{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:J6OBQ74QNU35ODDOYDFCEJ6R47","short_pith_number":"pith:J6OBQ74Q","canonical_record":{"source":{"id":"2205.05256","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-11T04:00:44Z","cross_cats_sorted":[],"title_canon_sha256":"accbfaa64ed4541d24fbcc0e3dd9849a70987f9714ff2222f3e7106607eba884","abstract_canon_sha256":"f7a2dd4b305fef47c5ae9cfe44a790ac65f10eaee467ab5ce803b78350124689"},"schema_version":"1.0"},"canonical_sha256":"4f9c187f906d37d70c6ec0ca2227d1e7d33900e9497581f3328d144a6891c870","source":{"kind":"arxiv","id":"2205.05256","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.05256","created_at":"2026-07-05T04:22:23Z"},{"alias_kind":"arxiv_version","alias_value":"2205.05256v1","created_at":"2026-07-05T04:22:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.05256","created_at":"2026-07-05T04:22:23Z"},{"alias_kind":"pith_short_12","alias_value":"J6OBQ74QNU35","created_at":"2026-07-05T04:22:23Z"},{"alias_kind":"pith_short_16","alias_value":"J6OBQ74QNU35ODDO","created_at":"2026-07-05T04:22:23Z"},{"alias_kind":"pith_short_8","alias_value":"J6OBQ74Q","created_at":"2026-07-05T04:22:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:J6OBQ74QNU35ODDOYDFCEJ6R47","target":"record","payload":{"canonical_record":{"source":{"id":"2205.05256","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-11T04:00:44Z","cross_cats_sorted":[],"title_canon_sha256":"accbfaa64ed4541d24fbcc0e3dd9849a70987f9714ff2222f3e7106607eba884","abstract_canon_sha256":"f7a2dd4b305fef47c5ae9cfe44a790ac65f10eaee467ab5ce803b78350124689"},"schema_version":"1.0"},"canonical_sha256":"4f9c187f906d37d70c6ec0ca2227d1e7d33900e9497581f3328d144a6891c870","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:23.966446Z","signature_b64":"551LNPqmn0BWFy3woS9UOzxSuM2WNUT9WJsfqZem9pkRxOkGnMV0QU7qgd/rUtPJJr7wJ9TVmrGf93n6aFVxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f9c187f906d37d70c6ec0ca2227d1e7d33900e9497581f3328d144a6891c870","last_reissued_at":"2026-07-05T04:22:23.965930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:23.965930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.05256","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":"2026-07-05T04:22:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qh6jISpNM5Hp18lY0j76jgufSMzn19Iv30/kFGV7ZtD9nx+4p13ct03SBPQkdr2WKeNYWd45uejxBq9nASUtDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:46:17.811489Z"},"content_sha256":"1166f91c8bd19152541a76801d251ce313b3c049ee3efdd356be82de1ffe6ec1","schema_version":"1.0","event_id":"sha256:1166f91c8bd19152541a76801d251ce313b3c049ee3efdd356be82de1ffe6ec1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:J6OBQ74QNU35ODDOYDFCEJ6R47","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluation Gaps in Machine Learning Practice","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ben Hutchinson, Christina Greer, Katherine Heller, Negar Rostamzadeh, Vinodkumar Prabhakaran","submitted_at":"2022-05-11T04:00:44Z","abstract_excerpt":"Forming a reliable judgement of a machine learning (ML) model's appropriateness for an application ecosystem is critical for its responsible use, and requires considering a broad range of factors including harms, benefits, and responsibilities. In practice, however, evaluations of ML models frequently focus on only a narrow range of decontextualized predictive behaviours. We examine the evaluation gaps between the idealized breadth of evaluation concerns and the observed narrow focus of actual evaluations. Through an empirical study of papers from recent high-profile conferences in the Compute"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.05256","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/2205.05256/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":"2026-07-05T04:22:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KmFqV+xGwaHn9ybhW//ojcslBLf+jlt6QyXWVx/YfvXXahs81Je16YIHnzY67Am89iJcdVf2ePx3Aqg2NupOBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:46:17.811882Z"},"content_sha256":"602ed76b5690359c55b51ed543d837b69b776fa2e17f3c1f6a323e610c6ad71e","schema_version":"1.0","event_id":"sha256:602ed76b5690359c55b51ed543d837b69b776fa2e17f3c1f6a323e610c6ad71e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J6OBQ74QNU35ODDOYDFCEJ6R47/bundle.json","state_url":"https://pith.science/pith/J6OBQ74QNU35ODDOYDFCEJ6R47/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J6OBQ74QNU35ODDOYDFCEJ6R47/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":"2026-08-12T22:46:17Z","links":{"resolver":"https://pith.science/pith/J6OBQ74QNU35ODDOYDFCEJ6R47","bundle":"https://pith.science/pith/J6OBQ74QNU35ODDOYDFCEJ6R47/bundle.json","state":"https://pith.science/pith/J6OBQ74QNU35ODDOYDFCEJ6R47/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J6OBQ74QNU35ODDOYDFCEJ6R47/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:J6OBQ74QNU35ODDOYDFCEJ6R47","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":"f7a2dd4b305fef47c5ae9cfe44a790ac65f10eaee467ab5ce803b78350124689","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-11T04:00:44Z","title_canon_sha256":"accbfaa64ed4541d24fbcc0e3dd9849a70987f9714ff2222f3e7106607eba884"},"schema_version":"1.0","source":{"id":"2205.05256","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.05256","created_at":"2026-07-05T04:22:23Z"},{"alias_kind":"arxiv_version","alias_value":"2205.05256v1","created_at":"2026-07-05T04:22:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.05256","created_at":"2026-07-05T04:22:23Z"},{"alias_kind":"pith_short_12","alias_value":"J6OBQ74QNU35","created_at":"2026-07-05T04:22:23Z"},{"alias_kind":"pith_short_16","alias_value":"J6OBQ74QNU35ODDO","created_at":"2026-07-05T04:22:23Z"},{"alias_kind":"pith_short_8","alias_value":"J6OBQ74Q","created_at":"2026-07-05T04:22:23Z"}],"graph_snapshots":[{"event_id":"sha256:602ed76b5690359c55b51ed543d837b69b776fa2e17f3c1f6a323e610c6ad71e","target":"graph","created_at":"2026-07-05T04:22:23Z","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/2205.05256/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Forming a reliable judgement of a machine learning (ML) model's appropriateness for an application ecosystem is critical for its responsible use, and requires considering a broad range of factors including harms, benefits, and responsibilities. In practice, however, evaluations of ML models frequently focus on only a narrow range of decontextualized predictive behaviours. We examine the evaluation gaps between the idealized breadth of evaluation concerns and the observed narrow focus of actual evaluations. Through an empirical study of papers from recent high-profile conferences in the Compute","authors_text":"Ben Hutchinson, Christina Greer, Katherine Heller, Negar Rostamzadeh, Vinodkumar Prabhakaran","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-11T04:00:44Z","title":"Evaluation Gaps in Machine Learning Practice"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.05256","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":"sha256:1166f91c8bd19152541a76801d251ce313b3c049ee3efdd356be82de1ffe6ec1","target":"record","created_at":"2026-07-05T04:22:23Z","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":"f7a2dd4b305fef47c5ae9cfe44a790ac65f10eaee467ab5ce803b78350124689","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-11T04:00:44Z","title_canon_sha256":"accbfaa64ed4541d24fbcc0e3dd9849a70987f9714ff2222f3e7106607eba884"},"schema_version":"1.0","source":{"id":"2205.05256","kind":"arxiv","version":1}},"canonical_sha256":"4f9c187f906d37d70c6ec0ca2227d1e7d33900e9497581f3328d144a6891c870","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f9c187f906d37d70c6ec0ca2227d1e7d33900e9497581f3328d144a6891c870","first_computed_at":"2026-07-05T04:22:23.965930Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:22:23.965930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"551LNPqmn0BWFy3woS9UOzxSuM2WNUT9WJsfqZem9pkRxOkGnMV0QU7qgd/rUtPJJr7wJ9TVmrGf93n6aFVxBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:22:23.966446Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.05256","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1166f91c8bd19152541a76801d251ce313b3c049ee3efdd356be82de1ffe6ec1","sha256:602ed76b5690359c55b51ed543d837b69b776fa2e17f3c1f6a323e610c6ad71e"],"state_sha256":"d53ffa09db84a8890a8298c3845d4113e489dc20fe2def6d0eea84eafc6dd7d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EfQr1el6El+zHKtjM1k9NM3J1YhuHzjUvlUsz06nCq/4qgzUDgolQJ3qr3hwUlTCbVsW2NFcihFeShiconocAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T22:46:17.814668Z","bundle_sha256":"dfdb26551b6030fbfe9b5fa2a55947c3b950c5394108ee33ef9497bcc5855071"}}