{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RH37B4NJOTHZZFLCEQSJQPFJIA","short_pith_number":"pith:RH37B4NJ","canonical_record":{"source":{"id":"2106.15209","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2021-06-29T09:50:41Z","cross_cats_sorted":[],"title_canon_sha256":"4508e08a719c7082c42c3b55ca6933e3b5feeb1653358577356911145abf77f9","abstract_canon_sha256":"09baa58186a4279092d2f238cb6dd8bb8dabb7acd0b13764a0ab3a46a69dd29e"},"schema_version":"1.0"},"canonical_sha256":"89f7f0f1a974cf9c95622424983ca94039804cf63971852c27b845b1c5e5983b","source":{"kind":"arxiv","id":"2106.15209","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.15209","created_at":"2026-07-05T02:53:14Z"},{"alias_kind":"arxiv_version","alias_value":"2106.15209v1","created_at":"2026-07-05T02:53:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15209","created_at":"2026-07-05T02:53:14Z"},{"alias_kind":"pith_short_12","alias_value":"RH37B4NJOTHZ","created_at":"2026-07-05T02:53:14Z"},{"alias_kind":"pith_short_16","alias_value":"RH37B4NJOTHZZFLC","created_at":"2026-07-05T02:53:14Z"},{"alias_kind":"pith_short_8","alias_value":"RH37B4NJ","created_at":"2026-07-05T02:53:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RH37B4NJOTHZZFLCEQSJQPFJIA","target":"record","payload":{"canonical_record":{"source":{"id":"2106.15209","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2021-06-29T09:50:41Z","cross_cats_sorted":[],"title_canon_sha256":"4508e08a719c7082c42c3b55ca6933e3b5feeb1653358577356911145abf77f9","abstract_canon_sha256":"09baa58186a4279092d2f238cb6dd8bb8dabb7acd0b13764a0ab3a46a69dd29e"},"schema_version":"1.0"},"canonical_sha256":"89f7f0f1a974cf9c95622424983ca94039804cf63971852c27b845b1c5e5983b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:53:14.787131Z","signature_b64":"L4X4asdEhq2ptgaTEfRFnUEcQGTHG2L9v5EjkEDnJa59TvrAQ4J34gWL9kwNa1h6ZifEZCU31txOi+mvfl92Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89f7f0f1a974cf9c95622424983ca94039804cf63971852c27b845b1c5e5983b","last_reissued_at":"2026-07-05T02:53:14.786643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:53:14.786643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.15209","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":"2026-07-05T02:53:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3zx1S1YK9tCiPblhzVeoM//lQ6FfzKM+s8IdzK9YkO2DFPwfup7ztdqOR5ir4uyf6bVe9O4PLioLQnt+yaZxDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T23:14:43.455721Z"},"content_sha256":"71cfc08bdffc8cf487151256b84bcae7375156bb605cae21c6624106ae662efb","schema_version":"1.0","event_id":"sha256:71cfc08bdffc8cf487151256b84bcae7375156bb605cae21c6624106ae662efb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RH37B4NJOTHZZFLCEQSJQPFJIA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Making the most of small Software Engineering datasets with modern machine learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Julian Aron Prenner, Romain Robbes","submitted_at":"2021-06-29T09:50:41Z","abstract_excerpt":"This paper provides a starting point for Software Engineering (SE) researchers and practitioners faced with the problem of training machine learning models on small datasets. Due to the high costs associated with labeling data, in Software Engineering,there exist many small (< 1 000 samples) and medium-sized (< 100 000 samples) datasets. While deep learning has set the state of the art in many machine learning tasks, it is only recently that it has proven effective on small-sized datasets, primarily thanks to pre-training, a semi-supervised learning technique that leverages abundant unlabelled"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15209","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/2106.15209/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":"2026-07-05T02:53:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9skcKLYxX8Z6U4b8SvEO5F4H8H9RP6izkV8nVbvGKFRVQpfA94ysXLG9Dj+lk7WwCjMcbPEkpmgX08yYdCFgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T23:14:43.456685Z"},"content_sha256":"80867070bd6d95aef533849d6ec7e534e76252eb3073dce7b6c7be8bfef9a1bb","schema_version":"1.0","event_id":"sha256:80867070bd6d95aef533849d6ec7e534e76252eb3073dce7b6c7be8bfef9a1bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RH37B4NJOTHZZFLCEQSJQPFJIA/bundle.json","state_url":"https://pith.science/pith/RH37B4NJOTHZZFLCEQSJQPFJIA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RH37B4NJOTHZZFLCEQSJQPFJIA/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":"2026-08-22T23:14:43Z","links":{"resolver":"https://pith.science/pith/RH37B4NJOTHZZFLCEQSJQPFJIA","bundle":"https://pith.science/pith/RH37B4NJOTHZZFLCEQSJQPFJIA/bundle.json","state":"https://pith.science/pith/RH37B4NJOTHZZFLCEQSJQPFJIA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RH37B4NJOTHZZFLCEQSJQPFJIA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RH37B4NJOTHZZFLCEQSJQPFJIA","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":"09baa58186a4279092d2f238cb6dd8bb8dabb7acd0b13764a0ab3a46a69dd29e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2021-06-29T09:50:41Z","title_canon_sha256":"4508e08a719c7082c42c3b55ca6933e3b5feeb1653358577356911145abf77f9"},"schema_version":"1.0","source":{"id":"2106.15209","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.15209","created_at":"2026-07-05T02:53:14Z"},{"alias_kind":"arxiv_version","alias_value":"2106.15209v1","created_at":"2026-07-05T02:53:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15209","created_at":"2026-07-05T02:53:14Z"},{"alias_kind":"pith_short_12","alias_value":"RH37B4NJOTHZ","created_at":"2026-07-05T02:53:14Z"},{"alias_kind":"pith_short_16","alias_value":"RH37B4NJOTHZZFLC","created_at":"2026-07-05T02:53:14Z"},{"alias_kind":"pith_short_8","alias_value":"RH37B4NJ","created_at":"2026-07-05T02:53:14Z"}],"graph_snapshots":[{"event_id":"sha256:80867070bd6d95aef533849d6ec7e534e76252eb3073dce7b6c7be8bfef9a1bb","target":"graph","created_at":"2026-07-05T02:53:14Z","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/2106.15209/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper provides a starting point for Software Engineering (SE) researchers and practitioners faced with the problem of training machine learning models on small datasets. Due to the high costs associated with labeling data, in Software Engineering,there exist many small (< 1 000 samples) and medium-sized (< 100 000 samples) datasets. While deep learning has set the state of the art in many machine learning tasks, it is only recently that it has proven effective on small-sized datasets, primarily thanks to pre-training, a semi-supervised learning technique that leverages abundant unlabelled","authors_text":"Julian Aron Prenner, Romain Robbes","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2021-06-29T09:50:41Z","title":"Making the most of small Software Engineering datasets with modern machine learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15209","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":"sha256:71cfc08bdffc8cf487151256b84bcae7375156bb605cae21c6624106ae662efb","target":"record","created_at":"2026-07-05T02:53:14Z","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":"09baa58186a4279092d2f238cb6dd8bb8dabb7acd0b13764a0ab3a46a69dd29e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2021-06-29T09:50:41Z","title_canon_sha256":"4508e08a719c7082c42c3b55ca6933e3b5feeb1653358577356911145abf77f9"},"schema_version":"1.0","source":{"id":"2106.15209","kind":"arxiv","version":1}},"canonical_sha256":"89f7f0f1a974cf9c95622424983ca94039804cf63971852c27b845b1c5e5983b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89f7f0f1a974cf9c95622424983ca94039804cf63971852c27b845b1c5e5983b","first_computed_at":"2026-07-05T02:53:14.786643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:53:14.786643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L4X4asdEhq2ptgaTEfRFnUEcQGTHG2L9v5EjkEDnJa59TvrAQ4J34gWL9kwNa1h6ZifEZCU31txOi+mvfl92Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:53:14.787131Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.15209","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71cfc08bdffc8cf487151256b84bcae7375156bb605cae21c6624106ae662efb","sha256:80867070bd6d95aef533849d6ec7e534e76252eb3073dce7b6c7be8bfef9a1bb"],"state_sha256":"68953d4d02a08221b9fc43a3d472f2c274920b82305ad1ba185ae678c4bddfd9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2JlywBh8G5kEZsXQoZV1nAxqTvqBWweq+gWbFlfmBWW+XValHym2iy8pQtm91p+7WCs5qFnRmzAbs8/dbJzdCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T23:14:43.462523Z","bundle_sha256":"0e2e581681323b734ba20545bd52ea7f4598ce7d1f22b00c3f13e9014430eeee"}}