{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:M6BGLQW3DHEGKHDMFNELYQG4VA","short_pith_number":"pith:M6BGLQW3","canonical_record":{"source":{"id":"2011.00767","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-02T06:24:58Z","cross_cats_sorted":[],"title_canon_sha256":"547a47a6c159d27608c98c0618ba4de1f88b389edd724430d8ac5795c4c8aac0","abstract_canon_sha256":"e3905f2b99efad2c7dff4cf862104284aec520b4e8e09e90245798bbef13d97a"},"schema_version":"1.0"},"canonical_sha256":"678265c2db19c8651c6c2b48bc40dca80f0aaa29e2de2c676ff28bb9091ec247","source":{"kind":"arxiv","id":"2011.00767","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.00767","created_at":"2026-07-05T01:53:22Z"},{"alias_kind":"arxiv_version","alias_value":"2011.00767v2","created_at":"2026-07-05T01:53:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.00767","created_at":"2026-07-05T01:53:22Z"},{"alias_kind":"pith_short_12","alias_value":"M6BGLQW3DHEG","created_at":"2026-07-05T01:53:22Z"},{"alias_kind":"pith_short_16","alias_value":"M6BGLQW3DHEGKHDM","created_at":"2026-07-05T01:53:22Z"},{"alias_kind":"pith_short_8","alias_value":"M6BGLQW3","created_at":"2026-07-05T01:53:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:M6BGLQW3DHEGKHDMFNELYQG4VA","target":"record","payload":{"canonical_record":{"source":{"id":"2011.00767","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-02T06:24:58Z","cross_cats_sorted":[],"title_canon_sha256":"547a47a6c159d27608c98c0618ba4de1f88b389edd724430d8ac5795c4c8aac0","abstract_canon_sha256":"e3905f2b99efad2c7dff4cf862104284aec520b4e8e09e90245798bbef13d97a"},"schema_version":"1.0"},"canonical_sha256":"678265c2db19c8651c6c2b48bc40dca80f0aaa29e2de2c676ff28bb9091ec247","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:22.758621Z","signature_b64":"8vVEVNc5YYW6J39Q67lGuKhfAbw+ky5duN+QAxD2oLierFXxSPle1n/3Re7FIcqtjacszx6SH/Zy0mXsuToqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"678265c2db19c8651c6c2b48bc40dca80f0aaa29e2de2c676ff28bb9091ec247","last_reissued_at":"2026-07-05T01:53:22.758123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:22.758123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.00767","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:53:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wp/hXx81og0ZG3V1pF6xWGt9bG4hIzhyaL2enR+4tGJh4ZeGlNnCQ/Y3qe/Jf8LwZKcX+w3lAYq/R+IFmvD3Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T16:42:30.224325Z"},"content_sha256":"baabf63a22f5c25dda0469891cc45d6aba3309ee8cf5b040f24e6e19ff3e5223","schema_version":"1.0","event_id":"sha256:baabf63a22f5c25dda0469891cc45d6aba3309ee8cf5b040f24e6e19ff3e5223"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:M6BGLQW3DHEGKHDMFNELYQG4VA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reducing Confusion in Active Learning for Part-Of-Speech Tagging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditi Chaudhary, Antonios Anastasopoulos, Graham Neubig, Zaid Sheikh","submitted_at":"2020-11-02T06:24:58Z","abstract_excerpt":"Active learning (AL) uses a data selection algorithm to select useful training samples to minimize annotation cost. This is now an essential tool for building low-resource syntactic analyzers such as part-of-speech (POS) taggers. Existing AL heuristics are generally designed on the principle of selecting uncertain yet representative training instances, where annotating these instances may reduce a large number of errors. However, in an empirical study across six typologically diverse languages (German, Swedish, Galician, North Sami, Persian, and Ukrainian), we found the surprising result that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.00767","kind":"arxiv","version":2},"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/2011.00767/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":"2026-07-05T01:53:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3/2T5QlyuYkb/eswzYNSzsAQsL9jhkSVrePZKVFtFNrW+K8BziQtVt2FFc5VuvRWa7C87eWAhryb3k/xc+iWDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T16:42:30.224822Z"},"content_sha256":"3feb522556b39451b7af2dfaa95bab5ae793c0a128178b592f6bbadc9e9c7947","schema_version":"1.0","event_id":"sha256:3feb522556b39451b7af2dfaa95bab5ae793c0a128178b592f6bbadc9e9c7947"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M6BGLQW3DHEGKHDMFNELYQG4VA/bundle.json","state_url":"https://pith.science/pith/M6BGLQW3DHEGKHDMFNELYQG4VA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M6BGLQW3DHEGKHDMFNELYQG4VA/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":"2026-08-19T16:42:30Z","links":{"resolver":"https://pith.science/pith/M6BGLQW3DHEGKHDMFNELYQG4VA","bundle":"https://pith.science/pith/M6BGLQW3DHEGKHDMFNELYQG4VA/bundle.json","state":"https://pith.science/pith/M6BGLQW3DHEGKHDMFNELYQG4VA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M6BGLQW3DHEGKHDMFNELYQG4VA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:M6BGLQW3DHEGKHDMFNELYQG4VA","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":"e3905f2b99efad2c7dff4cf862104284aec520b4e8e09e90245798bbef13d97a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-02T06:24:58Z","title_canon_sha256":"547a47a6c159d27608c98c0618ba4de1f88b389edd724430d8ac5795c4c8aac0"},"schema_version":"1.0","source":{"id":"2011.00767","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.00767","created_at":"2026-07-05T01:53:22Z"},{"alias_kind":"arxiv_version","alias_value":"2011.00767v2","created_at":"2026-07-05T01:53:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.00767","created_at":"2026-07-05T01:53:22Z"},{"alias_kind":"pith_short_12","alias_value":"M6BGLQW3DHEG","created_at":"2026-07-05T01:53:22Z"},{"alias_kind":"pith_short_16","alias_value":"M6BGLQW3DHEGKHDM","created_at":"2026-07-05T01:53:22Z"},{"alias_kind":"pith_short_8","alias_value":"M6BGLQW3","created_at":"2026-07-05T01:53:22Z"}],"graph_snapshots":[{"event_id":"sha256:3feb522556b39451b7af2dfaa95bab5ae793c0a128178b592f6bbadc9e9c7947","target":"graph","created_at":"2026-07-05T01:53:22Z","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/2011.00767/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Active learning (AL) uses a data selection algorithm to select useful training samples to minimize annotation cost. This is now an essential tool for building low-resource syntactic analyzers such as part-of-speech (POS) taggers. Existing AL heuristics are generally designed on the principle of selecting uncertain yet representative training instances, where annotating these instances may reduce a large number of errors. However, in an empirical study across six typologically diverse languages (German, Swedish, Galician, North Sami, Persian, and Ukrainian), we found the surprising result that ","authors_text":"Aditi Chaudhary, Antonios Anastasopoulos, Graham Neubig, Zaid Sheikh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-02T06:24:58Z","title":"Reducing Confusion in Active Learning for Part-Of-Speech Tagging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.00767","kind":"arxiv","version":2},"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:baabf63a22f5c25dda0469891cc45d6aba3309ee8cf5b040f24e6e19ff3e5223","target":"record","created_at":"2026-07-05T01:53:22Z","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":"e3905f2b99efad2c7dff4cf862104284aec520b4e8e09e90245798bbef13d97a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-02T06:24:58Z","title_canon_sha256":"547a47a6c159d27608c98c0618ba4de1f88b389edd724430d8ac5795c4c8aac0"},"schema_version":"1.0","source":{"id":"2011.00767","kind":"arxiv","version":2}},"canonical_sha256":"678265c2db19c8651c6c2b48bc40dca80f0aaa29e2de2c676ff28bb9091ec247","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"678265c2db19c8651c6c2b48bc40dca80f0aaa29e2de2c676ff28bb9091ec247","first_computed_at":"2026-07-05T01:53:22.758123Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:53:22.758123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8vVEVNc5YYW6J39Q67lGuKhfAbw+ky5duN+QAxD2oLierFXxSPle1n/3Re7FIcqtjacszx6SH/Zy0mXsuToqAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:53:22.758621Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.00767","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:baabf63a22f5c25dda0469891cc45d6aba3309ee8cf5b040f24e6e19ff3e5223","sha256:3feb522556b39451b7af2dfaa95bab5ae793c0a128178b592f6bbadc9e9c7947"],"state_sha256":"0b3d18be19d4b4c05da43801c32bfc2f11a39750f0e27c6f92a74046ae9c1504"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JMiH47CFWawFqyV9XINbi8JghFFwBwfWMXzK6VY5QeYOeEH8wnR0h7ukoOOBCHR+rCX+2IOSj1p6xCn4h1XABg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T16:42:30.229591Z","bundle_sha256":"865b1d2f72f9d56aab3ed2f5ee53d04d76076a951306b8b2af4b0bd69c7b19bc"}}