{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:REZ627GJJ33OJVLMXNPP2D2XAF","short_pith_number":"pith:REZ627GJ","canonical_record":{"source":{"id":"2203.10315","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-19T12:33:38Z","cross_cats_sorted":[],"title_canon_sha256":"7980f38b9ed697cfcbda4376e89c056098aa5448454473c2c0b37128ac5faee6","abstract_canon_sha256":"fef6a7860e2b480f5f435090b3f77c48414502d9d480ca35dfab00bd0e0110b5"},"schema_version":"1.0"},"canonical_sha256":"8933ed7cc94ef6e4d56cbb5efd0f57016246c5b177a9810ce9ce447c0bfef8f3","source":{"kind":"arxiv","id":"2203.10315","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.10315","created_at":"2026-07-05T04:06:51Z"},{"alias_kind":"arxiv_version","alias_value":"2203.10315v1","created_at":"2026-07-05T04:06:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10315","created_at":"2026-07-05T04:06:51Z"},{"alias_kind":"pith_short_12","alias_value":"REZ627GJJ33O","created_at":"2026-07-05T04:06:51Z"},{"alias_kind":"pith_short_16","alias_value":"REZ627GJJ33OJVLM","created_at":"2026-07-05T04:06:51Z"},{"alias_kind":"pith_short_8","alias_value":"REZ627GJ","created_at":"2026-07-05T04:06:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:REZ627GJJ33OJVLMXNPP2D2XAF","target":"record","payload":{"canonical_record":{"source":{"id":"2203.10315","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-19T12:33:38Z","cross_cats_sorted":[],"title_canon_sha256":"7980f38b9ed697cfcbda4376e89c056098aa5448454473c2c0b37128ac5faee6","abstract_canon_sha256":"fef6a7860e2b480f5f435090b3f77c48414502d9d480ca35dfab00bd0e0110b5"},"schema_version":"1.0"},"canonical_sha256":"8933ed7cc94ef6e4d56cbb5efd0f57016246c5b177a9810ce9ce447c0bfef8f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:51.574390Z","signature_b64":"CyPX2oO2odQVHobiuzMvUSYjd3iqpG3f1tZ4uRy4ScDYkQxLbL0319o/Sf37it7oOmYbKlPKhEgPDWmC+l71Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8933ed7cc94ef6e4d56cbb5efd0f57016246c5b177a9810ce9ce447c0bfef8f3","last_reissued_at":"2026-07-05T04:06:51.573930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:51.573930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.10315","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:06:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ub0QeJ+cwlu11ROSNV1iOYlZ+4FXMmFZW9JWfZQab1NAc+zqSkQKUfU6jDbjni8P6Yt7TZlCtEvUU1WMtshOAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T12:06:23.004413Z"},"content_sha256":"86be76af5f98ee7016db969dcf1325e1be9e4fa2c1fa60c8740660fde0c73467","schema_version":"1.0","event_id":"sha256:86be76af5f98ee7016db969dcf1325e1be9e4fa2c1fa60c8740660fde0c73467"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:REZ627GJJ33OJVLMXNPP2D2XAF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Houquan Zhou, Min Zhang, Yang Li, Zhenghua Li","submitted_at":"2022-03-19T12:33:38Z","abstract_excerpt":"In recent years, large-scale pre-trained language models (PLMs) have made extraordinary progress in most NLP tasks. But, in the unsupervised POS tagging task, works utilizing PLMs are few and fail to achieve state-of-the-art (SOTA) performance. The recent SOTA performance is yielded by a Guassian HMM variant proposed by He et al. (2018). However, as a generative model, HMM makes very strong independence assumptions, making it very challenging to incorporate contexualized word representations from PLMs. In this work, we for the first time propose a neural conditional random field autoencoder (C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10315","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/2203.10315/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:06:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/GFVVZYEjPmFL+EzbsWfeY1wv4Wl5xgBPPSHLZ7Rb/pSSu7bDzD8ewiinv3Ux419PmjaGx6Oj9+i322JElQ9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T12:06:23.005282Z"},"content_sha256":"ba3c015af77665357f447f2deab5d140cd9f0ad3924a22f3e709331910675c8f","schema_version":"1.0","event_id":"sha256:ba3c015af77665357f447f2deab5d140cd9f0ad3924a22f3e709331910675c8f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/REZ627GJJ33OJVLMXNPP2D2XAF/bundle.json","state_url":"https://pith.science/pith/REZ627GJJ33OJVLMXNPP2D2XAF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/REZ627GJJ33OJVLMXNPP2D2XAF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T12:06:23Z","links":{"resolver":"https://pith.science/pith/REZ627GJJ33OJVLMXNPP2D2XAF","bundle":"https://pith.science/pith/REZ627GJJ33OJVLMXNPP2D2XAF/bundle.json","state":"https://pith.science/pith/REZ627GJJ33OJVLMXNPP2D2XAF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/REZ627GJJ33OJVLMXNPP2D2XAF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:REZ627GJJ33OJVLMXNPP2D2XAF","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":"fef6a7860e2b480f5f435090b3f77c48414502d9d480ca35dfab00bd0e0110b5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-19T12:33:38Z","title_canon_sha256":"7980f38b9ed697cfcbda4376e89c056098aa5448454473c2c0b37128ac5faee6"},"schema_version":"1.0","source":{"id":"2203.10315","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.10315","created_at":"2026-07-05T04:06:51Z"},{"alias_kind":"arxiv_version","alias_value":"2203.10315v1","created_at":"2026-07-05T04:06:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10315","created_at":"2026-07-05T04:06:51Z"},{"alias_kind":"pith_short_12","alias_value":"REZ627GJJ33O","created_at":"2026-07-05T04:06:51Z"},{"alias_kind":"pith_short_16","alias_value":"REZ627GJJ33OJVLM","created_at":"2026-07-05T04:06:51Z"},{"alias_kind":"pith_short_8","alias_value":"REZ627GJ","created_at":"2026-07-05T04:06:51Z"}],"graph_snapshots":[{"event_id":"sha256:ba3c015af77665357f447f2deab5d140cd9f0ad3924a22f3e709331910675c8f","target":"graph","created_at":"2026-07-05T04:06:51Z","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/2203.10315/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, large-scale pre-trained language models (PLMs) have made extraordinary progress in most NLP tasks. But, in the unsupervised POS tagging task, works utilizing PLMs are few and fail to achieve state-of-the-art (SOTA) performance. The recent SOTA performance is yielded by a Guassian HMM variant proposed by He et al. (2018). However, as a generative model, HMM makes very strong independence assumptions, making it very challenging to incorporate contexualized word representations from PLMs. In this work, we for the first time propose a neural conditional random field autoencoder (C","authors_text":"Houquan Zhou, Min Zhang, Yang Li, Zhenghua Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-19T12:33:38Z","title":"Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10315","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":"sha256:86be76af5f98ee7016db969dcf1325e1be9e4fa2c1fa60c8740660fde0c73467","target":"record","created_at":"2026-07-05T04:06:51Z","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":"fef6a7860e2b480f5f435090b3f77c48414502d9d480ca35dfab00bd0e0110b5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-19T12:33:38Z","title_canon_sha256":"7980f38b9ed697cfcbda4376e89c056098aa5448454473c2c0b37128ac5faee6"},"schema_version":"1.0","source":{"id":"2203.10315","kind":"arxiv","version":1}},"canonical_sha256":"8933ed7cc94ef6e4d56cbb5efd0f57016246c5b177a9810ce9ce447c0bfef8f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8933ed7cc94ef6e4d56cbb5efd0f57016246c5b177a9810ce9ce447c0bfef8f3","first_computed_at":"2026-07-05T04:06:51.573930Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:51.573930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CyPX2oO2odQVHobiuzMvUSYjd3iqpG3f1tZ4uRy4ScDYkQxLbL0319o/Sf37it7oOmYbKlPKhEgPDWmC+l71Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:51.574390Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.10315","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86be76af5f98ee7016db969dcf1325e1be9e4fa2c1fa60c8740660fde0c73467","sha256:ba3c015af77665357f447f2deab5d140cd9f0ad3924a22f3e709331910675c8f"],"state_sha256":"0a60f4359ee2604bd21f76f7b76f9030ec7d890e95dbff4ada1f62f43f39c0a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qa+d5xqGDLRmanTbsy6ysXbejvDCSLOKmVd+RH6ddEESxiGYT/SJXrTQ1HjGegbhnIkhPMGBaKz45mUgrqAPCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T12:06:23.010153Z","bundle_sha256":"2a4643ac1a570a90c24643c455cf21c44f316639f021db258ff2a35eb688cc71"}}