{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KX3C624F6G7OIWLC3KBI2TC7EG","short_pith_number":"pith:KX3C624F","schema_version":"1.0","canonical_sha256":"55f62f6b85f1bee45962da828d4c5f2196ad3151f54a108cf0a969da32e925a7","source":{"kind":"arxiv","id":"2005.14707","version":3},"attestation_state":"computed","paper":{"title":"Towards Context-Agnostic Learning Using Synthetic Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Charles Jin, Martin Rinard","submitted_at":"2020-05-29T17:53:25Z","abstract_excerpt":"We propose a novel setting for learning, where the input domain is the image of a map defined on the product of two sets, one of which completely determines the labels. We derive a new risk bound for this setting that decomposes into a bias and an error term, and exhibits a surprisingly weak dependence on the true labels. Inspired by these results, we present an algorithm aimed at minimizing the bias term by exploiting the ability to sample from each set independently. We apply our setting to visual classification tasks, where our approach enables us to train classifiers on datasets that consi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2005.14707","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-29T17:53:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c834b7010ae06187587e5df323803a5bf13d08393597396d1e42c9b6e863c5ec","abstract_canon_sha256":"9af08cd7a1f4c317fc933b9a122b8ff3bb8dfaaa3ea65a2afa554221d2051fe0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:12.035352Z","signature_b64":"dGtw0cTjr3YeSj6eYnFycq053kxH1w9w7ud3bV5IiakPd5WEuHSOQ7Q1MnGhy4FywXwISlqRwN24q9mOs8bzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55f62f6b85f1bee45962da828d4c5f2196ad3151f54a108cf0a969da32e925a7","last_reissued_at":"2026-07-05T03:38:12.034795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:12.034795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Context-Agnostic Learning Using Synthetic Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Charles Jin, Martin Rinard","submitted_at":"2020-05-29T17:53:25Z","abstract_excerpt":"We propose a novel setting for learning, where the input domain is the image of a map defined on the product of two sets, one of which completely determines the labels. We derive a new risk bound for this setting that decomposes into a bias and an error term, and exhibits a surprisingly weak dependence on the true labels. Inspired by these results, we present an algorithm aimed at minimizing the bias term by exploiting the ability to sample from each set independently. We apply our setting to visual classification tasks, where our approach enables us to train classifiers on datasets that consi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.14707","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/2005.14707/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2005.14707","created_at":"2026-07-05T03:38:12.034857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.14707v3","created_at":"2026-07-05T03:38:12.034857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.14707","created_at":"2026-07-05T03:38:12.034857+00:00"},{"alias_kind":"pith_short_12","alias_value":"KX3C624F6G7O","created_at":"2026-07-05T03:38:12.034857+00:00"},{"alias_kind":"pith_short_16","alias_value":"KX3C624F6G7OIWLC","created_at":"2026-07-05T03:38:12.034857+00:00"},{"alias_kind":"pith_short_8","alias_value":"KX3C624F","created_at":"2026-07-05T03:38:12.034857+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02365","citing_title":"Dynamic real-time multi-UAV cooperative mission planning method under multiple constraints","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KX3C624F6G7OIWLC3KBI2TC7EG","json":"https://pith.science/pith/KX3C624F6G7OIWLC3KBI2TC7EG.json","graph_json":"https://pith.science/api/pith-number/KX3C624F6G7OIWLC3KBI2TC7EG/graph.json","events_json":"https://pith.science/api/pith-number/KX3C624F6G7OIWLC3KBI2TC7EG/events.json","paper":"https://pith.science/paper/KX3C624F"},"agent_actions":{"view_html":"https://pith.science/pith/KX3C624F6G7OIWLC3KBI2TC7EG","download_json":"https://pith.science/pith/KX3C624F6G7OIWLC3KBI2TC7EG.json","view_paper":"https://pith.science/paper/KX3C624F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.14707&json=true","fetch_graph":"https://pith.science/api/pith-number/KX3C624F6G7OIWLC3KBI2TC7EG/graph.json","fetch_events":"https://pith.science/api/pith-number/KX3C624F6G7OIWLC3KBI2TC7EG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KX3C624F6G7OIWLC3KBI2TC7EG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KX3C624F6G7OIWLC3KBI2TC7EG/action/storage_attestation","attest_author":"https://pith.science/pith/KX3C624F6G7OIWLC3KBI2TC7EG/action/author_attestation","sign_citation":"https://pith.science/pith/KX3C624F6G7OIWLC3KBI2TC7EG/action/citation_signature","submit_replication":"https://pith.science/pith/KX3C624F6G7OIWLC3KBI2TC7EG/action/replication_record"}},"created_at":"2026-07-05T03:38:12.034857+00:00","updated_at":"2026-07-05T03:38:12.034857+00:00"}