{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NS4OSU4H35LDPSERGEDIUB3UVF","short_pith_number":"pith:NS4OSU4H","schema_version":"1.0","canonical_sha256":"6cb8e95387df5637c89131068a0774a95f4b360dcf024eed81269816ec527aad","source":{"kind":"arxiv","id":"2111.08190","version":2},"attestation_state":"computed","paper":{"title":"Learning Augmentation Distributions using Transformed Risk Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Edgar Dobriban, Evangelos Chatzipantazis, Kostas Daniilidis, Stefanos Pertigkiozoglou","submitted_at":"2021-11-16T02:07:20Z","abstract_excerpt":"We propose a new \\emph{Transformed Risk Minimization} (TRM) framework as an extension of classical risk minimization. In TRM, we optimize not only over predictive models, but also over data transformations; specifically over distributions thereof. As a key application, we focus on learning augmentations; for instance appropriate rotations of images, to improve classification performance with a given class of predictors. Our TRM method (1) jointly learns transformations and models in a \\emph{single training loop}, (2) works with any training algorithm applicable to standard risk minimization, a"},"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":"2111.08190","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-16T02:07:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2e8fca376bc4e10b6f18eeeb509f922867cebcfdb884f151f0e06508c059121f","abstract_canon_sha256":"f7976e0e4bc99e6d956e93af88c8f7986eaaa020328b37f7f79e61fd32fcc061"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:37.829701Z","signature_b64":"EimGwwSCGV0Bc+mn/WUbngSyVzjPgZfZsLBVy6UDoufAo1Kw5NbatJovglEuKAiMuWsM5XBRgE9089EHK4tcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cb8e95387df5637c89131068a0774a95f4b360dcf024eed81269816ec527aad","last_reissued_at":"2026-07-05T06:57:37.829129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:37.829129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Augmentation Distributions using Transformed Risk Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Edgar Dobriban, Evangelos Chatzipantazis, Kostas Daniilidis, Stefanos Pertigkiozoglou","submitted_at":"2021-11-16T02:07:20Z","abstract_excerpt":"We propose a new \\emph{Transformed Risk Minimization} (TRM) framework as an extension of classical risk minimization. In TRM, we optimize not only over predictive models, but also over data transformations; specifically over distributions thereof. As a key application, we focus on learning augmentations; for instance appropriate rotations of images, to improve classification performance with a given class of predictors. Our TRM method (1) jointly learns transformations and models in a \\emph{single training loop}, (2) works with any training algorithm applicable to standard risk minimization, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08190","kind":"arxiv","version":2},"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/2111.08190/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":"2111.08190","created_at":"2026-07-05T06:57:37.829193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.08190v2","created_at":"2026-07-05T06:57:37.829193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08190","created_at":"2026-07-05T06:57:37.829193+00:00"},{"alias_kind":"pith_short_12","alias_value":"NS4OSU4H35LD","created_at":"2026-07-05T06:57:37.829193+00:00"},{"alias_kind":"pith_short_16","alias_value":"NS4OSU4H35LDPSER","created_at":"2026-07-05T06:57:37.829193+00:00"},{"alias_kind":"pith_short_8","alias_value":"NS4OSU4H","created_at":"2026-07-05T06:57:37.829193+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NS4OSU4H35LDPSERGEDIUB3UVF","json":"https://pith.science/pith/NS4OSU4H35LDPSERGEDIUB3UVF.json","graph_json":"https://pith.science/api/pith-number/NS4OSU4H35LDPSERGEDIUB3UVF/graph.json","events_json":"https://pith.science/api/pith-number/NS4OSU4H35LDPSERGEDIUB3UVF/events.json","paper":"https://pith.science/paper/NS4OSU4H"},"agent_actions":{"view_html":"https://pith.science/pith/NS4OSU4H35LDPSERGEDIUB3UVF","download_json":"https://pith.science/pith/NS4OSU4H35LDPSERGEDIUB3UVF.json","view_paper":"https://pith.science/paper/NS4OSU4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.08190&json=true","fetch_graph":"https://pith.science/api/pith-number/NS4OSU4H35LDPSERGEDIUB3UVF/graph.json","fetch_events":"https://pith.science/api/pith-number/NS4OSU4H35LDPSERGEDIUB3UVF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NS4OSU4H35LDPSERGEDIUB3UVF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NS4OSU4H35LDPSERGEDIUB3UVF/action/storage_attestation","attest_author":"https://pith.science/pith/NS4OSU4H35LDPSERGEDIUB3UVF/action/author_attestation","sign_citation":"https://pith.science/pith/NS4OSU4H35LDPSERGEDIUB3UVF/action/citation_signature","submit_replication":"https://pith.science/pith/NS4OSU4H35LDPSERGEDIUB3UVF/action/replication_record"}},"created_at":"2026-07-05T06:57:37.829193+00:00","updated_at":"2026-07-05T06:57:37.829193+00:00"}