{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:WKDOCSSDIQS67NCJKFM7SUB42T","short_pith_number":"pith:WKDOCSSD","canonical_record":{"source":{"id":"2012.08387","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2020-12-15T16:01:21Z","cross_cats_sorted":[],"title_canon_sha256":"1eb994216c4da5634636bb7c3cb973496d7f30549f64bbb00cbf013720d2929d","abstract_canon_sha256":"83d30e84bd6cf0680d610fbe0b3941a76732c3934586d6372fe1c51cde256d5c"},"schema_version":"1.0"},"canonical_sha256":"b286e14a434425efb4495159f9503cd4e6d060ffa5656a292f0e3c45f276e773","source":{"kind":"arxiv","id":"2012.08387","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.08387","created_at":"2026-07-05T01:59:42Z"},{"alias_kind":"arxiv_version","alias_value":"2012.08387v1","created_at":"2026-07-05T01:59:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.08387","created_at":"2026-07-05T01:59:42Z"},{"alias_kind":"pith_short_12","alias_value":"WKDOCSSDIQS6","created_at":"2026-07-05T01:59:42Z"},{"alias_kind":"pith_short_16","alias_value":"WKDOCSSDIQS67NCJ","created_at":"2026-07-05T01:59:42Z"},{"alias_kind":"pith_short_8","alias_value":"WKDOCSSD","created_at":"2026-07-05T01:59:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:WKDOCSSDIQS67NCJKFM7SUB42T","target":"record","payload":{"canonical_record":{"source":{"id":"2012.08387","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2020-12-15T16:01:21Z","cross_cats_sorted":[],"title_canon_sha256":"1eb994216c4da5634636bb7c3cb973496d7f30549f64bbb00cbf013720d2929d","abstract_canon_sha256":"83d30e84bd6cf0680d610fbe0b3941a76732c3934586d6372fe1c51cde256d5c"},"schema_version":"1.0"},"canonical_sha256":"b286e14a434425efb4495159f9503cd4e6d060ffa5656a292f0e3c45f276e773","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:59:42.903003Z","signature_b64":"EXaJ64gt5aTfc6wAsnpOiyTRDvNBuEzeOL1hVlxauXgOnhhXZzE3VjyH/kcAU9nNMUbyUqC/Ui3ujRM+RT50CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b286e14a434425efb4495159f9503cd4e6d060ffa5656a292f0e3c45f276e773","last_reissued_at":"2026-07-05T01:59:42.902597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:59:42.902597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.08387","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":"2026-07-05T01:59:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eYysDJehg04u8HtG7rLWiaQrFKgWDnT5qdWH5a727eIi4vyvMgbvfUMlxm6o0JpqKqr073g9DFtFCRM2sxt1DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T08:06:56.150433Z"},"content_sha256":"9dce43f9391eaca1f9b761f65a2d183ff6ec52384392fab86f3939948506050a","schema_version":"1.0","event_id":"sha256:9dce43f9391eaca1f9b761f65a2d183ff6ec52384392fab86f3939948506050a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:WKDOCSSDIQS67NCJKFM7SUB42T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Run, Forest, Run? On Randomization and Reproducibility in Predictive Software Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Annibale Panichella, Cynthia C. S. Liem","submitted_at":"2020-12-15T16:01:21Z","abstract_excerpt":"Machine learning (ML) has been widely used in the literature to automate software engineering tasks. However, ML outcomes may be sensitive to randomization in data sampling mechanisms and learning procedures. To understand whether and how researchers in SE address these threats, we surveyed 45 recent papers related to three predictive tasks: defect prediction (DP), predictive mutation testing (PMT), and code smell detection (CSD). We found that less than 50% of the surveyed papers address the threats related to randomized data sampling (via multiple repetitions); only 8% of the papers address "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.08387","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/2012.08387/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":"2026-07-05T01:59:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3YJbaGX+5tFYjaCRCwksDhHFz3pCaPQglzbM2XBN/5bRxLMB0j+CHHPNadKPjScbrfN/KGcAWbvP0xEcUUuzDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T08:06:56.150795Z"},"content_sha256":"41c697e5764893b280317b18153073a1e517b75f6d0f4fba3c97fbf151612a55","schema_version":"1.0","event_id":"sha256:41c697e5764893b280317b18153073a1e517b75f6d0f4fba3c97fbf151612a55"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WKDOCSSDIQS67NCJKFM7SUB42T/bundle.json","state_url":"https://pith.science/pith/WKDOCSSDIQS67NCJKFM7SUB42T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WKDOCSSDIQS67NCJKFM7SUB42T/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":"2026-07-22T08:06:56Z","links":{"resolver":"https://pith.science/pith/WKDOCSSDIQS67NCJKFM7SUB42T","bundle":"https://pith.science/pith/WKDOCSSDIQS67NCJKFM7SUB42T/bundle.json","state":"https://pith.science/pith/WKDOCSSDIQS67NCJKFM7SUB42T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WKDOCSSDIQS67NCJKFM7SUB42T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:WKDOCSSDIQS67NCJKFM7SUB42T","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":"83d30e84bd6cf0680d610fbe0b3941a76732c3934586d6372fe1c51cde256d5c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2020-12-15T16:01:21Z","title_canon_sha256":"1eb994216c4da5634636bb7c3cb973496d7f30549f64bbb00cbf013720d2929d"},"schema_version":"1.0","source":{"id":"2012.08387","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.08387","created_at":"2026-07-05T01:59:42Z"},{"alias_kind":"arxiv_version","alias_value":"2012.08387v1","created_at":"2026-07-05T01:59:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.08387","created_at":"2026-07-05T01:59:42Z"},{"alias_kind":"pith_short_12","alias_value":"WKDOCSSDIQS6","created_at":"2026-07-05T01:59:42Z"},{"alias_kind":"pith_short_16","alias_value":"WKDOCSSDIQS67NCJ","created_at":"2026-07-05T01:59:42Z"},{"alias_kind":"pith_short_8","alias_value":"WKDOCSSD","created_at":"2026-07-05T01:59:42Z"}],"graph_snapshots":[{"event_id":"sha256:41c697e5764893b280317b18153073a1e517b75f6d0f4fba3c97fbf151612a55","target":"graph","created_at":"2026-07-05T01:59:42Z","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/2012.08387/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning (ML) has been widely used in the literature to automate software engineering tasks. However, ML outcomes may be sensitive to randomization in data sampling mechanisms and learning procedures. To understand whether and how researchers in SE address these threats, we surveyed 45 recent papers related to three predictive tasks: defect prediction (DP), predictive mutation testing (PMT), and code smell detection (CSD). We found that less than 50% of the surveyed papers address the threats related to randomized data sampling (via multiple repetitions); only 8% of the papers address ","authors_text":"Annibale Panichella, Cynthia C. S. Liem","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2020-12-15T16:01:21Z","title":"Run, Forest, Run? On Randomization and Reproducibility in Predictive Software Engineering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.08387","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":"sha256:9dce43f9391eaca1f9b761f65a2d183ff6ec52384392fab86f3939948506050a","target":"record","created_at":"2026-07-05T01:59:42Z","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":"83d30e84bd6cf0680d610fbe0b3941a76732c3934586d6372fe1c51cde256d5c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2020-12-15T16:01:21Z","title_canon_sha256":"1eb994216c4da5634636bb7c3cb973496d7f30549f64bbb00cbf013720d2929d"},"schema_version":"1.0","source":{"id":"2012.08387","kind":"arxiv","version":1}},"canonical_sha256":"b286e14a434425efb4495159f9503cd4e6d060ffa5656a292f0e3c45f276e773","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b286e14a434425efb4495159f9503cd4e6d060ffa5656a292f0e3c45f276e773","first_computed_at":"2026-07-05T01:59:42.902597Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:59:42.902597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EXaJ64gt5aTfc6wAsnpOiyTRDvNBuEzeOL1hVlxauXgOnhhXZzE3VjyH/kcAU9nNMUbyUqC/Ui3ujRM+RT50CA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:59:42.903003Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.08387","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9dce43f9391eaca1f9b761f65a2d183ff6ec52384392fab86f3939948506050a","sha256:41c697e5764893b280317b18153073a1e517b75f6d0f4fba3c97fbf151612a55"],"state_sha256":"c4f00820b4162b7c75d8170e2b8eee939026caa3818312a6a42754c8a5a3ad1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jq1iPHP9uDNxDU/CuarLSpzWz+ySXn0W1LA8me3EspyKzui4bTgAyOTkkeFxwuFpqW0CyW1tLA2V+Vn42E51Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-22T08:06:56.152730Z","bundle_sha256":"8a5b5966833ed1ff132c3654a0217925b2145dbb5b677d061bad22d7a72b4f72"}}