{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:UERAOGVSFQWAMPGRHLNJYPE2UB","short_pith_number":"pith:UERAOGVS","canonical_record":{"source":{"id":"1909.09389","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-09-20T09:35:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"eb98bb2e4d46ec9d6d114bde3c3c7c4f63b2f8b1017c41ac019710bc297dd67d","abstract_canon_sha256":"b72a250cb1dd2ebbd8edf03fc7b639785767bc4e3d42a8e6360028ce92a15423"},"schema_version":"1.0"},"canonical_sha256":"a122071ab22c2c063cd13ada9c3c9aa058e574ebc61a420f59fe748def079b55","source":{"kind":"arxiv","id":"1909.09389","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.09389","created_at":"2026-07-05T00:05:59Z"},{"alias_kind":"arxiv_version","alias_value":"1909.09389v1","created_at":"2026-07-05T00:05:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.09389","created_at":"2026-07-05T00:05:59Z"},{"alias_kind":"pith_short_12","alias_value":"UERAOGVSFQWA","created_at":"2026-07-05T00:05:59Z"},{"alias_kind":"pith_short_16","alias_value":"UERAOGVSFQWAMPGR","created_at":"2026-07-05T00:05:59Z"},{"alias_kind":"pith_short_8","alias_value":"UERAOGVS","created_at":"2026-07-05T00:05:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:UERAOGVSFQWAMPGRHLNJYPE2UB","target":"record","payload":{"canonical_record":{"source":{"id":"1909.09389","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-09-20T09:35:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"eb98bb2e4d46ec9d6d114bde3c3c7c4f63b2f8b1017c41ac019710bc297dd67d","abstract_canon_sha256":"b72a250cb1dd2ebbd8edf03fc7b639785767bc4e3d42a8e6360028ce92a15423"},"schema_version":"1.0"},"canonical_sha256":"a122071ab22c2c063cd13ada9c3c9aa058e574ebc61a420f59fe748def079b55","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:05:59.259556Z","signature_b64":"E6z5aqV8Yc6CTvRuVY0eGUjfcmMEBGZ6WYeQM5giHoJ9Jkrmdu1OHgWZNJpcyBbGu7XkOEW9p0LpiSYK3S+rDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a122071ab22c2c063cd13ada9c3c9aa058e574ebc61a420f59fe748def079b55","last_reissued_at":"2026-07-05T00:05:59.259166Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:05:59.259166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.09389","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":"2026-07-05T00:05:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iC2++Xrs1xPVR+hdt0KF7DfvGE5N677XfteK4S410t0OuP94j/2fW6M8MhkmS3te/pzzlHR+Yt2Lg8vP0fXYBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:45:32.678461Z"},"content_sha256":"59ac7b4b54e7d05810d30bc664d038a69fa1b22cf85ddceba83263415b99f8d4","schema_version":"1.0","event_id":"sha256:59ac7b4b54e7d05810d30bc664d038a69fa1b22cf85ddceba83263415b99f8d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:UERAOGVSFQWAMPGRHLNJYPE2UB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sampling Bias in Deep Active Classification: An Empirical Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ameya Prabhu, Charles Dognin, Maneesh Singh","submitted_at":"2019-09-20T09:35:20Z","abstract_excerpt":"The exploding cost and time needed for data labeling and model training are bottlenecks for training DNN models on large datasets. Identifying smaller representative data samples with strategies like active learning can help mitigate such bottlenecks. Previous works on active learning in NLP identify the problem of sampling bias in the samples acquired by uncertainty-based querying and develop costly approaches to address it. Using a large empirical study, we demonstrate that active set selection using the posterior entropy of deep models like FastText.zip (FTZ) is robust to sampling biases an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.09389","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/1909.09389/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":"2026-07-05T00:05:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cpYC9Kf+vTzFY9c9ewb4kX+hqg1/c6DGd7kI29qAg4YMIp4XTuhdvgFXhLR7LHi1OdVP3CYmeDOEmW8tE4c9Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:45:32.678984Z"},"content_sha256":"c56dd7b8d3662326d998f5860fae7fed9bea54dadf0e34acd0c0631409afe558","schema_version":"1.0","event_id":"sha256:c56dd7b8d3662326d998f5860fae7fed9bea54dadf0e34acd0c0631409afe558"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UERAOGVSFQWAMPGRHLNJYPE2UB/bundle.json","state_url":"https://pith.science/pith/UERAOGVSFQWAMPGRHLNJYPE2UB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UERAOGVSFQWAMPGRHLNJYPE2UB/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":"2026-08-09T22:45:32Z","links":{"resolver":"https://pith.science/pith/UERAOGVSFQWAMPGRHLNJYPE2UB","bundle":"https://pith.science/pith/UERAOGVSFQWAMPGRHLNJYPE2UB/bundle.json","state":"https://pith.science/pith/UERAOGVSFQWAMPGRHLNJYPE2UB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UERAOGVSFQWAMPGRHLNJYPE2UB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UERAOGVSFQWAMPGRHLNJYPE2UB","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":"b72a250cb1dd2ebbd8edf03fc7b639785767bc4e3d42a8e6360028ce92a15423","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-09-20T09:35:20Z","title_canon_sha256":"eb98bb2e4d46ec9d6d114bde3c3c7c4f63b2f8b1017c41ac019710bc297dd67d"},"schema_version":"1.0","source":{"id":"1909.09389","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.09389","created_at":"2026-07-05T00:05:59Z"},{"alias_kind":"arxiv_version","alias_value":"1909.09389v1","created_at":"2026-07-05T00:05:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.09389","created_at":"2026-07-05T00:05:59Z"},{"alias_kind":"pith_short_12","alias_value":"UERAOGVSFQWA","created_at":"2026-07-05T00:05:59Z"},{"alias_kind":"pith_short_16","alias_value":"UERAOGVSFQWAMPGR","created_at":"2026-07-05T00:05:59Z"},{"alias_kind":"pith_short_8","alias_value":"UERAOGVS","created_at":"2026-07-05T00:05:59Z"}],"graph_snapshots":[{"event_id":"sha256:c56dd7b8d3662326d998f5860fae7fed9bea54dadf0e34acd0c0631409afe558","target":"graph","created_at":"2026-07-05T00:05:59Z","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/1909.09389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The exploding cost and time needed for data labeling and model training are bottlenecks for training DNN models on large datasets. Identifying smaller representative data samples with strategies like active learning can help mitigate such bottlenecks. Previous works on active learning in NLP identify the problem of sampling bias in the samples acquired by uncertainty-based querying and develop costly approaches to address it. Using a large empirical study, we demonstrate that active set selection using the posterior entropy of deep models like FastText.zip (FTZ) is robust to sampling biases an","authors_text":"Ameya Prabhu, Charles Dognin, Maneesh Singh","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-09-20T09:35:20Z","title":"Sampling Bias in Deep Active Classification: An Empirical Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.09389","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":"sha256:59ac7b4b54e7d05810d30bc664d038a69fa1b22cf85ddceba83263415b99f8d4","target":"record","created_at":"2026-07-05T00:05:59Z","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":"b72a250cb1dd2ebbd8edf03fc7b639785767bc4e3d42a8e6360028ce92a15423","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-09-20T09:35:20Z","title_canon_sha256":"eb98bb2e4d46ec9d6d114bde3c3c7c4f63b2f8b1017c41ac019710bc297dd67d"},"schema_version":"1.0","source":{"id":"1909.09389","kind":"arxiv","version":1}},"canonical_sha256":"a122071ab22c2c063cd13ada9c3c9aa058e574ebc61a420f59fe748def079b55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a122071ab22c2c063cd13ada9c3c9aa058e574ebc61a420f59fe748def079b55","first_computed_at":"2026-07-05T00:05:59.259166Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:05:59.259166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E6z5aqV8Yc6CTvRuVY0eGUjfcmMEBGZ6WYeQM5giHoJ9Jkrmdu1OHgWZNJpcyBbGu7XkOEW9p0LpiSYK3S+rDw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:05:59.259556Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.09389","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59ac7b4b54e7d05810d30bc664d038a69fa1b22cf85ddceba83263415b99f8d4","sha256:c56dd7b8d3662326d998f5860fae7fed9bea54dadf0e34acd0c0631409afe558"],"state_sha256":"997ad3e4886ee98b864f718e09f796beaa69f9a6339acf9c90c534d82ea19d1e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1EYZxxO5y9rF5VKmCPxvTmnefbuAC6uf2XM31XGrai5v8qLs91cJo+K2/4Gq+jE6cyUwRWt99QgeimzvGiTRCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:45:32.683118Z","bundle_sha256":"0449f8c1108e215bed7e69974ffac957e9ca64e8a6c48f7ba4b3fe44cda25992"}}