{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:LDTLUSR3N2Y5UVEJWKGNW7DTU6","short_pith_number":"pith:LDTLUSR3","canonical_record":{"source":{"id":"2005.11442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-23T01:50:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7ff361c78d494a2ef7fc5e48354a9df6c44481aa93f80fb14f7c409e3835726b","abstract_canon_sha256":"ce0a4d25fee027d61ab26d5bdd539bcc0d0c8d6ceb6c17e47340098064585b2f"},"schema_version":"1.0"},"canonical_sha256":"58e6ba4a3b6eb1da5489b28cdb7c73a7ac2ad91d3044d0467d4fc1e9a06a0427","source":{"kind":"arxiv","id":"2005.11442","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.11442","created_at":"2026-07-05T01:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2005.11442v1","created_at":"2026-07-05T01:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.11442","created_at":"2026-07-05T01:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"LDTLUSR3N2Y5","created_at":"2026-07-05T01:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"LDTLUSR3N2Y5UVEJ","created_at":"2026-07-05T01:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"LDTLUSR3","created_at":"2026-07-05T01:05:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:LDTLUSR3N2Y5UVEJWKGNW7DTU6","target":"record","payload":{"canonical_record":{"source":{"id":"2005.11442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-23T01:50:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7ff361c78d494a2ef7fc5e48354a9df6c44481aa93f80fb14f7c409e3835726b","abstract_canon_sha256":"ce0a4d25fee027d61ab26d5bdd539bcc0d0c8d6ceb6c17e47340098064585b2f"},"schema_version":"1.0"},"canonical_sha256":"58e6ba4a3b6eb1da5489b28cdb7c73a7ac2ad91d3044d0467d4fc1e9a06a0427","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:05:14.481529Z","signature_b64":"TU25YzMDD46xU7V31+c/+m074M1PLQuTU/Vt8B2cWcnUPupiRN+wYpaqzZNTTuAzYzYFq+a28zh5G1qIS4nCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58e6ba4a3b6eb1da5489b28cdb7c73a7ac2ad91d3044d0467d4fc1e9a06a0427","last_reissued_at":"2026-07-05T01:05:14.481174Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:05:14.481174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.11442","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":"2026-07-05T01:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pSyKypdsXC39l/J8k67IfI32BsOWLBu/vHympW+2KQ0wruAqofIKovRa6VRPafIk24XbRNtu6NR9ZarG35qpCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:54:46.783253Z"},"content_sha256":"e09a44da278361793f2119eb9c80fc9ddd5676615c9beae71ecc3ce96ff5e827","schema_version":"1.0","event_id":"sha256:e09a44da278361793f2119eb9c80fc9ddd5676615c9beae71ecc3ce96ff5e827"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:LDTLUSR3N2Y5UVEJWKGNW7DTU6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Active Learning for Skewed Data Sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Abbas Kazerouni, Jing Xie, Marc Najork, Qi Zhao, Sandeep Tata","submitted_at":"2020-05-23T01:50:19Z","abstract_excerpt":"Consider a sequential active learning problem where, at each round, an agent selects a batch of unlabeled data points, queries their labels and updates a binary classifier. While there exists a rich body of work on active learning in this general form, in this paper, we focus on problems with two distinguishing characteristics: severe class imbalance (skew) and small amounts of initial training data. Both of these problems occur with surprising frequency in many web applications. For instance, detecting offensive or sensitive content in online communities (pornography, violence, and hate-speec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.11442","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/2005.11442/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":"2026-07-05T01:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bmYGDbDOgry+M0MZXGRg5SB2vkqfTCJi+E1ZdQa0TkjqCJa92PGy4ALgbCBrftC5wiuqCN1hMLCMSC6EgydFCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:54:46.783770Z"},"content_sha256":"a4a663240bae213bb880623acb25f4eb311793536f5061195ecf51c999b964ec","schema_version":"1.0","event_id":"sha256:a4a663240bae213bb880623acb25f4eb311793536f5061195ecf51c999b964ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LDTLUSR3N2Y5UVEJWKGNW7DTU6/bundle.json","state_url":"https://pith.science/pith/LDTLUSR3N2Y5UVEJWKGNW7DTU6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LDTLUSR3N2Y5UVEJWKGNW7DTU6/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":"2026-08-08T22:54:46Z","links":{"resolver":"https://pith.science/pith/LDTLUSR3N2Y5UVEJWKGNW7DTU6","bundle":"https://pith.science/pith/LDTLUSR3N2Y5UVEJWKGNW7DTU6/bundle.json","state":"https://pith.science/pith/LDTLUSR3N2Y5UVEJWKGNW7DTU6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LDTLUSR3N2Y5UVEJWKGNW7DTU6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LDTLUSR3N2Y5UVEJWKGNW7DTU6","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":"ce0a4d25fee027d61ab26d5bdd539bcc0d0c8d6ceb6c17e47340098064585b2f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-23T01:50:19Z","title_canon_sha256":"7ff361c78d494a2ef7fc5e48354a9df6c44481aa93f80fb14f7c409e3835726b"},"schema_version":"1.0","source":{"id":"2005.11442","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.11442","created_at":"2026-07-05T01:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2005.11442v1","created_at":"2026-07-05T01:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.11442","created_at":"2026-07-05T01:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"LDTLUSR3N2Y5","created_at":"2026-07-05T01:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"LDTLUSR3N2Y5UVEJ","created_at":"2026-07-05T01:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"LDTLUSR3","created_at":"2026-07-05T01:05:14Z"}],"graph_snapshots":[{"event_id":"sha256:a4a663240bae213bb880623acb25f4eb311793536f5061195ecf51c999b964ec","target":"graph","created_at":"2026-07-05T01:05:14Z","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/2005.11442/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Consider a sequential active learning problem where, at each round, an agent selects a batch of unlabeled data points, queries their labels and updates a binary classifier. While there exists a rich body of work on active learning in this general form, in this paper, we focus on problems with two distinguishing characteristics: severe class imbalance (skew) and small amounts of initial training data. Both of these problems occur with surprising frequency in many web applications. For instance, detecting offensive or sensitive content in online communities (pornography, violence, and hate-speec","authors_text":"Abbas Kazerouni, Jing Xie, Marc Najork, Qi Zhao, Sandeep Tata","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-23T01:50:19Z","title":"Active Learning for Skewed Data Sets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.11442","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:e09a44da278361793f2119eb9c80fc9ddd5676615c9beae71ecc3ce96ff5e827","target":"record","created_at":"2026-07-05T01:05:14Z","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":"ce0a4d25fee027d61ab26d5bdd539bcc0d0c8d6ceb6c17e47340098064585b2f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-23T01:50:19Z","title_canon_sha256":"7ff361c78d494a2ef7fc5e48354a9df6c44481aa93f80fb14f7c409e3835726b"},"schema_version":"1.0","source":{"id":"2005.11442","kind":"arxiv","version":1}},"canonical_sha256":"58e6ba4a3b6eb1da5489b28cdb7c73a7ac2ad91d3044d0467d4fc1e9a06a0427","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58e6ba4a3b6eb1da5489b28cdb7c73a7ac2ad91d3044d0467d4fc1e9a06a0427","first_computed_at":"2026-07-05T01:05:14.481174Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:05:14.481174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TU25YzMDD46xU7V31+c/+m074M1PLQuTU/Vt8B2cWcnUPupiRN+wYpaqzZNTTuAzYzYFq+a28zh5G1qIS4nCDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:05:14.481529Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.11442","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e09a44da278361793f2119eb9c80fc9ddd5676615c9beae71ecc3ce96ff5e827","sha256:a4a663240bae213bb880623acb25f4eb311793536f5061195ecf51c999b964ec"],"state_sha256":"5f541ca9a6cdf9ad5d64544c33d619595a5051b08805cb1478bb307c117ba99b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+ubjrwPXpYkqmDGrjY7TXMrFdJbqWYm8ar4QVjbwSLTpHuuuApre0t/ssIL3xRrezFtKESGvlCnkNYsBOLhODQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:54:46.787597Z","bundle_sha256":"85d05da9994c9cde080f9b274eb41a9d389c7f2b2f8ae7ed12d041dead20b998"}}