{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ESTJQLIBR5F47KD6BX32ZV5IPF","short_pith_number":"pith:ESTJQLIB","schema_version":"1.0","canonical_sha256":"24a6982d018f4bcfa87e0df7acd7a87945488429b125f7502d50aa4e410ce43d","source":{"kind":"arxiv","id":"2505.20976","version":1},"attestation_state":"computed","paper":{"title":"Contrastive Learning on LLM Back Generation Treebank for Cross-domain Constituency Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianling Li, Meishan Zhang, Min Zhang, Peiming Guo, Yue Zhang","submitted_at":"2025-05-27T10:07:54Z","abstract_excerpt":"Cross-domain constituency parsing is still an unsolved challenge in computational linguistics since the available multi-domain constituency treebank is limited. We investigate automatic treebank generation by large language models (LLMs) in this paper. The performance of LLMs on constituency parsing is poor, therefore we propose a novel treebank generation method, LLM back generation, which is similar to the reverse process of constituency parsing. LLM back generation takes the incomplete cross-domain constituency tree with only domain keyword leaf nodes as input and fills the missing words to"},"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":"2505.20976","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T10:07:54Z","cross_cats_sorted":[],"title_canon_sha256":"a282870160156a182ab344f9f4b085ecefa3806ffa54ec766d63818f5047fcae","abstract_canon_sha256":"f6c89f55f1f523b03aaf0eafceb69b65366ad27ae9a6859a97ede7af4ac70205"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:21.916672Z","signature_b64":"ybRg5Yvlwln0mqavCuyWmoNpN+h0dcUkjNMnugpMWwVbBWYOQvdlQ5lT9l2S5aU/selUMDoG2eu8MCWvvCt/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24a6982d018f4bcfa87e0df7acd7a87945488429b125f7502d50aa4e410ce43d","last_reissued_at":"2026-07-05T11:10:21.916156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:21.916156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Learning on LLM Back Generation Treebank for Cross-domain Constituency Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianling Li, Meishan Zhang, Min Zhang, Peiming Guo, Yue Zhang","submitted_at":"2025-05-27T10:07:54Z","abstract_excerpt":"Cross-domain constituency parsing is still an unsolved challenge in computational linguistics since the available multi-domain constituency treebank is limited. We investigate automatic treebank generation by large language models (LLMs) in this paper. The performance of LLMs on constituency parsing is poor, therefore we propose a novel treebank generation method, LLM back generation, which is similar to the reverse process of constituency parsing. LLM back generation takes the incomplete cross-domain constituency tree with only domain keyword leaf nodes as input and fills the missing words to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20976","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/2505.20976/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":"2505.20976","created_at":"2026-07-05T11:10:21.916216+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20976v1","created_at":"2026-07-05T11:10:21.916216+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20976","created_at":"2026-07-05T11:10:21.916216+00:00"},{"alias_kind":"pith_short_12","alias_value":"ESTJQLIBR5F4","created_at":"2026-07-05T11:10:21.916216+00:00"},{"alias_kind":"pith_short_16","alias_value":"ESTJQLIBR5F47KD6","created_at":"2026-07-05T11:10:21.916216+00:00"},{"alias_kind":"pith_short_8","alias_value":"ESTJQLIB","created_at":"2026-07-05T11:10:21.916216+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/ESTJQLIBR5F47KD6BX32ZV5IPF","json":"https://pith.science/pith/ESTJQLIBR5F47KD6BX32ZV5IPF.json","graph_json":"https://pith.science/api/pith-number/ESTJQLIBR5F47KD6BX32ZV5IPF/graph.json","events_json":"https://pith.science/api/pith-number/ESTJQLIBR5F47KD6BX32ZV5IPF/events.json","paper":"https://pith.science/paper/ESTJQLIB"},"agent_actions":{"view_html":"https://pith.science/pith/ESTJQLIBR5F47KD6BX32ZV5IPF","download_json":"https://pith.science/pith/ESTJQLIBR5F47KD6BX32ZV5IPF.json","view_paper":"https://pith.science/paper/ESTJQLIB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20976&json=true","fetch_graph":"https://pith.science/api/pith-number/ESTJQLIBR5F47KD6BX32ZV5IPF/graph.json","fetch_events":"https://pith.science/api/pith-number/ESTJQLIBR5F47KD6BX32ZV5IPF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ESTJQLIBR5F47KD6BX32ZV5IPF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ESTJQLIBR5F47KD6BX32ZV5IPF/action/storage_attestation","attest_author":"https://pith.science/pith/ESTJQLIBR5F47KD6BX32ZV5IPF/action/author_attestation","sign_citation":"https://pith.science/pith/ESTJQLIBR5F47KD6BX32ZV5IPF/action/citation_signature","submit_replication":"https://pith.science/pith/ESTJQLIBR5F47KD6BX32ZV5IPF/action/replication_record"}},"created_at":"2026-07-05T11:10:21.916216+00:00","updated_at":"2026-07-05T11:10:21.916216+00:00"}