{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:1994:OZ7SIHYOC2WFXMIPJR7HV3CP2A","short_pith_number":"pith:OZ7SIHYO","canonical_record":{"source":{"id":"cmp-lg/9407020","kind":"arxiv","version":2},"metadata":{"license":"","primary_cat":"cmp-lg","submitted_at":"1994-07-24T13:38:00Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8d63d18b4463a57e14eb83356b2f93bd3887e34e75e96eb0b5a1e89f68c1007c","abstract_canon_sha256":"c4dc3e25da483fcfe7a3b22ad7cd3e2b3f7a9c3caeed9643e5e6c5eea720a7c3"},"schema_version":"1.0"},"canonical_sha256":"767f241f0e16ac5bb10f4c7e7aec4fd01791f081e08e0c0854e52e9020ade5cf","source":{"kind":"arxiv","id":"cmp-lg/9407020","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cmp-lg/9407020","created_at":"2026-07-04T15:07:19Z"},{"alias_kind":"arxiv_version","alias_value":"cmp-lg/9407020v2","created_at":"2026-07-04T15:07:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cmp-lg/9407020","created_at":"2026-07-04T15:07:19Z"},{"alias_kind":"pith_short_12","alias_value":"OZ7SIHYOC2WF","created_at":"2026-07-04T15:07:19Z"},{"alias_kind":"pith_short_16","alias_value":"OZ7SIHYOC2WFXMIP","created_at":"2026-07-04T15:07:19Z"},{"alias_kind":"pith_short_8","alias_value":"OZ7SIHYO","created_at":"2026-07-04T15:07:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:1994:OZ7SIHYOC2WFXMIPJR7HV3CP2A","target":"record","payload":{"canonical_record":{"source":{"id":"cmp-lg/9407020","kind":"arxiv","version":2},"metadata":{"license":"","primary_cat":"cmp-lg","submitted_at":"1994-07-24T13:38:00Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8d63d18b4463a57e14eb83356b2f93bd3887e34e75e96eb0b5a1e89f68c1007c","abstract_canon_sha256":"c4dc3e25da483fcfe7a3b22ad7cd3e2b3f7a9c3caeed9643e5e6c5eea720a7c3"},"schema_version":"1.0"},"canonical_sha256":"767f241f0e16ac5bb10f4c7e7aec4fd01791f081e08e0c0854e52e9020ade5cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T15:07:19.193781Z","signature_b64":"Mybs/ctczFyGD6wcDenZ+aVPm5GiiJPCzQx4EGnfxWazEU2DUQGKmcw2nAvxfaQ4FjUbPMS65uvGaJOD65jhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"767f241f0e16ac5bb10f4c7e7aec4fd01791f081e08e0c0854e52e9020ade5cf","last_reissued_at":"2026-07-04T15:07:19.193304Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T15:07:19.193304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"cmp-lg/9407020","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T15:07:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DGWk8PzKEJP9UhHAqjzGhWAJzyQdwx82vNLOy8Je+GSp4D+zQwXtFYtyC8dl7jfez0uz7NHyKvqjDD9OQ06iBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:42:15.345085Z"},"content_sha256":"4b5052772dfc19ed3226c0ad60dc7427c9be771b8da765454c7887ccb7416629","schema_version":"1.0","event_id":"sha256:4b5052772dfc19ed3226c0ad60dc7427c9be771b8da765454c7887ccb7416629"},{"event_type":"graph_snapshot","subject_pith_number":"pith:1994:OZ7SIHYOC2WFXMIPJR7HV3CP2A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Sequential Algorithm for Training Text Classifiers","license":"","headline":"","cross_cats":["cs.CL"],"primary_cat":"cmp-lg","authors_text":"David D. Lewis (AT&T Bell Labs), William A. Gale (AT&T Bell Labs)","submitted_at":"1994-07-24T13:38:00Z","abstract_excerpt":"The ability to cheaply train text classifiers is critical to their use in information retrieval, content analysis, natural language processing, and other tasks involving data which is partly or fully textual. An algorithm for sequential sampling during machine learning of statistical classifiers was developed and tested on a newswire text categorization task. This method, which we call uncertainty sampling, reduced by as much as 500-fold the amount of training data that would have to be manually classified to achieve a given level of effectiveness."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cmp-lg/9407020","kind":"arxiv","version":2},"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/cmp-lg/9407020/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":"2026-07-04T15:07:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u2N30cYS9AMdQjRw+1z6BQM9vqlGAjrFeala1mLyIgux+IYfEvfkiq80h5wUVL1TvkfbaXNSqYTTLjBrHjsfBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:42:15.346053Z"},"content_sha256":"1cecb412492c4b3ce94faf38902babce9a5e8105a0707b566948fc4f4f59cde8","schema_version":"1.0","event_id":"sha256:1cecb412492c4b3ce94faf38902babce9a5e8105a0707b566948fc4f4f59cde8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OZ7SIHYOC2WFXMIPJR7HV3CP2A/bundle.json","state_url":"https://pith.science/pith/OZ7SIHYOC2WFXMIPJR7HV3CP2A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OZ7SIHYOC2WFXMIPJR7HV3CP2A/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":"2026-08-06T04:42:15Z","links":{"resolver":"https://pith.science/pith/OZ7SIHYOC2WFXMIPJR7HV3CP2A","bundle":"https://pith.science/pith/OZ7SIHYOC2WFXMIPJR7HV3CP2A/bundle.json","state":"https://pith.science/pith/OZ7SIHYOC2WFXMIPJR7HV3CP2A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OZ7SIHYOC2WFXMIPJR7HV3CP2A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:1994:OZ7SIHYOC2WFXMIPJR7HV3CP2A","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":"c4dc3e25da483fcfe7a3b22ad7cd3e2b3f7a9c3caeed9643e5e6c5eea720a7c3","cross_cats_sorted":["cs.CL"],"license":"","primary_cat":"cmp-lg","submitted_at":"1994-07-24T13:38:00Z","title_canon_sha256":"8d63d18b4463a57e14eb83356b2f93bd3887e34e75e96eb0b5a1e89f68c1007c"},"schema_version":"1.0","source":{"id":"cmp-lg/9407020","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cmp-lg/9407020","created_at":"2026-07-04T15:07:19Z"},{"alias_kind":"arxiv_version","alias_value":"cmp-lg/9407020v2","created_at":"2026-07-04T15:07:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cmp-lg/9407020","created_at":"2026-07-04T15:07:19Z"},{"alias_kind":"pith_short_12","alias_value":"OZ7SIHYOC2WF","created_at":"2026-07-04T15:07:19Z"},{"alias_kind":"pith_short_16","alias_value":"OZ7SIHYOC2WFXMIP","created_at":"2026-07-04T15:07:19Z"},{"alias_kind":"pith_short_8","alias_value":"OZ7SIHYO","created_at":"2026-07-04T15:07:19Z"}],"graph_snapshots":[{"event_id":"sha256:1cecb412492c4b3ce94faf38902babce9a5e8105a0707b566948fc4f4f59cde8","target":"graph","created_at":"2026-07-04T15:07:19Z","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/cmp-lg/9407020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability to cheaply train text classifiers is critical to their use in information retrieval, content analysis, natural language processing, and other tasks involving data which is partly or fully textual. An algorithm for sequential sampling during machine learning of statistical classifiers was developed and tested on a newswire text categorization task. This method, which we call uncertainty sampling, reduced by as much as 500-fold the amount of training data that would have to be manually classified to achieve a given level of effectiveness.","authors_text":"David D. Lewis (AT&T Bell Labs), William A. Gale (AT&T Bell Labs)","cross_cats":["cs.CL"],"headline":"","license":"","primary_cat":"cmp-lg","submitted_at":"1994-07-24T13:38:00Z","title":"A Sequential Algorithm for Training Text Classifiers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cmp-lg/9407020","kind":"arxiv","version":2},"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":"sha256:4b5052772dfc19ed3226c0ad60dc7427c9be771b8da765454c7887ccb7416629","target":"record","created_at":"2026-07-04T15:07:19Z","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":"c4dc3e25da483fcfe7a3b22ad7cd3e2b3f7a9c3caeed9643e5e6c5eea720a7c3","cross_cats_sorted":["cs.CL"],"license":"","primary_cat":"cmp-lg","submitted_at":"1994-07-24T13:38:00Z","title_canon_sha256":"8d63d18b4463a57e14eb83356b2f93bd3887e34e75e96eb0b5a1e89f68c1007c"},"schema_version":"1.0","source":{"id":"cmp-lg/9407020","kind":"arxiv","version":2}},"canonical_sha256":"767f241f0e16ac5bb10f4c7e7aec4fd01791f081e08e0c0854e52e9020ade5cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"767f241f0e16ac5bb10f4c7e7aec4fd01791f081e08e0c0854e52e9020ade5cf","first_computed_at":"2026-07-04T15:07:19.193304Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T15:07:19.193304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Mybs/ctczFyGD6wcDenZ+aVPm5GiiJPCzQx4EGnfxWazEU2DUQGKmcw2nAvxfaQ4FjUbPMS65uvGaJOD65jhCw==","signature_status":"signed_v1","signed_at":"2026-07-04T15:07:19.193781Z","signed_message":"canonical_sha256_bytes"},"source_id":"cmp-lg/9407020","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b5052772dfc19ed3226c0ad60dc7427c9be771b8da765454c7887ccb7416629","sha256:1cecb412492c4b3ce94faf38902babce9a5e8105a0707b566948fc4f4f59cde8"],"state_sha256":"2137a7177db682f86ea6ba49e9c07ee33d7f87ccae88acc6cdf5145073d03b83"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WDWsTmdP8v5eaUxNRfTVTNycVy3gh46hwRcGEyIYBEGOqN5s7MicrnKyAbOp+0QfKRMGc3uOndh7gCgdrqQYBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:42:15.352801Z","bundle_sha256":"3709b5c14de41be630502b88d31329bb6e98e4cc7362871e1e36ebf22e67d826"}}