{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:UKDJLKZ7DDG5QWMMTEJL5AZC7D","short_pith_number":"pith:UKDJLKZ7","canonical_record":{"source":{"id":"2103.13165","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2021-03-24T13:09:23Z","cross_cats_sorted":[],"title_canon_sha256":"ceef42e0ccedcd76e2f676b153a04c0c4427c133a14a9566e49b845a978e79f2","abstract_canon_sha256":"d187b2e7fa1d2704514756bd5426f648984580d9c63286c63c697550e98af578"},"schema_version":"1.0"},"canonical_sha256":"a28695ab3f18cdd8598c9912be8322f8fce98176d35fec72025e32a344331866","source":{"kind":"arxiv","id":"2103.13165","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.13165","created_at":"2026-07-05T02:26:06Z"},{"alias_kind":"arxiv_version","alias_value":"2103.13165v1","created_at":"2026-07-05T02:26:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.13165","created_at":"2026-07-05T02:26:06Z"},{"alias_kind":"pith_short_12","alias_value":"UKDJLKZ7DDG5","created_at":"2026-07-05T02:26:06Z"},{"alias_kind":"pith_short_16","alias_value":"UKDJLKZ7DDG5QWMM","created_at":"2026-07-05T02:26:06Z"},{"alias_kind":"pith_short_8","alias_value":"UKDJLKZ7","created_at":"2026-07-05T02:26:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:UKDJLKZ7DDG5QWMMTEJL5AZC7D","target":"record","payload":{"canonical_record":{"source":{"id":"2103.13165","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2021-03-24T13:09:23Z","cross_cats_sorted":[],"title_canon_sha256":"ceef42e0ccedcd76e2f676b153a04c0c4427c133a14a9566e49b845a978e79f2","abstract_canon_sha256":"d187b2e7fa1d2704514756bd5426f648984580d9c63286c63c697550e98af578"},"schema_version":"1.0"},"canonical_sha256":"a28695ab3f18cdd8598c9912be8322f8fce98176d35fec72025e32a344331866","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:06.695642Z","signature_b64":"p0YXv5zoCUN2e4NSO4tEEY6InOwCU2uD+7t1YUdzk3/FA3fqDkNzxugsQtjh3e9iNr/66Qqizz9cvicdZWEICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a28695ab3f18cdd8598c9912be8322f8fce98176d35fec72025e32a344331866","last_reissued_at":"2026-07-05T02:26:06.695170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:06.695170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.13165","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":"2026-07-05T02:26:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lJbntbviXUndSTBLTLHsUwsP5Kh80g9gCbPxQ+HF/t0hcWUBQqPKEhmQTxS781vlLf8WpACTc9PXx4y/4tvWCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T05:08:55.210190Z"},"content_sha256":"bafc9f497a7a086fdf30075d06abde5496352a9e3a876400c8cf82bf1180b2bb","schema_version":"1.0","event_id":"sha256:bafc9f497a7a086fdf30075d06abde5496352a9e3a876400c8cf82bf1180b2bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:UKDJLKZ7DDG5QWMMTEJL5AZC7D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Balancing Improves Self-Admitted Technical Debt Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Leevi Rantala, Maelick Claes, Mika Mantyla, Murali Sridharan","submitted_at":"2021-03-24T13:09:23Z","abstract_excerpt":"A high imbalance exists between technical debt and non-technical debt source code comments. Such imbalance affects Self-Admitted Technical Debt (SATD) detection performance, and existing literature lacks empirical evidence on the choice of balancing technique. In this work, we evaluate the impact of multiple balancing techniques, including Data level, Classifier level, and Hybrid, for SATD detection in Within-Project and Cross-Project setup. Our results show that the Data level balancing technique SMOTE or Classifier level Ensemble approaches Random Forest or XGBoost are reasonable choices dep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.13165","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/2103.13165/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":"2026-07-05T02:26:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"izxWHCI8cf9WICFJXYuJjYvcsdzArGuGF57A5Drj0JLTC+nTKKoocn9aCSfbBVmJb7/6x7sxAA/bKzXW3TZvCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T05:08:55.210572Z"},"content_sha256":"38bc105afdbb53e198b200fedd7dfa96b25a50de7e9f2a0cb016fc22746e9d20","schema_version":"1.0","event_id":"sha256:38bc105afdbb53e198b200fedd7dfa96b25a50de7e9f2a0cb016fc22746e9d20"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UKDJLKZ7DDG5QWMMTEJL5AZC7D/bundle.json","state_url":"https://pith.science/pith/UKDJLKZ7DDG5QWMMTEJL5AZC7D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UKDJLKZ7DDG5QWMMTEJL5AZC7D/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":"2026-08-22T05:08:55Z","links":{"resolver":"https://pith.science/pith/UKDJLKZ7DDG5QWMMTEJL5AZC7D","bundle":"https://pith.science/pith/UKDJLKZ7DDG5QWMMTEJL5AZC7D/bundle.json","state":"https://pith.science/pith/UKDJLKZ7DDG5QWMMTEJL5AZC7D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UKDJLKZ7DDG5QWMMTEJL5AZC7D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UKDJLKZ7DDG5QWMMTEJL5AZC7D","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":"d187b2e7fa1d2704514756bd5426f648984580d9c63286c63c697550e98af578","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2021-03-24T13:09:23Z","title_canon_sha256":"ceef42e0ccedcd76e2f676b153a04c0c4427c133a14a9566e49b845a978e79f2"},"schema_version":"1.0","source":{"id":"2103.13165","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.13165","created_at":"2026-07-05T02:26:06Z"},{"alias_kind":"arxiv_version","alias_value":"2103.13165v1","created_at":"2026-07-05T02:26:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.13165","created_at":"2026-07-05T02:26:06Z"},{"alias_kind":"pith_short_12","alias_value":"UKDJLKZ7DDG5","created_at":"2026-07-05T02:26:06Z"},{"alias_kind":"pith_short_16","alias_value":"UKDJLKZ7DDG5QWMM","created_at":"2026-07-05T02:26:06Z"},{"alias_kind":"pith_short_8","alias_value":"UKDJLKZ7","created_at":"2026-07-05T02:26:06Z"}],"graph_snapshots":[{"event_id":"sha256:38bc105afdbb53e198b200fedd7dfa96b25a50de7e9f2a0cb016fc22746e9d20","target":"graph","created_at":"2026-07-05T02:26:06Z","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/2103.13165/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A high imbalance exists between technical debt and non-technical debt source code comments. Such imbalance affects Self-Admitted Technical Debt (SATD) detection performance, and existing literature lacks empirical evidence on the choice of balancing technique. In this work, we evaluate the impact of multiple balancing techniques, including Data level, Classifier level, and Hybrid, for SATD detection in Within-Project and Cross-Project setup. Our results show that the Data level balancing technique SMOTE or Classifier level Ensemble approaches Random Forest or XGBoost are reasonable choices dep","authors_text":"Leevi Rantala, Maelick Claes, Mika Mantyla, Murali Sridharan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2021-03-24T13:09:23Z","title":"Data Balancing Improves Self-Admitted Technical Debt Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.13165","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:bafc9f497a7a086fdf30075d06abde5496352a9e3a876400c8cf82bf1180b2bb","target":"record","created_at":"2026-07-05T02:26:06Z","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":"d187b2e7fa1d2704514756bd5426f648984580d9c63286c63c697550e98af578","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2021-03-24T13:09:23Z","title_canon_sha256":"ceef42e0ccedcd76e2f676b153a04c0c4427c133a14a9566e49b845a978e79f2"},"schema_version":"1.0","source":{"id":"2103.13165","kind":"arxiv","version":1}},"canonical_sha256":"a28695ab3f18cdd8598c9912be8322f8fce98176d35fec72025e32a344331866","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a28695ab3f18cdd8598c9912be8322f8fce98176d35fec72025e32a344331866","first_computed_at":"2026-07-05T02:26:06.695170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:26:06.695170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p0YXv5zoCUN2e4NSO4tEEY6InOwCU2uD+7t1YUdzk3/FA3fqDkNzxugsQtjh3e9iNr/66Qqizz9cvicdZWEICw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:26:06.695642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.13165","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bafc9f497a7a086fdf30075d06abde5496352a9e3a876400c8cf82bf1180b2bb","sha256:38bc105afdbb53e198b200fedd7dfa96b25a50de7e9f2a0cb016fc22746e9d20"],"state_sha256":"e81441e64fe25feedc849cdefdc5c2a04ca431baf2a0bcedd94d5a452a11baa7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wVPWkJnIEt7gGidq1tyuFXKCpU5/rdVaj6U+00bofgXto8tlh4GHxmVD73B9AGuqz9ZiOgHFUxkIRwVZlvkEDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T05:08:55.213297Z","bundle_sha256":"f275d066952d78908e905fdb53acf340e7082e9dc80ee01d3c12f047158419c5"}}