{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LDMNB2BUOP6ZDWWTER6TKSHFM5","short_pith_number":"pith:LDMNB2BU","schema_version":"1.0","canonical_sha256":"58d8d0e83473fd91dad3247d3548e5675a233fba7071cadd137773aa827d5535","source":{"kind":"arxiv","id":"1705.02395","version":1},"attestation_state":"computed","paper":{"title":"On Using Active Learning and Self-Training when Mining Performance Discussions on Stack Overflow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.LG","cs.SE"],"primary_cat":"cs.CL","authors_text":"Elizabeth Bjarnason, Iben Lennerstad, Markus Borg, Rasmus Ros","submitted_at":"2017-04-26T20:47:36Z","abstract_excerpt":"Abundant data is the key to successful machine learning. However, supervised learning requires annotated data that are often hard to obtain. In a classification task with limited resources, Active Learning (AL) promises to guide annotators to examples that bring the most value for a classifier. AL can be successfully combined with self-training, i.e., extending a training set with the unlabelled examples for which a classifier is the most certain. We report our experiences on using AL in a systematic manner to train an SVM classifier for Stack Overflow posts discussing performance of software "},"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":"1705.02395","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-26T20:47:36Z","cross_cats_sorted":["cs.HC","cs.LG","cs.SE"],"title_canon_sha256":"635eba6191e55b4868bdd45361c48190b9d7a15a36a3162fcaa9603ef9be1697","abstract_canon_sha256":"16cc65b7a55905acff0a847501d5b3d5e9306df383e7baf796d3fcb25b56a789"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:56.709856Z","signature_b64":"nSgc+ZfFysk8MScNknnWrQ49AmUZTl7PFcBGbX7P8JQmiFDwcBEJFriVR01EeWPhCk5CILmMrzUoCenXSSITCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58d8d0e83473fd91dad3247d3548e5675a233fba7071cadd137773aa827d5535","last_reissued_at":"2026-05-18T00:44:56.709284Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:56.709284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Using Active Learning and Self-Training when Mining Performance Discussions on Stack Overflow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.LG","cs.SE"],"primary_cat":"cs.CL","authors_text":"Elizabeth Bjarnason, Iben Lennerstad, Markus Borg, Rasmus Ros","submitted_at":"2017-04-26T20:47:36Z","abstract_excerpt":"Abundant data is the key to successful machine learning. However, supervised learning requires annotated data that are often hard to obtain. In a classification task with limited resources, Active Learning (AL) promises to guide annotators to examples that bring the most value for a classifier. AL can be successfully combined with self-training, i.e., extending a training set with the unlabelled examples for which a classifier is the most certain. We report our experiences on using AL in a systematic manner to train an SVM classifier for Stack Overflow posts discussing performance of software "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.02395","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":"1705.02395","created_at":"2026-05-18T00:44:56.709406+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.02395v1","created_at":"2026-05-18T00:44:56.709406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.02395","created_at":"2026-05-18T00:44:56.709406+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDMNB2BUOP6Z","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDMNB2BUOP6ZDWWT","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDMNB2BU","created_at":"2026-05-18T12:31:28.150371+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/LDMNB2BUOP6ZDWWTER6TKSHFM5","json":"https://pith.science/pith/LDMNB2BUOP6ZDWWTER6TKSHFM5.json","graph_json":"https://pith.science/api/pith-number/LDMNB2BUOP6ZDWWTER6TKSHFM5/graph.json","events_json":"https://pith.science/api/pith-number/LDMNB2BUOP6ZDWWTER6TKSHFM5/events.json","paper":"https://pith.science/paper/LDMNB2BU"},"agent_actions":{"view_html":"https://pith.science/pith/LDMNB2BUOP6ZDWWTER6TKSHFM5","download_json":"https://pith.science/pith/LDMNB2BUOP6ZDWWTER6TKSHFM5.json","view_paper":"https://pith.science/paper/LDMNB2BU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.02395&json=true","fetch_graph":"https://pith.science/api/pith-number/LDMNB2BUOP6ZDWWTER6TKSHFM5/graph.json","fetch_events":"https://pith.science/api/pith-number/LDMNB2BUOP6ZDWWTER6TKSHFM5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDMNB2BUOP6ZDWWTER6TKSHFM5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDMNB2BUOP6ZDWWTER6TKSHFM5/action/storage_attestation","attest_author":"https://pith.science/pith/LDMNB2BUOP6ZDWWTER6TKSHFM5/action/author_attestation","sign_citation":"https://pith.science/pith/LDMNB2BUOP6ZDWWTER6TKSHFM5/action/citation_signature","submit_replication":"https://pith.science/pith/LDMNB2BUOP6ZDWWTER6TKSHFM5/action/replication_record"}},"created_at":"2026-05-18T00:44:56.709406+00:00","updated_at":"2026-05-18T00:44:56.709406+00:00"}