{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:73Y4LUF6DHZ2EWSZ275IT4XHJY","short_pith_number":"pith:73Y4LUF6","schema_version":"1.0","canonical_sha256":"fef1c5d0be19f3a25a59d7fa89f2e74e2b3a185e2bde8cde3f3c70dc985a9139","source":{"kind":"arxiv","id":"2301.06841","version":1},"attestation_state":"computed","paper":{"title":"Syntactically Robust Training on Partially-Observed Data for Open Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bin Xu, Ji Qi, Juanzi Li, Lei Hou, Yuxiang Chen","submitted_at":"2023-01-17T12:39:13Z","abstract_excerpt":"Open Information Extraction models have shown promising results with sufficient supervision. However, these models face a fundamental challenge that the syntactic distribution of training data is partially observable in comparison to the real world. In this paper, we propose a syntactically robust training framework that enables models to be trained on a syntactic-abundant distribution based on diverse paraphrase generation. To tackle the intrinsic problem of knowledge deformation of paraphrasing, two algorithms based on semantic similarity matching and syntactic tree walking are used to resto"},"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":"2301.06841","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-17T12:39:13Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5f2a8a05e7d83db3af98a6e84503bed42d13c05a6b3844b81e0972726b9bf8c4","abstract_canon_sha256":"05ac6b7697a46d6b050962c1472915a132fc93ce4853a79d5ab68b17fa4c78a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:33:36.410369Z","signature_b64":"Yv2gwHM64ycv+pgf1e3SVs7b6iPUqWpi3haaI77AlTUJw6xToKK9S4BRYo9Pv/uT7bBEtEbD3Cd4U6lghITLAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fef1c5d0be19f3a25a59d7fa89f2e74e2b3a185e2bde8cde3f3c70dc985a9139","last_reissued_at":"2026-07-05T05:33:36.409831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:33:36.409831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Syntactically Robust Training on Partially-Observed Data for Open Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bin Xu, Ji Qi, Juanzi Li, Lei Hou, Yuxiang Chen","submitted_at":"2023-01-17T12:39:13Z","abstract_excerpt":"Open Information Extraction models have shown promising results with sufficient supervision. However, these models face a fundamental challenge that the syntactic distribution of training data is partially observable in comparison to the real world. In this paper, we propose a syntactically robust training framework that enables models to be trained on a syntactic-abundant distribution based on diverse paraphrase generation. To tackle the intrinsic problem of knowledge deformation of paraphrasing, two algorithms based on semantic similarity matching and syntactic tree walking are used to resto"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.06841","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/2301.06841/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":"2301.06841","created_at":"2026-07-05T05:33:36.409939+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.06841v1","created_at":"2026-07-05T05:33:36.409939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.06841","created_at":"2026-07-05T05:33:36.409939+00:00"},{"alias_kind":"pith_short_12","alias_value":"73Y4LUF6DHZ2","created_at":"2026-07-05T05:33:36.409939+00:00"},{"alias_kind":"pith_short_16","alias_value":"73Y4LUF6DHZ2EWSZ","created_at":"2026-07-05T05:33:36.409939+00:00"},{"alias_kind":"pith_short_8","alias_value":"73Y4LUF6","created_at":"2026-07-05T05:33:36.409939+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/73Y4LUF6DHZ2EWSZ275IT4XHJY","json":"https://pith.science/pith/73Y4LUF6DHZ2EWSZ275IT4XHJY.json","graph_json":"https://pith.science/api/pith-number/73Y4LUF6DHZ2EWSZ275IT4XHJY/graph.json","events_json":"https://pith.science/api/pith-number/73Y4LUF6DHZ2EWSZ275IT4XHJY/events.json","paper":"https://pith.science/paper/73Y4LUF6"},"agent_actions":{"view_html":"https://pith.science/pith/73Y4LUF6DHZ2EWSZ275IT4XHJY","download_json":"https://pith.science/pith/73Y4LUF6DHZ2EWSZ275IT4XHJY.json","view_paper":"https://pith.science/paper/73Y4LUF6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.06841&json=true","fetch_graph":"https://pith.science/api/pith-number/73Y4LUF6DHZ2EWSZ275IT4XHJY/graph.json","fetch_events":"https://pith.science/api/pith-number/73Y4LUF6DHZ2EWSZ275IT4XHJY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73Y4LUF6DHZ2EWSZ275IT4XHJY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73Y4LUF6DHZ2EWSZ275IT4XHJY/action/storage_attestation","attest_author":"https://pith.science/pith/73Y4LUF6DHZ2EWSZ275IT4XHJY/action/author_attestation","sign_citation":"https://pith.science/pith/73Y4LUF6DHZ2EWSZ275IT4XHJY/action/citation_signature","submit_replication":"https://pith.science/pith/73Y4LUF6DHZ2EWSZ275IT4XHJY/action/replication_record"}},"created_at":"2026-07-05T05:33:36.409939+00:00","updated_at":"2026-07-05T05:33:36.409939+00:00"}