{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6ZUOHTV56FQRUCJIQB2E3LXPMN","short_pith_number":"pith:6ZUOHTV5","canonical_record":{"source":{"id":"2405.14422","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T10:43:20Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"e7ae42481c22d22ac2f9416eb2c5d939c76d81d7a8f9ebff115e16dd4484b1d0","abstract_canon_sha256":"170132742622ffd14b8bd344df1625fdada05949c1254f391ee902e5ddedfb3f"},"schema_version":"1.0"},"canonical_sha256":"f668e3cebdf1611a092880744daeef6353afe47edcc38b71caff68bd732a7536","source":{"kind":"arxiv","id":"2405.14422","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14422","created_at":"2026-07-05T08:42:54Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14422v3","created_at":"2026-07-05T08:42:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14422","created_at":"2026-07-05T08:42:54Z"},{"alias_kind":"pith_short_12","alias_value":"6ZUOHTV56FQR","created_at":"2026-07-05T08:42:54Z"},{"alias_kind":"pith_short_16","alias_value":"6ZUOHTV56FQRUCJI","created_at":"2026-07-05T08:42:54Z"},{"alias_kind":"pith_short_8","alias_value":"6ZUOHTV5","created_at":"2026-07-05T08:42:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6ZUOHTV56FQRUCJIQB2E3LXPMN","target":"record","payload":{"canonical_record":{"source":{"id":"2405.14422","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T10:43:20Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"e7ae42481c22d22ac2f9416eb2c5d939c76d81d7a8f9ebff115e16dd4484b1d0","abstract_canon_sha256":"170132742622ffd14b8bd344df1625fdada05949c1254f391ee902e5ddedfb3f"},"schema_version":"1.0"},"canonical_sha256":"f668e3cebdf1611a092880744daeef6353afe47edcc38b71caff68bd732a7536","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:54.770045Z","signature_b64":"oQFOPqHx1tsmi/QPRqCZDtN+T8/lzwn6vdNGyQU11jaEqBX7lQEsSGFG1ljdAYn6DwYHLEDAkkm/WHquvdltAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f668e3cebdf1611a092880744daeef6353afe47edcc38b71caff68bd732a7536","last_reissued_at":"2026-07-05T08:42:54.769633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:54.769633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.14422","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:42:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5qhcHFlbHHJ+FDVY+thPc4FeRpEXcyalovYl0JHzIRNI/qEtDQjXiQj7QTGfIAkt52+qXbsaIvN16Cf1ECVdAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:31:45.330989Z"},"content_sha256":"6698f33ef9c6c64f7521b0683c2ffd83ee5f550b94143ff6feae7d3a57a72e8f","schema_version":"1.0","event_id":"sha256:6698f33ef9c6c64f7521b0683c2ffd83ee5f550b94143ff6feae7d3a57a72e8f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6ZUOHTV56FQRUCJIQB2E3LXPMN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unraveling overoptimism and publication bias in ML-driven science","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.LG","authors_text":"Gautam Dasarathy, Pouria Saidi, Visar Berisha","submitted_at":"2024-05-23T10:43:20Z","abstract_excerpt":"Machine Learning (ML) is increasingly used across many disciplines with impressive reported results. However, recent studies suggest published performance of ML models are often overoptimistic. Validity concerns are underscored by findings of an inverse relationship between sample size and reported accuracy in published ML models, contrasting with the theory of learning curves where accuracy should improve or remain stable with increasing sample size. This paper investigates factors contributing to overoptimism in ML-driven science, focusing on overfitting and publication bias. We introduce a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14422","kind":"arxiv","version":3},"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/2405.14422/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":"2026-07-05T08:42:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1mYmmrMpGb/bYZ0R5Rug5UhB4r4dfR8pifPpknrF6LNf4DVyjpWTvb4JZZiTm87afVWbFh6TVOdaekMmHoKYDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:31:45.331479Z"},"content_sha256":"444c20dec2c0d9268286dc87fba6e09f875a099875ae4ae136d7dcaed352a500","schema_version":"1.0","event_id":"sha256:444c20dec2c0d9268286dc87fba6e09f875a099875ae4ae136d7dcaed352a500"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6ZUOHTV56FQRUCJIQB2E3LXPMN/bundle.json","state_url":"https://pith.science/pith/6ZUOHTV56FQRUCJIQB2E3LXPMN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6ZUOHTV56FQRUCJIQB2E3LXPMN/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":"2026-08-03T18:31:45Z","links":{"resolver":"https://pith.science/pith/6ZUOHTV56FQRUCJIQB2E3LXPMN","bundle":"https://pith.science/pith/6ZUOHTV56FQRUCJIQB2E3LXPMN/bundle.json","state":"https://pith.science/pith/6ZUOHTV56FQRUCJIQB2E3LXPMN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6ZUOHTV56FQRUCJIQB2E3LXPMN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6ZUOHTV56FQRUCJIQB2E3LXPMN","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":"170132742622ffd14b8bd344df1625fdada05949c1254f391ee902e5ddedfb3f","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T10:43:20Z","title_canon_sha256":"e7ae42481c22d22ac2f9416eb2c5d939c76d81d7a8f9ebff115e16dd4484b1d0"},"schema_version":"1.0","source":{"id":"2405.14422","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14422","created_at":"2026-07-05T08:42:54Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14422v3","created_at":"2026-07-05T08:42:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14422","created_at":"2026-07-05T08:42:54Z"},{"alias_kind":"pith_short_12","alias_value":"6ZUOHTV56FQR","created_at":"2026-07-05T08:42:54Z"},{"alias_kind":"pith_short_16","alias_value":"6ZUOHTV56FQRUCJI","created_at":"2026-07-05T08:42:54Z"},{"alias_kind":"pith_short_8","alias_value":"6ZUOHTV5","created_at":"2026-07-05T08:42:54Z"}],"graph_snapshots":[{"event_id":"sha256:444c20dec2c0d9268286dc87fba6e09f875a099875ae4ae136d7dcaed352a500","target":"graph","created_at":"2026-07-05T08:42:54Z","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/2405.14422/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine Learning (ML) is increasingly used across many disciplines with impressive reported results. However, recent studies suggest published performance of ML models are often overoptimistic. Validity concerns are underscored by findings of an inverse relationship between sample size and reported accuracy in published ML models, contrasting with the theory of learning curves where accuracy should improve or remain stable with increasing sample size. This paper investigates factors contributing to overoptimism in ML-driven science, focusing on overfitting and publication bias. We introduce a ","authors_text":"Gautam Dasarathy, Pouria Saidi, Visar Berisha","cross_cats":["cs.AI","cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T10:43:20Z","title":"Unraveling overoptimism and publication bias in ML-driven science"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14422","kind":"arxiv","version":3},"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":"sha256:6698f33ef9c6c64f7521b0683c2ffd83ee5f550b94143ff6feae7d3a57a72e8f","target":"record","created_at":"2026-07-05T08:42:54Z","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":"170132742622ffd14b8bd344df1625fdada05949c1254f391ee902e5ddedfb3f","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T10:43:20Z","title_canon_sha256":"e7ae42481c22d22ac2f9416eb2c5d939c76d81d7a8f9ebff115e16dd4484b1d0"},"schema_version":"1.0","source":{"id":"2405.14422","kind":"arxiv","version":3}},"canonical_sha256":"f668e3cebdf1611a092880744daeef6353afe47edcc38b71caff68bd732a7536","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f668e3cebdf1611a092880744daeef6353afe47edcc38b71caff68bd732a7536","first_computed_at":"2026-07-05T08:42:54.769633Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:54.769633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oQFOPqHx1tsmi/QPRqCZDtN+T8/lzwn6vdNGyQU11jaEqBX7lQEsSGFG1ljdAYn6DwYHLEDAkkm/WHquvdltAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:54.770045Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.14422","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6698f33ef9c6c64f7521b0683c2ffd83ee5f550b94143ff6feae7d3a57a72e8f","sha256:444c20dec2c0d9268286dc87fba6e09f875a099875ae4ae136d7dcaed352a500"],"state_sha256":"a208dba8fc1865cf0d1de5b71fe71266fc3b99fe7b266c3d6babc7c2a932e222"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"taokR+L2n3S1NyyJeDxlOSu3f7Y92haJThOzTtjC85atX9XQIXu2QpxlLr2emTbAMMPQd3DCHBF86/7H9eJhCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:31:45.335377Z","bundle_sha256":"9c053050e0ab88051def842a5d25d4bac9d64a7c02a8581be781ed06f73761e7"}}