{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:FC2QO26PHHKWRTUEAVVFOUSM7I","short_pith_number":"pith:FC2QO26P","canonical_record":{"source":{"id":"2012.02297","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2020-11-11T16:17:28Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"4dc6e505a01dd6cab82fc7b4f4d3a4f8a75c034c9fca63ac258018550870bedb","abstract_canon_sha256":"5859f385866d8b8f677f4c0d216858184dc20977c4782fc6b488cc28204487da"},"schema_version":"1.0"},"canonical_sha256":"28b5076bcf39d568ce84056a57524cfa23b4b005774a4a1983417f6efa2866b0","source":{"kind":"arxiv","id":"2012.02297","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.02297","created_at":"2026-07-05T01:56:58Z"},{"alias_kind":"arxiv_version","alias_value":"2012.02297v1","created_at":"2026-07-05T01:56:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02297","created_at":"2026-07-05T01:56:58Z"},{"alias_kind":"pith_short_12","alias_value":"FC2QO26PHHKW","created_at":"2026-07-05T01:56:58Z"},{"alias_kind":"pith_short_16","alias_value":"FC2QO26PHHKWRTUE","created_at":"2026-07-05T01:56:58Z"},{"alias_kind":"pith_short_8","alias_value":"FC2QO26P","created_at":"2026-07-05T01:56:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:FC2QO26PHHKWRTUEAVVFOUSM7I","target":"record","payload":{"canonical_record":{"source":{"id":"2012.02297","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2020-11-11T16:17:28Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"4dc6e505a01dd6cab82fc7b4f4d3a4f8a75c034c9fca63ac258018550870bedb","abstract_canon_sha256":"5859f385866d8b8f677f4c0d216858184dc20977c4782fc6b488cc28204487da"},"schema_version":"1.0"},"canonical_sha256":"28b5076bcf39d568ce84056a57524cfa23b4b005774a4a1983417f6efa2866b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:58.246792Z","signature_b64":"ExmRhITQB3IUKRsjobk4SLlhBNg/SYE/35Ij3iBaD+kPMIKZszx6U+/RCGfIfTqiCL8raPwYNrVgYT89TIp2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28b5076bcf39d568ce84056a57524cfa23b4b005774a4a1983417f6efa2866b0","last_reissued_at":"2026-07-05T01:56:58.246389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:58.246389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.02297","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":"RLux97W78qmPawOiX+Mrdy91ouQrzFcyEESLklBN5v/d1IMD5SkPy+0cjAAqini9I06/AmmOlSBqWJGVuDAYBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:32:36.175665Z"},"content_sha256":"4bb26ae6f28eaf4072e77d85fee164709afa788e66431e4cc97581d079ebdaa7","schema_version":"1.0","event_id":"sha256:4bb26ae6f28eaf4072e77d85fee164709afa788e66431e4cc97581d079ebdaa7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:FC2QO26PHHKWRTUEAVVFOUSM7I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Active Learning from Crowd in Document Screening","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Alessandro Bozzon, Burcu Sayin, Evgeny Krivosheev, Zolt\\'an Szl\\'avik","submitted_at":"2020-11-11T16:17:28Z","abstract_excerpt":"In this paper, we explore how to efficiently combine crowdsourcing and machine intelligence for the problem of document screening, where we need to screen documents with a set of machine-learning filters. Specifically, we focus on building a set of machine learning classifiers that evaluate documents, and then screen them efficiently. It is a challenging task since the budget is limited and there are countless number of ways to spend the given budget on the problem. We propose a multi-label active learning screening specific sampling technique -- objective-aware sampling -- for querying unlabe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02297","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/2012.02297/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":"N/VNpwgclgfwGkr3v74Xmh6kMrOb86x+yzhVv1QgXVwyddh5qEYDH0DwgXn1SIZ0cFsWSfMck2UWPBUzUSiTBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:32:36.176284Z"},"content_sha256":"0c2bd5ccc8aecbc639ea693a0f48fd7e7e139ae7c7df5ec30eb908e8c63211a7","schema_version":"1.0","event_id":"sha256:0c2bd5ccc8aecbc639ea693a0f48fd7e7e139ae7c7df5ec30eb908e8c63211a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FC2QO26PHHKWRTUEAVVFOUSM7I/bundle.json","state_url":"https://pith.science/pith/FC2QO26PHHKWRTUEAVVFOUSM7I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FC2QO26PHHKWRTUEAVVFOUSM7I/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":"2026-07-05T13:32:36Z","links":{"resolver":"https://pith.science/pith/FC2QO26PHHKWRTUEAVVFOUSM7I","bundle":"https://pith.science/pith/FC2QO26PHHKWRTUEAVVFOUSM7I/bundle.json","state":"https://pith.science/pith/FC2QO26PHHKWRTUEAVVFOUSM7I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FC2QO26PHHKWRTUEAVVFOUSM7I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FC2QO26PHHKWRTUEAVVFOUSM7I","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":"5859f385866d8b8f677f4c0d216858184dc20977c4782fc6b488cc28204487da","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2020-11-11T16:17:28Z","title_canon_sha256":"4dc6e505a01dd6cab82fc7b4f4d3a4f8a75c034c9fca63ac258018550870bedb"},"schema_version":"1.0","source":{"id":"2012.02297","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.02297","created_at":"2026-07-05T01:56:58Z"},{"alias_kind":"arxiv_version","alias_value":"2012.02297v1","created_at":"2026-07-05T01:56:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02297","created_at":"2026-07-05T01:56:58Z"},{"alias_kind":"pith_short_12","alias_value":"FC2QO26PHHKW","created_at":"2026-07-05T01:56:58Z"},{"alias_kind":"pith_short_16","alias_value":"FC2QO26PHHKWRTUE","created_at":"2026-07-05T01:56:58Z"},{"alias_kind":"pith_short_8","alias_value":"FC2QO26P","created_at":"2026-07-05T01:56:58Z"}],"graph_snapshots":[{"event_id":"sha256:0c2bd5ccc8aecbc639ea693a0f48fd7e7e139ae7c7df5ec30eb908e8c63211a7","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/2012.02297/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we explore how to efficiently combine crowdsourcing and machine intelligence for the problem of document screening, where we need to screen documents with a set of machine-learning filters. Specifically, we focus on building a set of machine learning classifiers that evaluate documents, and then screen them efficiently. It is a challenging task since the budget is limited and there are countless number of ways to spend the given budget on the problem. We propose a multi-label active learning screening specific sampling technique -- objective-aware sampling -- for querying unlabe","authors_text":"Alessandro Bozzon, Burcu Sayin, Evgeny Krivosheev, Zolt\\'an Szl\\'avik","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2020-11-11T16:17:28Z","title":"Active Learning from Crowd in Document Screening"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02297","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":"sha256:4bb26ae6f28eaf4072e77d85fee164709afa788e66431e4cc97581d079ebdaa7","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":"5859f385866d8b8f677f4c0d216858184dc20977c4782fc6b488cc28204487da","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2020-11-11T16:17:28Z","title_canon_sha256":"4dc6e505a01dd6cab82fc7b4f4d3a4f8a75c034c9fca63ac258018550870bedb"},"schema_version":"1.0","source":{"id":"2012.02297","kind":"arxiv","version":1}},"canonical_sha256":"28b5076bcf39d568ce84056a57524cfa23b4b005774a4a1983417f6efa2866b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28b5076bcf39d568ce84056a57524cfa23b4b005774a4a1983417f6efa2866b0","first_computed_at":"2026-07-05T01:56:58.246389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:56:58.246389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ExmRhITQB3IUKRsjobk4SLlhBNg/SYE/35Ij3iBaD+kPMIKZszx6U+/RCGfIfTqiCL8raPwYNrVgYT89TIp2Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:56:58.246792Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.02297","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bb26ae6f28eaf4072e77d85fee164709afa788e66431e4cc97581d079ebdaa7","sha256:0c2bd5ccc8aecbc639ea693a0f48fd7e7e139ae7c7df5ec30eb908e8c63211a7"],"state_sha256":"bb7fef15c545ab7f198103b53e6055060cb795693ef4dcb2976ea8ffd5af411a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7GtL8HdiuyxIBAo0xGN87mkw8sihjDacWYgjbc6HHENFbnLCBaA++Pd7BQIi1Fvt3H7S7BS17wcp5IkvEjGoBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T13:32:36.180505Z","bundle_sha256":"717b5f7398cb2dadb50fe891674f2cd96445c83be65d6295310a92c7abfa35da"}}