{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TEFTYCTZAKMQS3R3PFU7HC463R","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":"61a3c077649418156350b045f0e96444d31e404cdd7f8d68977adb56f80bd489","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T21:19:05Z","title_canon_sha256":"7b9a8022284c2a360a1951976e36ffcac2c3c9a815a1a49c6001fc1f17fefb73"},"schema_version":"1.0","source":{"id":"2210.01234","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.01234","created_at":"2026-07-05T05:03:08Z"},{"alias_kind":"arxiv_version","alias_value":"2210.01234v1","created_at":"2026-07-05T05:03:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01234","created_at":"2026-07-05T05:03:08Z"},{"alias_kind":"pith_short_12","alias_value":"TEFTYCTZAKMQ","created_at":"2026-07-05T05:03:08Z"},{"alias_kind":"pith_short_16","alias_value":"TEFTYCTZAKMQS3R3","created_at":"2026-07-05T05:03:08Z"},{"alias_kind":"pith_short_8","alias_value":"TEFTYCTZ","created_at":"2026-07-05T05:03:08Z"}],"graph_snapshots":[{"event_id":"sha256:45f8f794d752daec6ec814fdc4c91f780f565d778702db27827928bc2bbe18ff","target":"graph","created_at":"2026-07-05T05:03:08Z","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/2210.01234/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern deep learning systems require huge data sets to achieve impressive performance, but there is little guidance on how much or what kind of data to collect. Over-collecting data incurs unnecessary present costs, while under-collecting may incur future costs and delay workflows. We propose a new paradigm for modeling the data collection workflow as a formal optimal data collection problem that allows designers to specify performance targets, collection costs, a time horizon, and penalties for failing to meet the targets. Additionally, this formulation generalizes to tasks requiring multiple","authors_text":"James Lucas, Jose M. Alvarez, Marc T. Law, Rafid Mahmood, Sanja Fidler","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T21:19:05Z","title":"Optimizing Data Collection for Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01234","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:d6519885a4a034653e89a811a60afb0c4846dc9b11f9721aa1e7e3f8d4886514","target":"record","created_at":"2026-07-05T05:03:08Z","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":"61a3c077649418156350b045f0e96444d31e404cdd7f8d68977adb56f80bd489","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T21:19:05Z","title_canon_sha256":"7b9a8022284c2a360a1951976e36ffcac2c3c9a815a1a49c6001fc1f17fefb73"},"schema_version":"1.0","source":{"id":"2210.01234","kind":"arxiv","version":1}},"canonical_sha256":"990b3c0a790299096e3b7969f38b9edc51eae473f6dd0819e1e12fd387cdd96c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"990b3c0a790299096e3b7969f38b9edc51eae473f6dd0819e1e12fd387cdd96c","first_computed_at":"2026-07-05T05:03:08.478502Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:08.478502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JW/wNPkRN6c9E+/RKvZUuvaPN5eyz650rLkV689iJ/mFEXVQBlCNyfUX5yq28z6DpcSsDA0ptyKRu8Rpbd5VBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:08.478859Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.01234","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6519885a4a034653e89a811a60afb0c4846dc9b11f9721aa1e7e3f8d4886514","sha256:45f8f794d752daec6ec814fdc4c91f780f565d778702db27827928bc2bbe18ff"],"state_sha256":"5f05d3c38bc5bef9955c48b29a60ee0612ec5efb73386f718d11cc34290a3995"}