zhang et al., 2020). By framing the task as a sequence labelling problem where the goal is to iteratively segment a document into individual discourse units, we are able to eliminate the decoder and reduce the search space for splitting points. We explore both traditional recurrent models and modern pre-trained transformer models for the task, and additionally introduce a novel dynamic oracle for top-down parsing. Based on the Full metric, our proposed LSTM model se"},"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":"2102.02080","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-02-03T14:30:21Z","cross_cats_sorted":[],"title_canon_sha256":"7a1989b830c9dbecd2bc710b32671d8d8586e12ef25e7a995da4a66004f31009","abstract_canon_sha256":"bf2006c8275fd6fcd9efc435e6895d9ec34e506aef01165b965bc68ddb16faca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:12.529574Z","signature_b64":"5vEMsWJP+OL82SKaST9MBZ7P1HyUvsJn+/yLAd0JbSBRardl0VzmyB4K3K5p4lUj5yW9P+Epv0ECteQzwlRFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4d6bd2a176e82165a2c01845a14d00805bea8124a1bb6e3363352f8ed0a49ad","last_reissued_at":"2026-07-05T02:29:12.528930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:12.528930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Top-down Discourse Parsing via Sequence Labelling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fajri Koto, Jey Han Lau, Timothy Baldwin","submitted_at":"2021-02-03T14:30:21Z","abstract_excerpt":"We introduce a top-down approach to discourse parsing that is conceptually simpler than its predecessors (Kobayashi et al., 2020; Zhang et al., 2020). By framing the task as a sequence labelling problem where the goal is to iteratively segment a document into individual discourse units, we are able to eliminate the decoder and reduce the search space for splitting points. We explore both traditional recurrent models and modern pre-trained transformer models for the task, and additionally introduce a novel dynamic oracle for top-down parsing. Based on the Full metric, our proposed LSTM model se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02080","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/2102.02080/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":"2102.02080","created_at":"2026-07-05T02:29:12.528996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.02080v2","created_at":"2026-07-05T02:29:12.528996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02080","created_at":"2026-07-05T02:29:12.528996+00:00"},{"alias_kind":"pith_short_12","alias_value":"YTLL2KQXN2BB","created_at":"2026-07-05T02:29:12.528996+00:00"},{"alias_kind":"pith_short_16","alias_value":"YTLL2KQXN2BBMWRM","created_at":"2026-07-05T02:29:12.528996+00:00"},{"alias_kind":"pith_short_8","alias_value":"YTLL2KQX","created_at":"2026-07-05T02:29:12.528996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07723","citing_title":"ESURF: Simple and Effective EDU Segmentation","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YTLL2KQXN2BBMWRMAGCFUFGQBA","json":"https://pith.science/pith/YTLL2KQXN2BBMWRMAGCFUFGQBA.json","graph_json":"https://pith.science/api/pith-number/YTLL2KQXN2BBMWRMAGCFUFGQBA/graph.json","events_json":"https://pith.science/api/pith-number/YTLL2KQXN2BBMWRMAGCFUFGQBA/events.json","paper":"https://pith.science/paper/YTLL2KQX"},"agent_actions":{"view_html":"https://pith.science/pith/YTLL2KQXN2BBMWRMAGCFUFGQBA","download_json":"https://pith.science/pith/YTLL2KQXN2BBMWRMAGCFUFGQBA.json","view_paper":"https://pith.science/paper/YTLL2KQX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.02080&json=true","fetch_graph":"https://pith.science/api/pith-number/YTLL2KQXN2BBMWRMAGCFUFGQBA/graph.json","fetch_events":"https://pith.science/api/pith-number/YTLL2KQXN2BBMWRMAGCFUFGQBA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YTLL2KQXN2BBMWRMAGCFUFGQBA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YTLL2KQXN2BBMWRMAGCFUFGQBA/action/storage_attestation","attest_author":"https://pith.science/pith/YTLL2KQXN2BBMWRMAGCFUFGQBA/action/author_attestation","sign_citation":"https://pith.science/pith/YTLL2KQXN2BBMWRMAGCFUFGQBA/action/citation_signature","submit_replication":"https://pith.science/pith/YTLL2KQXN2BBMWRMAGCFUFGQBA/action/replication_record"}},"created_at":"2026-07-05T02:29:12.528996+00:00","updated_at":"2026-07-05T02:29:12.528996+00:00"}