{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:3JNURX6S57DQE2LD4OZYKFGGPV","short_pith_number":"pith:3JNURX6S","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"},"canonical_sha256":"da5b48dfd2efc7026963e3b38514c67d5c9e0d6c049a00b1b04cbb7370f53df7","source":{"kind":"arxiv","id":"1510.00772","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1510.00772","created_at":"2026-05-18T01:31:05Z"},{"alias_kind":"arxiv_version","alias_value":"1510.00772v1","created_at":"2026-05-18T01:31:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.00772","created_at":"2026-05-18T01:31:05Z"},{"alias_kind":"pith_short_12","alias_value":"3JNURX6S57DQ","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"3JNURX6S57DQE2LD","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"3JNURX6S","created_at":"2026-05-18T12:29:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:3JNURX6S57DQE2LD4OZYKFGGPV","target":"record","payload":{"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"},"canonical_sha256":"da5b48dfd2efc7026963e3b38514c67d5c9e0d6c049a00b1b04cbb7370f53df7","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"},"source_kind":"arxiv","source_id":"1510.00772","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":"2026-05-18T01:31:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+cAXXV90Df2wRnW9ChoYBvMWg8ERACkArqlyyaMGawsIVJKSdSk2E4JUYrHqkAZoyKEVtM79BuJ7JFM/gSKUCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T23:29:05.356995Z"},"content_sha256":"cc3df4d5c82b829d5ba6311d1f468d51a0d7da0020efa98428ebf7cfa55cd5c4","schema_version":"1.0","event_id":"sha256:cc3df4d5c82b829d5ba6311d1f468d51a0d7da0020efa98428ebf7cfa55cd5c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:3JNURX6S57DQE2LD4OZYKFGGPV","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:31:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2c7gF/dNeq3Kl2Wn6y3tclx5cE1koWCdVsbbH2Z4oM0wp8ZYfZacjkLkRHwQtUad0ByroSbe1g2WNRDkK4fFDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T23:29:05.357347Z"},"content_sha256":"6796f3b0142263a8c71e780590daecd9049d423c337f67fb9bf9720110075f5b","schema_version":"1.0","event_id":"sha256:6796f3b0142263a8c71e780590daecd9049d423c337f67fb9bf9720110075f5b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3JNURX6S57DQE2LD4OZYKFGGPV/bundle.json","state_url":"https://pith.science/pith/3JNURX6S57DQE2LD4OZYKFGGPV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3JNURX6S57DQE2LD4OZYKFGGPV/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":"2026-07-02T23:29:05Z","links":{"resolver":"https://pith.science/pith/3JNURX6S57DQE2LD4OZYKFGGPV","bundle":"https://pith.science/pith/3JNURX6S57DQE2LD4OZYKFGGPV/bundle.json","state":"https://pith.science/pith/3JNURX6S57DQE2LD4OZYKFGGPV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3JNURX6S57DQE2LD4OZYKFGGPV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:3JNURX6S57DQE2LD4OZYKFGGPV","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":"2f5a4d5d3296ccffb62666959f9bec867d4c5de95145e1f460e66e2912aaac09","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-03T02:57:47Z","title_canon_sha256":"15d8fa5b588ff5e0df1ad8872ab376466a8424478b72d03a645605ee5ce4f8e4"},"schema_version":"1.0","source":{"id":"1510.00772","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1510.00772","created_at":"2026-05-18T01:31:05Z"},{"alias_kind":"arxiv_version","alias_value":"1510.00772v1","created_at":"2026-05-18T01:31:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.00772","created_at":"2026-05-18T01:31:05Z"},{"alias_kind":"pith_short_12","alias_value":"3JNURX6S57DQ","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"3JNURX6S57DQE2LD","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"3JNURX6S","created_at":"2026-05-18T12:29:02Z"}],"graph_snapshots":[{"event_id":"sha256:6796f3b0142263a8c71e780590daecd9049d423c337f67fb9bf9720110075f5b","target":"graph","created_at":"2026-05-18T01:31:05Z","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":"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 ","authors_text":"Sou-Cheng T. Choi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-03T02:57:47Z","title":"Machine Learning for Machine Data from a CATI Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.00772","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:cc3df4d5c82b829d5ba6311d1f468d51a0d7da0020efa98428ebf7cfa55cd5c4","target":"record","created_at":"2026-05-18T01:31:05Z","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":"2f5a4d5d3296ccffb62666959f9bec867d4c5de95145e1f460e66e2912aaac09","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-03T02:57:47Z","title_canon_sha256":"15d8fa5b588ff5e0df1ad8872ab376466a8424478b72d03a645605ee5ce4f8e4"},"schema_version":"1.0","source":{"id":"1510.00772","kind":"arxiv","version":1}},"canonical_sha256":"da5b48dfd2efc7026963e3b38514c67d5c9e0d6c049a00b1b04cbb7370f53df7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da5b48dfd2efc7026963e3b38514c67d5c9e0d6c049a00b1b04cbb7370f53df7","first_computed_at":"2026-05-18T01:31:05.756046Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:31:05.756046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oRk6o2wRcC7RAoNe72DsxPD/VT9AjUcCZ/ZdwwpZWuZZPRvrWdmx1MU+WC+5MwmR56TykI7BY1r5rMZu6bBSCA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:31:05.756786Z","signed_message":"canonical_sha256_bytes"},"source_id":"1510.00772","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc3df4d5c82b829d5ba6311d1f468d51a0d7da0020efa98428ebf7cfa55cd5c4","sha256:6796f3b0142263a8c71e780590daecd9049d423c337f67fb9bf9720110075f5b"],"state_sha256":"1c07634e834e11aa9fc4c2c4878077fb461ccad75f1d640d8ea67a1c9164e286"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dJ0nPZaobfQ4zaeynkqbpOouUqG4ZRdiKrs99DoGK1iNKliB9k83pAhEVFQeIOgbYWEDuIu4gIkUo9EBkATXDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T23:29:05.359261Z","bundle_sha256":"a54cce8e881d23d0693dcad1d0f99bfff956d4db825047956aefd87ee0ad849e"}}