{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:YLLO6PI2FFLCXXI4GK5RU3XDF3","short_pith_number":"pith:YLLO6PI2","canonical_record":{"source":{"id":"1608.07836","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-28T17:51:41Z","cross_cats_sorted":[],"title_canon_sha256":"b59fb599bdf8936f3ae15fc8e086a214d99bf4b5e3e9cbec3bb1efe2c5208148","abstract_canon_sha256":"b185ac5d3489fa7f7d776d2422deb7832169b2493943abe2685c205d3445f199"},"schema_version":"1.0"},"canonical_sha256":"c2d6ef3d1a29562bdd1c32bb1a6ee32ee5f60af1d0e4b15a52e28301f7610e9b","source":{"kind":"arxiv","id":"1608.07836","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.07836","created_at":"2026-05-18T01:07:49Z"},{"alias_kind":"arxiv_version","alias_value":"1608.07836v1","created_at":"2026-05-18T01:07:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.07836","created_at":"2026-05-18T01:07:49Z"},{"alias_kind":"pith_short_12","alias_value":"YLLO6PI2FFLC","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"YLLO6PI2FFLCXXI4","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"YLLO6PI2","created_at":"2026-05-18T12:30:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:YLLO6PI2FFLCXXI4GK5RU3XDF3","target":"record","payload":{"canonical_record":{"source":{"id":"1608.07836","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-28T17:51:41Z","cross_cats_sorted":[],"title_canon_sha256":"b59fb599bdf8936f3ae15fc8e086a214d99bf4b5e3e9cbec3bb1efe2c5208148","abstract_canon_sha256":"b185ac5d3489fa7f7d776d2422deb7832169b2493943abe2685c205d3445f199"},"schema_version":"1.0"},"canonical_sha256":"c2d6ef3d1a29562bdd1c32bb1a6ee32ee5f60af1d0e4b15a52e28301f7610e9b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:07:49.796472Z","signature_b64":"m15JGhuYr3mQnH/7esN+rYBPRZuobmwa1zUryi9ew6kSOpNOPiHVNKOsNVO5WJdpsqrVcUYMYrfAbp0pU4vvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2d6ef3d1a29562bdd1c32bb1a6ee32ee5f60af1d0e4b15a52e28301f7610e9b","last_reissued_at":"2026-05-18T01:07:49.795926Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:07:49.795926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1608.07836","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":"2026-05-18T01:07:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ULrWLaPN6qqP2BrOPKf2+8HyesCDgb9p/aYmnCLP0xBdXVMsPe/2zy9WAzZ9QKGnE2uPQKuAH2jtdpOuobT4AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T11:02:00.161442Z"},"content_sha256":"3662941a52e101b63fb3f6c35d485956e53c775530d70fa26bbf66e4e495bb2e","schema_version":"1.0","event_id":"sha256:3662941a52e101b63fb3f6c35d485956e53c775530d70fa26bbf66e4e495bb2e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:YLLO6PI2FFLCXXI4GK5RU3XDF3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What to do about non-standard (or non-canonical) language in NLP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barbara Plank","submitted_at":"2016-08-28T17:51:41Z","abstract_excerpt":"Real world data differs radically from the benchmark corpora we use in natural language processing (NLP). As soon as we apply our technologies to the real world, performance drops. The reason for this problem is obvious: NLP models are trained on samples from a limited set of canonical varieties that are considered standard, most prominently English newswire. However, there are many dimensions, e.g., socio-demographics, language, genre, sentence type, etc. on which texts can differ from the standard. The solution is not obvious: we cannot control for all factors, and it is not clear how to bes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.07836","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":""},"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":"2026-05-18T01:07:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YHBMqLJ2aGSoKhuS8amfvEqpSrUudB/I+Xl00bz/n9Qy1zxrWNcYGuMgeCA7X0/OvZ1rZHnpnSnYwiDV9/ovBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T11:02:00.162099Z"},"content_sha256":"7024523a65ab0fe8a9053d9cd168b5d94aefe723efbe6bc537e8df35a2063330","schema_version":"1.0","event_id":"sha256:7024523a65ab0fe8a9053d9cd168b5d94aefe723efbe6bc537e8df35a2063330"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YLLO6PI2FFLCXXI4GK5RU3XDF3/bundle.json","state_url":"https://pith.science/pith/YLLO6PI2FFLCXXI4GK5RU3XDF3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YLLO6PI2FFLCXXI4GK5RU3XDF3/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":"2026-06-07T11:02:00Z","links":{"resolver":"https://pith.science/pith/YLLO6PI2FFLCXXI4GK5RU3XDF3","bundle":"https://pith.science/pith/YLLO6PI2FFLCXXI4GK5RU3XDF3/bundle.json","state":"https://pith.science/pith/YLLO6PI2FFLCXXI4GK5RU3XDF3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YLLO6PI2FFLCXXI4GK5RU3XDF3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:YLLO6PI2FFLCXXI4GK5RU3XDF3","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":"b185ac5d3489fa7f7d776d2422deb7832169b2493943abe2685c205d3445f199","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-28T17:51:41Z","title_canon_sha256":"b59fb599bdf8936f3ae15fc8e086a214d99bf4b5e3e9cbec3bb1efe2c5208148"},"schema_version":"1.0","source":{"id":"1608.07836","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.07836","created_at":"2026-05-18T01:07:49Z"},{"alias_kind":"arxiv_version","alias_value":"1608.07836v1","created_at":"2026-05-18T01:07:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.07836","created_at":"2026-05-18T01:07:49Z"},{"alias_kind":"pith_short_12","alias_value":"YLLO6PI2FFLC","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"YLLO6PI2FFLCXXI4","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"YLLO6PI2","created_at":"2026-05-18T12:30:53Z"}],"graph_snapshots":[{"event_id":"sha256:7024523a65ab0fe8a9053d9cd168b5d94aefe723efbe6bc537e8df35a2063330","target":"graph","created_at":"2026-05-18T01:07:49Z","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"},"paper":{"abstract_excerpt":"Real world data differs radically from the benchmark corpora we use in natural language processing (NLP). As soon as we apply our technologies to the real world, performance drops. The reason for this problem is obvious: NLP models are trained on samples from a limited set of canonical varieties that are considered standard, most prominently English newswire. However, there are many dimensions, e.g., socio-demographics, language, genre, sentence type, etc. on which texts can differ from the standard. The solution is not obvious: we cannot control for all factors, and it is not clear how to bes","authors_text":"Barbara Plank","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-28T17:51:41Z","title":"What to do about non-standard (or non-canonical) language in NLP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.07836","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":"sha256:3662941a52e101b63fb3f6c35d485956e53c775530d70fa26bbf66e4e495bb2e","target":"record","created_at":"2026-05-18T01:07:49Z","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":"b185ac5d3489fa7f7d776d2422deb7832169b2493943abe2685c205d3445f199","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-28T17:51:41Z","title_canon_sha256":"b59fb599bdf8936f3ae15fc8e086a214d99bf4b5e3e9cbec3bb1efe2c5208148"},"schema_version":"1.0","source":{"id":"1608.07836","kind":"arxiv","version":1}},"canonical_sha256":"c2d6ef3d1a29562bdd1c32bb1a6ee32ee5f60af1d0e4b15a52e28301f7610e9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2d6ef3d1a29562bdd1c32bb1a6ee32ee5f60af1d0e4b15a52e28301f7610e9b","first_computed_at":"2026-05-18T01:07:49.795926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:07:49.795926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m15JGhuYr3mQnH/7esN+rYBPRZuobmwa1zUryi9ew6kSOpNOPiHVNKOsNVO5WJdpsqrVcUYMYrfAbp0pU4vvBw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:07:49.796472Z","signed_message":"canonical_sha256_bytes"},"source_id":"1608.07836","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3662941a52e101b63fb3f6c35d485956e53c775530d70fa26bbf66e4e495bb2e","sha256:7024523a65ab0fe8a9053d9cd168b5d94aefe723efbe6bc537e8df35a2063330"],"state_sha256":"69954ae22536b0635110dde748f28467125e480e554778a9d922e10e7201d90b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yNa+U9N4FUdHnRacVBytHeqOKh5F4YljPMyoRGfN+RK+54vZnrP5wVpVB7xqa/l1RH+oQqZdk3IBDdQtpxwOAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T11:02:00.165764Z","bundle_sha256":"ef425021eb4b966aac1a1308503a897f976684c09b60a67c403dd78816459384"}}