{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ISMDEYY5I2JL35B6TNNTKD7J5L","short_pith_number":"pith:ISMDEYY5","canonical_record":{"source":{"id":"1809.04019","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-09-11T16:43:52Z","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"title_canon_sha256":"6b1357d419141c6d1995ae2819305d9dbab86c1ca8dca5be35997106936edb75","abstract_canon_sha256":"3578b97b48c8d645313b40b14d24abd4b0e1dfd2a3bb6195d14b6cc78577d510"},"schema_version":"1.0"},"canonical_sha256":"449832631d4692bdf43e9b5b350fe9ead882ffaa1c5a185a1a6d158a7aaed4ee","source":{"kind":"arxiv","id":"1809.04019","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04019","created_at":"2026-05-18T00:05:57Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04019v1","created_at":"2026-05-18T00:05:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04019","created_at":"2026-05-18T00:05:57Z"},{"alias_kind":"pith_short_12","alias_value":"ISMDEYY5I2JL","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"ISMDEYY5I2JL35B6","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"ISMDEYY5","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ISMDEYY5I2JL35B6TNNTKD7J5L","target":"record","payload":{"canonical_record":{"source":{"id":"1809.04019","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-09-11T16:43:52Z","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"title_canon_sha256":"6b1357d419141c6d1995ae2819305d9dbab86c1ca8dca5be35997106936edb75","abstract_canon_sha256":"3578b97b48c8d645313b40b14d24abd4b0e1dfd2a3bb6195d14b6cc78577d510"},"schema_version":"1.0"},"canonical_sha256":"449832631d4692bdf43e9b5b350fe9ead882ffaa1c5a185a1a6d158a7aaed4ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:57.515473Z","signature_b64":"JRJtVnZV4GskCuvmgtZbDf/YQY37KXBKCxc+/g2F6zkpVmkOiJXtiBna0KaO08qbihCkD1qrOrFGLUhwcG1LDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"449832631d4692bdf43e9b5b350fe9ead882ffaa1c5a185a1a6d158a7aaed4ee","last_reissued_at":"2026-05-18T00:05:57.514984Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:57.514984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.04019","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":"2026-05-18T00:05:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iC8dzNAFRyXixGkegDo6zP/+OJZGudxUpiRQH3svpM0/vpeGI4XLOfLVhofjKM4+cV9ZcCKeMGivDVJZJsXHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T21:38:31.808467Z"},"content_sha256":"13215bcf9f131b81454059768b4a6ef9b3c6c1ab792382dfd31740767f8198fc","schema_version":"1.0","event_id":"sha256:13215bcf9f131b81454059768b4a6ef9b3c6c1ab792382dfd31740767f8198fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ISMDEYY5I2JL35B6TNNTKD7J5L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training and Prediction Data Discrepancies: Challenges of Text Classification with Noisy, Historical Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","stat.ML"],"primary_cat":"cs.IR","authors_text":"Emilia Apostolova, R. Andrew Kreek","submitted_at":"2018-09-11T16:43:52Z","abstract_excerpt":"Industry datasets used for text classification are rarely created for that purpose. In most cases, the data and target predictions are a by-product of accumulated historical data, typically fraught with noise, present in both the text-based document, as well as in the targeted labels. In this work, we address the question of how well performance metrics computed on noisy, historical data reflect the performance on the intended future machine learning model input. The results demonstrate the utility of dirty training datasets used to build prediction models for cleaner (and different) predictio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04019","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":"2026-05-18T00:05:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SUHmwNuU6G16A3WNWWXq8sLEkus/BsImLK2NMXhholrl4p0VRzkGaJOm8kq9mGuBm/W/YhyFzbrNk/5UGS8hCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T21:38:31.808815Z"},"content_sha256":"78ae29e93bd814f50052e9fc269aaf5015b33f5a860cf07a83b3417f8dd237c5","schema_version":"1.0","event_id":"sha256:78ae29e93bd814f50052e9fc269aaf5015b33f5a860cf07a83b3417f8dd237c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ISMDEYY5I2JL35B6TNNTKD7J5L/bundle.json","state_url":"https://pith.science/pith/ISMDEYY5I2JL35B6TNNTKD7J5L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ISMDEYY5I2JL35B6TNNTKD7J5L/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":"2026-08-21T21:38:31Z","links":{"resolver":"https://pith.science/pith/ISMDEYY5I2JL35B6TNNTKD7J5L","bundle":"https://pith.science/pith/ISMDEYY5I2JL35B6TNNTKD7J5L/bundle.json","state":"https://pith.science/pith/ISMDEYY5I2JL35B6TNNTKD7J5L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ISMDEYY5I2JL35B6TNNTKD7J5L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ISMDEYY5I2JL35B6TNNTKD7J5L","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":"3578b97b48c8d645313b40b14d24abd4b0e1dfd2a3bb6195d14b6cc78577d510","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-09-11T16:43:52Z","title_canon_sha256":"6b1357d419141c6d1995ae2819305d9dbab86c1ca8dca5be35997106936edb75"},"schema_version":"1.0","source":{"id":"1809.04019","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04019","created_at":"2026-05-18T00:05:57Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04019v1","created_at":"2026-05-18T00:05:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04019","created_at":"2026-05-18T00:05:57Z"},{"alias_kind":"pith_short_12","alias_value":"ISMDEYY5I2JL","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"ISMDEYY5I2JL35B6","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"ISMDEYY5","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:78ae29e93bd814f50052e9fc269aaf5015b33f5a860cf07a83b3417f8dd237c5","target":"graph","created_at":"2026-05-18T00:05:57Z","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":"Industry datasets used for text classification are rarely created for that purpose. In most cases, the data and target predictions are a by-product of accumulated historical data, typically fraught with noise, present in both the text-based document, as well as in the targeted labels. In this work, we address the question of how well performance metrics computed on noisy, historical data reflect the performance on the intended future machine learning model input. The results demonstrate the utility of dirty training datasets used to build prediction models for cleaner (and different) predictio","authors_text":"Emilia Apostolova, R. Andrew Kreek","cross_cats":["cs.CL","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-09-11T16:43:52Z","title":"Training and Prediction Data Discrepancies: Challenges of Text Classification with Noisy, Historical Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04019","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":"sha256:13215bcf9f131b81454059768b4a6ef9b3c6c1ab792382dfd31740767f8198fc","target":"record","created_at":"2026-05-18T00:05:57Z","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":"3578b97b48c8d645313b40b14d24abd4b0e1dfd2a3bb6195d14b6cc78577d510","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-09-11T16:43:52Z","title_canon_sha256":"6b1357d419141c6d1995ae2819305d9dbab86c1ca8dca5be35997106936edb75"},"schema_version":"1.0","source":{"id":"1809.04019","kind":"arxiv","version":1}},"canonical_sha256":"449832631d4692bdf43e9b5b350fe9ead882ffaa1c5a185a1a6d158a7aaed4ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"449832631d4692bdf43e9b5b350fe9ead882ffaa1c5a185a1a6d158a7aaed4ee","first_computed_at":"2026-05-18T00:05:57.514984Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:57.514984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JRJtVnZV4GskCuvmgtZbDf/YQY37KXBKCxc+/g2F6zkpVmkOiJXtiBna0KaO08qbihCkD1qrOrFGLUhwcG1LDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:57.515473Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.04019","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13215bcf9f131b81454059768b4a6ef9b3c6c1ab792382dfd31740767f8198fc","sha256:78ae29e93bd814f50052e9fc269aaf5015b33f5a860cf07a83b3417f8dd237c5"],"state_sha256":"fc173f8ce47f58bef6bd599e5588e3a18611feb1c54cd76bd8837e99539c6e66"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rsNxst/vONB5kNDLVRhVtuEf7yDzhU6mlj6YXoenN0GjR8SA3dCb7PRkXa2FTYv5wlaoh7M3o8ShUlsmx7zdCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T21:38:31.811515Z","bundle_sha256":"050529a57e60954b288fd135f4df38834896a8ee0e26aa7474d469a39663bae7"}}