{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:SBT6JHMQT3H53XX7YMBDZPMGLC","short_pith_number":"pith:SBT6JHMQ","canonical_record":{"source":{"id":"2006.09627","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-17T03:24:38Z","cross_cats_sorted":[],"title_canon_sha256":"a6ee1f1d251c6265de44f1ebc94303f2ce903af7feeb125174e5a2b22b88693f","abstract_canon_sha256":"12a239560e7e508922f57697f3895f4910f086e0bada96a69147e1eff9ed41f6"},"schema_version":"1.0"},"canonical_sha256":"9067e49d909ecfdddeffc3023cbd865893e846cf75d5eb75448f6b16f98ccc2e","source":{"kind":"arxiv","id":"2006.09627","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.09627","created_at":"2026-07-05T02:34:40Z"},{"alias_kind":"arxiv_version","alias_value":"2006.09627v2","created_at":"2026-07-05T02:34:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09627","created_at":"2026-07-05T02:34:40Z"},{"alias_kind":"pith_short_12","alias_value":"SBT6JHMQT3H5","created_at":"2026-07-05T02:34:40Z"},{"alias_kind":"pith_short_16","alias_value":"SBT6JHMQT3H53XX7","created_at":"2026-07-05T02:34:40Z"},{"alias_kind":"pith_short_8","alias_value":"SBT6JHMQ","created_at":"2026-07-05T02:34:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:SBT6JHMQT3H53XX7YMBDZPMGLC","target":"record","payload":{"canonical_record":{"source":{"id":"2006.09627","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-17T03:24:38Z","cross_cats_sorted":[],"title_canon_sha256":"a6ee1f1d251c6265de44f1ebc94303f2ce903af7feeb125174e5a2b22b88693f","abstract_canon_sha256":"12a239560e7e508922f57697f3895f4910f086e0bada96a69147e1eff9ed41f6"},"schema_version":"1.0"},"canonical_sha256":"9067e49d909ecfdddeffc3023cbd865893e846cf75d5eb75448f6b16f98ccc2e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:34:40.188171Z","signature_b64":"TOg3vScxnZsj9ACbJmwu5u4cCgc0IsarnkWX30Y6NoDdNlJ3DuDcVLAW5lHDPgy/NuDXqz0QMTS4C583L6t5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9067e49d909ecfdddeffc3023cbd865893e846cf75d5eb75448f6b16f98ccc2e","last_reissued_at":"2026-07-05T02:34:40.187758Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:34:40.187758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.09627","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":"2026-07-05T02:34:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dkmqgO4dWEtmjov9OAw90zUTO0S6QGyNhRpgz2tQBcGq5oYYxKJrV5RZrX1tTrq0o16a5vhL3eqETEAyVXOHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T01:48:56.523783Z"},"content_sha256":"ba49880e395b4dfa5a440e7c6b795fc24746d25d7980a3a6d38580a1e8b65599","schema_version":"1.0","event_id":"sha256:ba49880e395b4dfa5a440e7c6b795fc24746d25d7980a3a6d38580a1e8b65599"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:SBT6JHMQT3H53XX7YMBDZPMGLC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Building Low-Resource NER Models Using Non-Speaker Annotation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Roth, Francesca Marini, Stephen Mayhew, Tatiana Tsygankova","submitted_at":"2020-06-17T03:24:38Z","abstract_excerpt":"In low-resource natural language processing (NLP), the key problems are a lack of target language training data, and a lack of native speakers to create it. Cross-lingual methods have had notable success in addressing these concerns, but in certain common circumstances, such as insufficient pre-training corpora or languages far from the source language, their performance suffers. In this work we propose a complementary approach to building low-resource Named Entity Recognition (NER) models using ``non-speaker'' (NS) annotations, provided by annotators with no prior experience in the target lan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09627","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/2006.09627/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":"2026-07-05T02:34:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XHPpI0lGPZaCXPyEnBw3wipLzjrcN8NaUL6mgnPaPNUfSrEJN60Xp7hKruxa/QjagP21fVeSheFKO5ySMbRiCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T01:48:56.524757Z"},"content_sha256":"ae9a5066272a99ccf000fd423eced1766a668e7cdd62562600279274e31d48db","schema_version":"1.0","event_id":"sha256:ae9a5066272a99ccf000fd423eced1766a668e7cdd62562600279274e31d48db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SBT6JHMQT3H53XX7YMBDZPMGLC/bundle.json","state_url":"https://pith.science/pith/SBT6JHMQT3H53XX7YMBDZPMGLC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SBT6JHMQT3H53XX7YMBDZPMGLC/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":"2026-08-01T01:48:56Z","links":{"resolver":"https://pith.science/pith/SBT6JHMQT3H53XX7YMBDZPMGLC","bundle":"https://pith.science/pith/SBT6JHMQT3H53XX7YMBDZPMGLC/bundle.json","state":"https://pith.science/pith/SBT6JHMQT3H53XX7YMBDZPMGLC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SBT6JHMQT3H53XX7YMBDZPMGLC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SBT6JHMQT3H53XX7YMBDZPMGLC","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":"12a239560e7e508922f57697f3895f4910f086e0bada96a69147e1eff9ed41f6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-17T03:24:38Z","title_canon_sha256":"a6ee1f1d251c6265de44f1ebc94303f2ce903af7feeb125174e5a2b22b88693f"},"schema_version":"1.0","source":{"id":"2006.09627","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.09627","created_at":"2026-07-05T02:34:40Z"},{"alias_kind":"arxiv_version","alias_value":"2006.09627v2","created_at":"2026-07-05T02:34:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09627","created_at":"2026-07-05T02:34:40Z"},{"alias_kind":"pith_short_12","alias_value":"SBT6JHMQT3H5","created_at":"2026-07-05T02:34:40Z"},{"alias_kind":"pith_short_16","alias_value":"SBT6JHMQT3H53XX7","created_at":"2026-07-05T02:34:40Z"},{"alias_kind":"pith_short_8","alias_value":"SBT6JHMQ","created_at":"2026-07-05T02:34:40Z"}],"graph_snapshots":[{"event_id":"sha256:ae9a5066272a99ccf000fd423eced1766a668e7cdd62562600279274e31d48db","target":"graph","created_at":"2026-07-05T02:34:40Z","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/2006.09627/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In low-resource natural language processing (NLP), the key problems are a lack of target language training data, and a lack of native speakers to create it. Cross-lingual methods have had notable success in addressing these concerns, but in certain common circumstances, such as insufficient pre-training corpora or languages far from the source language, their performance suffers. In this work we propose a complementary approach to building low-resource Named Entity Recognition (NER) models using ``non-speaker'' (NS) annotations, provided by annotators with no prior experience in the target lan","authors_text":"Dan Roth, Francesca Marini, Stephen Mayhew, Tatiana Tsygankova","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-17T03:24:38Z","title":"Building Low-Resource NER Models Using Non-Speaker Annotation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09627","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:ba49880e395b4dfa5a440e7c6b795fc24746d25d7980a3a6d38580a1e8b65599","target":"record","created_at":"2026-07-05T02:34:40Z","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":"12a239560e7e508922f57697f3895f4910f086e0bada96a69147e1eff9ed41f6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-17T03:24:38Z","title_canon_sha256":"a6ee1f1d251c6265de44f1ebc94303f2ce903af7feeb125174e5a2b22b88693f"},"schema_version":"1.0","source":{"id":"2006.09627","kind":"arxiv","version":2}},"canonical_sha256":"9067e49d909ecfdddeffc3023cbd865893e846cf75d5eb75448f6b16f98ccc2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9067e49d909ecfdddeffc3023cbd865893e846cf75d5eb75448f6b16f98ccc2e","first_computed_at":"2026-07-05T02:34:40.187758Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:34:40.187758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TOg3vScxnZsj9ACbJmwu5u4cCgc0IsarnkWX30Y6NoDdNlJ3DuDcVLAW5lHDPgy/NuDXqz0QMTS4C583L6t5DA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:34:40.188171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.09627","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba49880e395b4dfa5a440e7c6b795fc24746d25d7980a3a6d38580a1e8b65599","sha256:ae9a5066272a99ccf000fd423eced1766a668e7cdd62562600279274e31d48db"],"state_sha256":"8b0b80ba4d7bbdf7f85e5e1f7aeccf1426dd9c68ccb3d2947c5e9e94da86ebde"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+wG8FgdDadK0/rtkrc/6Pki6vkoXhNmijUjbuD5uwsg51ZoSVeyhzguFjyZ1926m+WrD3zx3GwYWgi6f1lGYCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T01:48:56.530472Z","bundle_sha256":"5d168e5f58f0902d346a1abb9868eeaad24a5b1738f7457a701fd28a351fe097"}}