{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WDGZ6U24QLNI6NLQQSPDIW5FXW","short_pith_number":"pith:WDGZ6U24","schema_version":"1.0","canonical_sha256":"b0cd9f535c82da8f3570849e345ba5bdb65f51f51882d5e46d50c6b8e9cffddb","source":{"kind":"arxiv","id":"2212.08458","version":1},"attestation_state":"computed","paper":{"title":"Fast Rule-Based Decoding: Revisiting Syntactic Rules in Neural Constituency Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Cong Liu, Liyin Xiao, Tianyu Shi, Zhicheng Wang","submitted_at":"2022-12-16T13:07:09Z","abstract_excerpt":"Most recent studies on neural constituency parsing focus on encoder structures, while few developments are devoted to decoders. Previous research has demonstrated that probabilistic statistical methods based on syntactic rules are particularly effective in constituency parsing, whereas syntactic rules are not used during the training of neural models in prior work probably due to their enormous computation requirements. In this paper, we first implement a fast CKY decoding procedure harnessing GPU acceleration, based on which we further derive a syntactic rule-based (rule-constrained) CKY deco"},"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":"2212.08458","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-16T13:07:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3cd9256fcecae4b3262ae2ca1b830e4283bcf06a3065a9748df51f1de75f0355","abstract_canon_sha256":"c6795db0e811e38f08bd707e52984b850e7ee6805cc27e0c965fb8141d6c38fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:57.590839Z","signature_b64":"kmOJS0bH5xAe/lnB/Ou2yYbZuLsjoKA9dhBFW2EndbQYRaHCR/sxWLfLlWXSV+VecGKh/y1rgELxkN5vMT/GCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0cd9f535c82da8f3570849e345ba5bdb65f51f51882d5e46d50c6b8e9cffddb","last_reissued_at":"2026-07-05T05:25:57.590435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:57.590435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast Rule-Based Decoding: Revisiting Syntactic Rules in Neural Constituency Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Cong Liu, Liyin Xiao, Tianyu Shi, Zhicheng Wang","submitted_at":"2022-12-16T13:07:09Z","abstract_excerpt":"Most recent studies on neural constituency parsing focus on encoder structures, while few developments are devoted to decoders. Previous research has demonstrated that probabilistic statistical methods based on syntactic rules are particularly effective in constituency parsing, whereas syntactic rules are not used during the training of neural models in prior work probably due to their enormous computation requirements. In this paper, we first implement a fast CKY decoding procedure harnessing GPU acceleration, based on which we further derive a syntactic rule-based (rule-constrained) CKY deco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08458","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/2212.08458/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":"2212.08458","created_at":"2026-07-05T05:25:57.590499+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.08458v1","created_at":"2026-07-05T05:25:57.590499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08458","created_at":"2026-07-05T05:25:57.590499+00:00"},{"alias_kind":"pith_short_12","alias_value":"WDGZ6U24QLNI","created_at":"2026-07-05T05:25:57.590499+00:00"},{"alias_kind":"pith_short_16","alias_value":"WDGZ6U24QLNI6NLQ","created_at":"2026-07-05T05:25:57.590499+00:00"},{"alias_kind":"pith_short_8","alias_value":"WDGZ6U24","created_at":"2026-07-05T05:25:57.590499+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20976","citing_title":"Contrastive Learning on LLM Back Generation Treebank for Cross-domain Constituency Parsing","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WDGZ6U24QLNI6NLQQSPDIW5FXW","json":"https://pith.science/pith/WDGZ6U24QLNI6NLQQSPDIW5FXW.json","graph_json":"https://pith.science/api/pith-number/WDGZ6U24QLNI6NLQQSPDIW5FXW/graph.json","events_json":"https://pith.science/api/pith-number/WDGZ6U24QLNI6NLQQSPDIW5FXW/events.json","paper":"https://pith.science/paper/WDGZ6U24"},"agent_actions":{"view_html":"https://pith.science/pith/WDGZ6U24QLNI6NLQQSPDIW5FXW","download_json":"https://pith.science/pith/WDGZ6U24QLNI6NLQQSPDIW5FXW.json","view_paper":"https://pith.science/paper/WDGZ6U24","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.08458&json=true","fetch_graph":"https://pith.science/api/pith-number/WDGZ6U24QLNI6NLQQSPDIW5FXW/graph.json","fetch_events":"https://pith.science/api/pith-number/WDGZ6U24QLNI6NLQQSPDIW5FXW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WDGZ6U24QLNI6NLQQSPDIW5FXW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WDGZ6U24QLNI6NLQQSPDIW5FXW/action/storage_attestation","attest_author":"https://pith.science/pith/WDGZ6U24QLNI6NLQQSPDIW5FXW/action/author_attestation","sign_citation":"https://pith.science/pith/WDGZ6U24QLNI6NLQQSPDIW5FXW/action/citation_signature","submit_replication":"https://pith.science/pith/WDGZ6U24QLNI6NLQQSPDIW5FXW/action/replication_record"}},"created_at":"2026-07-05T05:25:57.590499+00:00","updated_at":"2026-07-05T05:25:57.590499+00:00"}