{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2V4IGDJIVWEVFZ4QECVBPQ7AR7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"60b7e347868271c832a4da273ca5720b5305b83ee242801aca8e7600623ae0c6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-10T08:24:54Z","title_canon_sha256":"94b77c47f517d3a447aaae876ee3f71bf52055d7b88b6428dbad25cb4d559f5e"},"schema_version":"1.0","source":{"id":"2109.04733","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.04733","created_at":"2026-07-05T03:13:09Z"},{"alias_kind":"arxiv_version","alias_value":"2109.04733v1","created_at":"2026-07-05T03:13:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04733","created_at":"2026-07-05T03:13:09Z"},{"alias_kind":"pith_short_12","alias_value":"2V4IGDJIVWEV","created_at":"2026-07-05T03:13:09Z"},{"alias_kind":"pith_short_16","alias_value":"2V4IGDJIVWEVFZ4Q","created_at":"2026-07-05T03:13:09Z"},{"alias_kind":"pith_short_8","alias_value":"2V4IGDJI","created_at":"2026-07-05T03:13:09Z"}],"graph_snapshots":[{"event_id":"sha256:610ab5ed89dd3d8bf08d242f2f3aea2c58d0a91c67ea78dddc6b1242040cb51c","target":"graph","created_at":"2026-07-05T03:13:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2109.04733/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Barbara Plank, Max M\\\"uller-Eberstein, Rob van der Goot","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-10T08:24:54Z","title":"Genre as Weak Supervision for Cross-lingual Dependency Parsing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04733","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ca0f0b39f942c5793ca31987cf67fece813bb5fc93804f7e3e76b952353999df","target":"record","created_at":"2026-07-05T03:13:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"60b7e347868271c832a4da273ca5720b5305b83ee242801aca8e7600623ae0c6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-10T08:24:54Z","title_canon_sha256":"94b77c47f517d3a447aaae876ee3f71bf52055d7b88b6428dbad25cb4d559f5e"},"schema_version":"1.0","source":{"id":"2109.04733","kind":"arxiv","version":1}},"canonical_sha256":"d578830d28ad8952e79020aa17c3e08ffa0c5a138df68949d13a6a33971f5c65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d578830d28ad8952e79020aa17c3e08ffa0c5a138df68949d13a6a33971f5c65","first_computed_at":"2026-07-05T03:13:09.504423Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:13:09.504423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xf3GjnjCmvFgXMDQoOmHuqyI24ekEZMGdyN4UfH//vS8CoHYriRZagAjJjLbyx0ovcnMHfYmKvo2rXThuAEmBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:13:09.504860Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.04733","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca0f0b39f942c5793ca31987cf67fece813bb5fc93804f7e3e76b952353999df","sha256:610ab5ed89dd3d8bf08d242f2f3aea2c58d0a91c67ea78dddc6b1242040cb51c"],"state_sha256":"38716dcf6da9fe0fd3a10c4406eb7b06be2a0ed953118356eafa3e4a8ad8df2e"}