{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2V4IGDJIVWEVFZ4QECVBPQ7AR7","short_pith_number":"pith:2V4IGDJI","schema_version":"1.0","canonical_sha256":"d578830d28ad8952e79020aa17c3e08ffa0c5a138df68949d13a6a33971f5c65","source":{"kind":"arxiv","id":"2109.04733","version":1},"attestation_state":"computed","paper":{"title":"Genre as Weak Supervision for Cross-lingual Dependency Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barbara Plank, Max M\\\"uller-Eberstein, Rob van der Goot","submitted_at":"2021-09-10T08:24:54Z","abstract_excerpt":"Recent work has shown that monolingual masked language models learn to represent data-driven notions of language variation which can be used for domain-targeted training data selection. Dataset genre labels are already frequently available, yet remain largely unexplored in cross-lingual setups. We harness this genre metadata as a weak supervision signal for targeted data selection in zero-shot dependency parsing. Specifically, we project treebank-level genre information to the finer-grained sentence level, with the goal to amplify information implicitly stored in unsupervised contextualized re"},"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":"2109.04733","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-10T08:24:54Z","cross_cats_sorted":[],"title_canon_sha256":"94b77c47f517d3a447aaae876ee3f71bf52055d7b88b6428dbad25cb4d559f5e","abstract_canon_sha256":"60b7e347868271c832a4da273ca5720b5305b83ee242801aca8e7600623ae0c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:09.504860Z","signature_b64":"Xf3GjnjCmvFgXMDQoOmHuqyI24ekEZMGdyN4UfH//vS8CoHYriRZagAjJjLbyx0ovcnMHfYmKvo2rXThuAEmBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d578830d28ad8952e79020aa17c3e08ffa0c5a138df68949d13a6a33971f5c65","last_reissued_at":"2026-07-05T03:13:09.504423Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:09.504423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Genre as Weak Supervision for Cross-lingual Dependency Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barbara Plank, Max M\\\"uller-Eberstein, Rob van der Goot","submitted_at":"2021-09-10T08:24:54Z","abstract_excerpt":"Recent work has shown that monolingual masked language models learn to represent data-driven notions of language variation which can be used for domain-targeted training data selection. Dataset genre labels are already frequently available, yet remain largely unexplored in cross-lingual setups. We harness this genre metadata as a weak supervision signal for targeted data selection in zero-shot dependency parsing. Specifically, we project treebank-level genre information to the finer-grained sentence level, with the goal to amplify information implicitly stored in unsupervised contextualized re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04733","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/2109.04733/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":"2109.04733","created_at":"2026-07-05T03:13:09.504503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.04733v1","created_at":"2026-07-05T03:13:09.504503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04733","created_at":"2026-07-05T03:13:09.504503+00:00"},{"alias_kind":"pith_short_12","alias_value":"2V4IGDJIVWEV","created_at":"2026-07-05T03:13:09.504503+00:00"},{"alias_kind":"pith_short_16","alias_value":"2V4IGDJIVWEVFZ4Q","created_at":"2026-07-05T03:13:09.504503+00:00"},{"alias_kind":"pith_short_8","alias_value":"2V4IGDJI","created_at":"2026-07-05T03:13:09.504503+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.20595","citing_title":"Controlling Out-of-Domain Gaps in LLMs for Genre Classification and Generated Text Detection","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2V4IGDJIVWEVFZ4QECVBPQ7AR7","json":"https://pith.science/pith/2V4IGDJIVWEVFZ4QECVBPQ7AR7.json","graph_json":"https://pith.science/api/pith-number/2V4IGDJIVWEVFZ4QECVBPQ7AR7/graph.json","events_json":"https://pith.science/api/pith-number/2V4IGDJIVWEVFZ4QECVBPQ7AR7/events.json","paper":"https://pith.science/paper/2V4IGDJI"},"agent_actions":{"view_html":"https://pith.science/pith/2V4IGDJIVWEVFZ4QECVBPQ7AR7","download_json":"https://pith.science/pith/2V4IGDJIVWEVFZ4QECVBPQ7AR7.json","view_paper":"https://pith.science/paper/2V4IGDJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.04733&json=true","fetch_graph":"https://pith.science/api/pith-number/2V4IGDJIVWEVFZ4QECVBPQ7AR7/graph.json","fetch_events":"https://pith.science/api/pith-number/2V4IGDJIVWEVFZ4QECVBPQ7AR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2V4IGDJIVWEVFZ4QECVBPQ7AR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2V4IGDJIVWEVFZ4QECVBPQ7AR7/action/storage_attestation","attest_author":"https://pith.science/pith/2V4IGDJIVWEVFZ4QECVBPQ7AR7/action/author_attestation","sign_citation":"https://pith.science/pith/2V4IGDJIVWEVFZ4QECVBPQ7AR7/action/citation_signature","submit_replication":"https://pith.science/pith/2V4IGDJIVWEVFZ4QECVBPQ7AR7/action/replication_record"}},"created_at":"2026-07-05T03:13:09.504503+00:00","updated_at":"2026-07-05T03:13:09.504503+00:00"}