{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:DVHYFAROCQXAKXOUJO5XUWNVAH","short_pith_number":"pith:DVHYFARO","canonical_record":{"source":{"id":"2012.02294","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2020-11-18T17:42:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"90131462d05a89cccc010030a24bd6919259e8c4f587ac7c3cce31ee38c57435","abstract_canon_sha256":"ae46a6bb2d632fef506f14af865beeffaca3e4af8fc382c85c068afc59bf7d0d"},"schema_version":"1.0"},"canonical_sha256":"1d4f82822e142e055dd44bbb7a59b501fb2346ffc643640a10ef438ef797d939","source":{"kind":"arxiv","id":"2012.02294","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.02294","created_at":"2026-07-05T01:56:58Z"},{"alias_kind":"arxiv_version","alias_value":"2012.02294v1","created_at":"2026-07-05T01:56:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02294","created_at":"2026-07-05T01:56:58Z"},{"alias_kind":"pith_short_12","alias_value":"DVHYFAROCQXA","created_at":"2026-07-05T01:56:58Z"},{"alias_kind":"pith_short_16","alias_value":"DVHYFAROCQXAKXOU","created_at":"2026-07-05T01:56:58Z"},{"alias_kind":"pith_short_8","alias_value":"DVHYFARO","created_at":"2026-07-05T01:56:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:DVHYFAROCQXAKXOUJO5XUWNVAH","target":"record","payload":{"canonical_record":{"source":{"id":"2012.02294","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2020-11-18T17:42:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"90131462d05a89cccc010030a24bd6919259e8c4f587ac7c3cce31ee38c57435","abstract_canon_sha256":"ae46a6bb2d632fef506f14af865beeffaca3e4af8fc382c85c068afc59bf7d0d"},"schema_version":"1.0"},"canonical_sha256":"1d4f82822e142e055dd44bbb7a59b501fb2346ffc643640a10ef438ef797d939","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:58.197479Z","signature_b64":"3uvDAQFcTuHpXrkFs8ntPRrNVy5SL6nTNV2AD76Jou2Ms4m9bVS9FJx7sH4TqggedYtO8ykYT05UepPu8jNoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d4f82822e142e055dd44bbb7a59b501fb2346ffc643640a10ef438ef797d939","last_reissued_at":"2026-07-05T01:56:58.197084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:58.197084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.02294","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":"2026-07-05T01:56:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pNg2XGWnwQM4PObL8z0Wtg/xEuo7xpvSOim9wqZDlNYaGvAopl/FCAbRY5lWrR2b5QEBn0FEQIUY84/WHFDzCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:56:05.586342Z"},"content_sha256":"e5cd7d6c57f4f6582f61a0d37661d176bd2f607724fb9698ef9529c7d4d277bc","schema_version":"1.0","event_id":"sha256:e5cd7d6c57f4f6582f61a0d37661d176bd2f607724fb9698ef9529c7d4d277bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:DVHYFAROCQXAKXOUJO5XUWNVAH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accelerating Text Mining Using Domain-Specific Stop Word Lists","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Alexander Herzog, Amy Apon, Farah Alshanik, Ilya Safro, Justin Sybrandt","submitted_at":"2020-11-18T17:42:32Z","abstract_excerpt":"Text preprocessing is an essential step in text mining. Removing words that can negatively impact the quality of prediction algorithms or are not informative enough is a crucial storage-saving technique in text indexing and results in improved computational efficiency. Typically, a generic stop word list is applied to a dataset regardless of the domain. However, many common words are different from one domain to another but have no significance within a particular domain. Eliminating domain-specific common words in a corpus reduces the dimensionality of the feature space, and improves the perf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02294","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/2012.02294/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":"2026-07-05T01:56:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mGRedaUxJxRFf6zux4BG2KeIgrV4IqMmGmx5guoAvVTmn4gPxgHxvXDWwcE+vPd82UbXFA8lQj5hxTLkk+biAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:56:05.586858Z"},"content_sha256":"a78a8c8e1ebd2bdc95456f48c012941a1929e894584251d9f6219deab79bb6d6","schema_version":"1.0","event_id":"sha256:a78a8c8e1ebd2bdc95456f48c012941a1929e894584251d9f6219deab79bb6d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DVHYFAROCQXAKXOUJO5XUWNVAH/bundle.json","state_url":"https://pith.science/pith/DVHYFAROCQXAKXOUJO5XUWNVAH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DVHYFAROCQXAKXOUJO5XUWNVAH/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":"2026-08-03T15:56:05Z","links":{"resolver":"https://pith.science/pith/DVHYFAROCQXAKXOUJO5XUWNVAH","bundle":"https://pith.science/pith/DVHYFAROCQXAKXOUJO5XUWNVAH/bundle.json","state":"https://pith.science/pith/DVHYFAROCQXAKXOUJO5XUWNVAH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DVHYFAROCQXAKXOUJO5XUWNVAH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:DVHYFAROCQXAKXOUJO5XUWNVAH","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":"ae46a6bb2d632fef506f14af865beeffaca3e4af8fc382c85c068afc59bf7d0d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2020-11-18T17:42:32Z","title_canon_sha256":"90131462d05a89cccc010030a24bd6919259e8c4f587ac7c3cce31ee38c57435"},"schema_version":"1.0","source":{"id":"2012.02294","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.02294","created_at":"2026-07-05T01:56:58Z"},{"alias_kind":"arxiv_version","alias_value":"2012.02294v1","created_at":"2026-07-05T01:56:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02294","created_at":"2026-07-05T01:56:58Z"},{"alias_kind":"pith_short_12","alias_value":"DVHYFAROCQXA","created_at":"2026-07-05T01:56:58Z"},{"alias_kind":"pith_short_16","alias_value":"DVHYFAROCQXAKXOU","created_at":"2026-07-05T01:56:58Z"},{"alias_kind":"pith_short_8","alias_value":"DVHYFARO","created_at":"2026-07-05T01:56:58Z"}],"graph_snapshots":[{"event_id":"sha256:a78a8c8e1ebd2bdc95456f48c012941a1929e894584251d9f6219deab79bb6d6","target":"graph","created_at":"2026-07-05T01:56:58Z","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/2012.02294/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text preprocessing is an essential step in text mining. Removing words that can negatively impact the quality of prediction algorithms or are not informative enough is a crucial storage-saving technique in text indexing and results in improved computational efficiency. Typically, a generic stop word list is applied to a dataset regardless of the domain. However, many common words are different from one domain to another but have no significance within a particular domain. Eliminating domain-specific common words in a corpus reduces the dimensionality of the feature space, and improves the perf","authors_text":"Alexander Herzog, Amy Apon, Farah Alshanik, Ilya Safro, Justin Sybrandt","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2020-11-18T17:42:32Z","title":"Accelerating Text Mining Using Domain-Specific Stop Word Lists"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02294","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:e5cd7d6c57f4f6582f61a0d37661d176bd2f607724fb9698ef9529c7d4d277bc","target":"record","created_at":"2026-07-05T01:56:58Z","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":"ae46a6bb2d632fef506f14af865beeffaca3e4af8fc382c85c068afc59bf7d0d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2020-11-18T17:42:32Z","title_canon_sha256":"90131462d05a89cccc010030a24bd6919259e8c4f587ac7c3cce31ee38c57435"},"schema_version":"1.0","source":{"id":"2012.02294","kind":"arxiv","version":1}},"canonical_sha256":"1d4f82822e142e055dd44bbb7a59b501fb2346ffc643640a10ef438ef797d939","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d4f82822e142e055dd44bbb7a59b501fb2346ffc643640a10ef438ef797d939","first_computed_at":"2026-07-05T01:56:58.197084Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:56:58.197084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3uvDAQFcTuHpXrkFs8ntPRrNVy5SL6nTNV2AD76Jou2Ms4m9bVS9FJx7sH4TqggedYtO8ykYT05UepPu8jNoDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:56:58.197479Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.02294","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5cd7d6c57f4f6582f61a0d37661d176bd2f607724fb9698ef9529c7d4d277bc","sha256:a78a8c8e1ebd2bdc95456f48c012941a1929e894584251d9f6219deab79bb6d6"],"state_sha256":"90978f14a773f3f03e218c555fc4e88512bf3bdfec7bf5ae8a5d8f935c4acfab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JzrLMywqywSqmy1BRGSaLbdaGeus7yQUBWHR5RdDuVucyHzlqW3E1horIW9slMfgbn/cTmoSAwXXqozBPogWDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:56:05.591710Z","bundle_sha256":"e8df9a384b484c0b9388cd967eb28f204f6b6c909a214d76a377eed6cc4402e5"}}