{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:3JNURX6S57DQE2LD4OZYKFGGPV","short_pith_number":"pith:3JNURX6S","schema_version":"1.0","canonical_sha256":"da5b48dfd2efc7026963e3b38514c67d5c9e0d6c049a00b1b04cbb7370f53df7","source":{"kind":"arxiv","id":"1510.00772","version":1},"attestation_state":"computed","paper":{"title":"Machine Learning for Machine Data from a CATI Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Sou-Cheng T. Choi","submitted_at":"2015-10-03T02:57:47Z","abstract_excerpt":"This is a machine learning application paper involving big data. We present high-accuracy prediction methods of rare events in semi-structured machine log files, which are produced at high velocity and high volume by NORC's computer-assisted telephone interviewing (CATI) network for conducting surveys. We judiciously apply natural language processing (NLP) techniques and data-mining strategies to train effective learning and prediction models for classifying uncommon error messages in the log---without access to source code, updated documentation or dictionaries. In particular, our simple but "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1510.00772","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-03T02:57:47Z","cross_cats_sorted":[],"title_canon_sha256":"15d8fa5b588ff5e0df1ad8872ab376466a8424478b72d03a645605ee5ce4f8e4","abstract_canon_sha256":"2f5a4d5d3296ccffb62666959f9bec867d4c5de95145e1f460e66e2912aaac09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:31:05.756786Z","signature_b64":"oRk6o2wRcC7RAoNe72DsxPD/VT9AjUcCZ/ZdwwpZWuZZPRvrWdmx1MU+WC+5MwmR56TykI7BY1r5rMZu6bBSCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da5b48dfd2efc7026963e3b38514c67d5c9e0d6c049a00b1b04cbb7370f53df7","last_reissued_at":"2026-05-18T01:31:05.756046Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:31:05.756046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine Learning for Machine Data from a CATI Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Sou-Cheng T. Choi","submitted_at":"2015-10-03T02:57:47Z","abstract_excerpt":"This is a machine learning application paper involving big data. We present high-accuracy prediction methods of rare events in semi-structured machine log files, which are produced at high velocity and high volume by NORC's computer-assisted telephone interviewing (CATI) network for conducting surveys. We judiciously apply natural language processing (NLP) techniques and data-mining strategies to train effective learning and prediction models for classifying uncommon error messages in the log---without access to source code, updated documentation or dictionaries. In particular, our simple but "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.00772","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1510.00772","created_at":"2026-05-18T01:31:05.756166+00:00"},{"alias_kind":"arxiv_version","alias_value":"1510.00772v1","created_at":"2026-05-18T01:31:05.756166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.00772","created_at":"2026-05-18T01:31:05.756166+00:00"},{"alias_kind":"pith_short_12","alias_value":"3JNURX6S57DQ","created_at":"2026-05-18T12:29:02.477457+00:00"},{"alias_kind":"pith_short_16","alias_value":"3JNURX6S57DQE2LD","created_at":"2026-05-18T12:29:02.477457+00:00"},{"alias_kind":"pith_short_8","alias_value":"3JNURX6S","created_at":"2026-05-18T12:29:02.477457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3JNURX6S57DQE2LD4OZYKFGGPV","json":"https://pith.science/pith/3JNURX6S57DQE2LD4OZYKFGGPV.json","graph_json":"https://pith.science/api/pith-number/3JNURX6S57DQE2LD4OZYKFGGPV/graph.json","events_json":"https://pith.science/api/pith-number/3JNURX6S57DQE2LD4OZYKFGGPV/events.json","paper":"https://pith.science/paper/3JNURX6S"},"agent_actions":{"view_html":"https://pith.science/pith/3JNURX6S57DQE2LD4OZYKFGGPV","download_json":"https://pith.science/pith/3JNURX6S57DQE2LD4OZYKFGGPV.json","view_paper":"https://pith.science/paper/3JNURX6S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1510.00772&json=true","fetch_graph":"https://pith.science/api/pith-number/3JNURX6S57DQE2LD4OZYKFGGPV/graph.json","fetch_events":"https://pith.science/api/pith-number/3JNURX6S57DQE2LD4OZYKFGGPV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3JNURX6S57DQE2LD4OZYKFGGPV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3JNURX6S57DQE2LD4OZYKFGGPV/action/storage_attestation","attest_author":"https://pith.science/pith/3JNURX6S57DQE2LD4OZYKFGGPV/action/author_attestation","sign_citation":"https://pith.science/pith/3JNURX6S57DQE2LD4OZYKFGGPV/action/citation_signature","submit_replication":"https://pith.science/pith/3JNURX6S57DQE2LD4OZYKFGGPV/action/replication_record"}},"created_at":"2026-05-18T01:31:05.756166+00:00","updated_at":"2026-05-18T01:31:05.756166+00:00"}