{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HXWDM6NTO3NNQD3A56U7V7ESY2","short_pith_number":"pith:HXWDM6NT","canonical_record":{"source":{"id":"1810.05222","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-11T19:50:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a6e7a05e905223ff3f209acbe77c253afb3209e955fab1e6dadbc38cdd92065b","abstract_canon_sha256":"0872a49a6520b18f488c19e1b00b9279878fe23c95765f8ed924f5f149f74018"},"schema_version":"1.0"},"canonical_sha256":"3dec3679b376dad80f60efa9fafc92c6b4b0bb4a0703350a5b0ab22b3ec603f3","source":{"kind":"arxiv","id":"1810.05222","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.05222","created_at":"2026-05-17T23:52:24Z"},{"alias_kind":"arxiv_version","alias_value":"1810.05222v2","created_at":"2026-05-17T23:52:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.05222","created_at":"2026-05-17T23:52:24Z"},{"alias_kind":"pith_short_12","alias_value":"HXWDM6NTO3NN","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HXWDM6NTO3NNQD3A","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HXWDM6NT","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HXWDM6NTO3NNQD3A56U7V7ESY2","target":"record","payload":{"canonical_record":{"source":{"id":"1810.05222","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-11T19:50:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a6e7a05e905223ff3f209acbe77c253afb3209e955fab1e6dadbc38cdd92065b","abstract_canon_sha256":"0872a49a6520b18f488c19e1b00b9279878fe23c95765f8ed924f5f149f74018"},"schema_version":"1.0"},"canonical_sha256":"3dec3679b376dad80f60efa9fafc92c6b4b0bb4a0703350a5b0ab22b3ec603f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:24.053541Z","signature_b64":"2x5kXI10z2Oh+82fjj50wg1e4mmaWoxO90SL1JbJYjrTDD+weTrrIw5hfbMsdLLOB3nLmd8FcFq+SmNOsU22Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dec3679b376dad80f60efa9fafc92c6b4b0bb4a0703350a5b0ab22b3ec603f3","last_reissued_at":"2026-05-17T23:52:24.052867Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:24.052867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.05222","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:52:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZoMCnuSsXPmoJJgXg/U7dBM7kvgtg1T3JlZjln0IP0cWWHP3sYKxsORpxKbR3dyLI2E48jsF0y1hFxJUjipsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T04:04:27.045524Z"},"content_sha256":"1add4eee08913516b408973d35e3de3e1d92fd22190f947ca37a272b3c09a8e5","schema_version":"1.0","event_id":"sha256:1add4eee08913516b408973d35e3de3e1d92fd22190f947ca37a272b3c09a8e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HXWDM6NTO3NNQD3A56U7V7ESY2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Augmentation via Data Subsampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Michael Kuchnik, Virginia Smith","submitted_at":"2018-10-11T19:50:08Z","abstract_excerpt":"Data augmentation is commonly used to encode invariances in learning methods. However, this process is often performed in an inefficient manner, as artificial examples are created by applying a number of transformations to all points in the training set. The resulting explosion of the dataset size can be an issue in terms of storage and training costs, as well as in selecting and tuning the optimal set of transformations to apply. In this work, we demonstrate that it is possible to significantly reduce the number of data points included in data augmentation while realizing the same accuracy an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.05222","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":""},"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":"2026-05-17T23:52:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qfoF0Q/QYaisFyhkm4t5uoHRj2oRvCnkzn6k+bWdw0Uf30vWN58TLxBCzbIEM/o6+QVQTGc2/Zg7rw/KneBjCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T04:04:27.045906Z"},"content_sha256":"aec94641a5ec3ec892baaf0f6cef05373eafd7023323b1294529fd0c1eba726a","schema_version":"1.0","event_id":"sha256:aec94641a5ec3ec892baaf0f6cef05373eafd7023323b1294529fd0c1eba726a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HXWDM6NTO3NNQD3A56U7V7ESY2/bundle.json","state_url":"https://pith.science/pith/HXWDM6NTO3NNQD3A56U7V7ESY2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HXWDM6NTO3NNQD3A56U7V7ESY2/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":"2026-06-20T04:04:27Z","links":{"resolver":"https://pith.science/pith/HXWDM6NTO3NNQD3A56U7V7ESY2","bundle":"https://pith.science/pith/HXWDM6NTO3NNQD3A56U7V7ESY2/bundle.json","state":"https://pith.science/pith/HXWDM6NTO3NNQD3A56U7V7ESY2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HXWDM6NTO3NNQD3A56U7V7ESY2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HXWDM6NTO3NNQD3A56U7V7ESY2","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":"0872a49a6520b18f488c19e1b00b9279878fe23c95765f8ed924f5f149f74018","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-11T19:50:08Z","title_canon_sha256":"a6e7a05e905223ff3f209acbe77c253afb3209e955fab1e6dadbc38cdd92065b"},"schema_version":"1.0","source":{"id":"1810.05222","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.05222","created_at":"2026-05-17T23:52:24Z"},{"alias_kind":"arxiv_version","alias_value":"1810.05222v2","created_at":"2026-05-17T23:52:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.05222","created_at":"2026-05-17T23:52:24Z"},{"alias_kind":"pith_short_12","alias_value":"HXWDM6NTO3NN","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HXWDM6NTO3NNQD3A","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HXWDM6NT","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:aec94641a5ec3ec892baaf0f6cef05373eafd7023323b1294529fd0c1eba726a","target":"graph","created_at":"2026-05-17T23:52:24Z","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"},"paper":{"abstract_excerpt":"Data augmentation is commonly used to encode invariances in learning methods. However, this process is often performed in an inefficient manner, as artificial examples are created by applying a number of transformations to all points in the training set. The resulting explosion of the dataset size can be an issue in terms of storage and training costs, as well as in selecting and tuning the optimal set of transformations to apply. In this work, we demonstrate that it is possible to significantly reduce the number of data points included in data augmentation while realizing the same accuracy an","authors_text":"Michael Kuchnik, Virginia Smith","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-11T19:50:08Z","title":"Efficient Augmentation via Data Subsampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.05222","kind":"arxiv","version":2},"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":"sha256:1add4eee08913516b408973d35e3de3e1d92fd22190f947ca37a272b3c09a8e5","target":"record","created_at":"2026-05-17T23:52:24Z","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":"0872a49a6520b18f488c19e1b00b9279878fe23c95765f8ed924f5f149f74018","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-11T19:50:08Z","title_canon_sha256":"a6e7a05e905223ff3f209acbe77c253afb3209e955fab1e6dadbc38cdd92065b"},"schema_version":"1.0","source":{"id":"1810.05222","kind":"arxiv","version":2}},"canonical_sha256":"3dec3679b376dad80f60efa9fafc92c6b4b0bb4a0703350a5b0ab22b3ec603f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3dec3679b376dad80f60efa9fafc92c6b4b0bb4a0703350a5b0ab22b3ec603f3","first_computed_at":"2026-05-17T23:52:24.052867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:24.052867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2x5kXI10z2Oh+82fjj50wg1e4mmaWoxO90SL1JbJYjrTDD+weTrrIw5hfbMsdLLOB3nLmd8FcFq+SmNOsU22Dw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:24.053541Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.05222","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1add4eee08913516b408973d35e3de3e1d92fd22190f947ca37a272b3c09a8e5","sha256:aec94641a5ec3ec892baaf0f6cef05373eafd7023323b1294529fd0c1eba726a"],"state_sha256":"4cdd1f114693cba334ea16d454a6fff4ba399fd05deb8347f8f0c38fcd58eba0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EVbHp3XCrdehVppf0+NEMZ6tuWir9NEBgIcjXmRSxBveIHENL40Vlf071arfLhJW8Vnsyn2Q5rjUznNvpcONCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T04:04:27.047882Z","bundle_sha256":"9c39ab22506e9fcc88359bdcda12b8eadacfbd4dfa48d67621eb417c301a79c2"}}