{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PACWRXSEYRDSMQB7BCUR3DLAE6","short_pith_number":"pith:PACWRXSE","canonical_record":{"source":{"id":"1805.06447","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-16T17:53:21Z","cross_cats_sorted":[],"title_canon_sha256":"b8af0624d84b3b3b472adda9cc7c1ea7f6e0953196216de7d1c22e6939a67e4c","abstract_canon_sha256":"3293f672e6f651d0d5102839bd7efeb02a0aefff02dc880d408bfbb9ae16cda9"},"schema_version":"1.0"},"canonical_sha256":"780568de44c44726403f08a91d8d60279b24f61ee19409e08605e8a73a4203fe","source":{"kind":"arxiv","id":"1805.06447","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.06447","created_at":"2026-07-05T01:13:40Z"},{"alias_kind":"arxiv_version","alias_value":"1805.06447v3","created_at":"2026-07-05T01:13:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.06447","created_at":"2026-07-05T01:13:40Z"},{"alias_kind":"pith_short_12","alias_value":"PACWRXSEYRDS","created_at":"2026-07-05T01:13:40Z"},{"alias_kind":"pith_short_16","alias_value":"PACWRXSEYRDSMQB7","created_at":"2026-07-05T01:13:40Z"},{"alias_kind":"pith_short_8","alias_value":"PACWRXSE","created_at":"2026-07-05T01:13:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PACWRXSEYRDSMQB7BCUR3DLAE6","target":"record","payload":{"canonical_record":{"source":{"id":"1805.06447","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-16T17:53:21Z","cross_cats_sorted":[],"title_canon_sha256":"b8af0624d84b3b3b472adda9cc7c1ea7f6e0953196216de7d1c22e6939a67e4c","abstract_canon_sha256":"3293f672e6f651d0d5102839bd7efeb02a0aefff02dc880d408bfbb9ae16cda9"},"schema_version":"1.0"},"canonical_sha256":"780568de44c44726403f08a91d8d60279b24f61ee19409e08605e8a73a4203fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:13:40.980296Z","signature_b64":"JSrg97HOgZRFwA9Ky764fD4AcCBQ2u+aVxQBR8TAITTE5aIOMhzTab4E6T5HLiVNMUTZKKLy1fLlB5VuUXwQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"780568de44c44726403f08a91d8d60279b24f61ee19409e08605e8a73a4203fe","last_reissued_at":"2026-07-05T01:13:40.979873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:13:40.979873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.06447","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:13:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QnwFNEUB1YrZdsbCpumOg/50AJzOOWiShFmJB2Oi/DlBc1li/Gb5ZZp/+SzsmEMSgkPzs0s7p1V+g+ZvOByqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T08:03:42.895699Z"},"content_sha256":"9fa17817de5acc9d960605555e806088bbb5958ecf8dd5f3d630cc6523012a33","schema_version":"1.0","event_id":"sha256:9fa17817de5acc9d960605555e806088bbb5958ecf8dd5f3d630cc6523012a33"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PACWRXSEYRDSMQB7BCUR3DLAE6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Resisting Large Data Variations via Introspective Transformation Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Charless Fowlkes, Wei Shen, Ye Tian, Yunhan Zhao","submitted_at":"2018-05-16T17:53:21Z","abstract_excerpt":"Training deep networks that generalize to a wide range of variations in test data is essential to building accurate and robust image classifiers. One standard strategy is to apply data augmentation to synthetically enlarge the training set. However, data augmentation is essentially a brute-force method which generates uniform samples from some pre-defined set of transformations. In this paper, we propose a principled approach to train networks with significantly improved resistance to large variations between training and testing data. This is achieved by embedding a learnable transformation m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.06447","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/1805.06447/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":"2026-07-05T01:13:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AwVpNVxOWXEcM5+FyzHPzdG210obrFRE1QpH8fC6qx/snRcykD2+DrkQ7GhS/VxKJV90H8vA8vKwJv28JyWEBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T08:03:42.896211Z"},"content_sha256":"8c139e00dadf50da0f37c361f0d128061f4e1e43c0fd963c78622cae83f130e4","schema_version":"1.0","event_id":"sha256:8c139e00dadf50da0f37c361f0d128061f4e1e43c0fd963c78622cae83f130e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PACWRXSEYRDSMQB7BCUR3DLAE6/bundle.json","state_url":"https://pith.science/pith/PACWRXSEYRDSMQB7BCUR3DLAE6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PACWRXSEYRDSMQB7BCUR3DLAE6/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":"2026-08-07T08:03:42Z","links":{"resolver":"https://pith.science/pith/PACWRXSEYRDSMQB7BCUR3DLAE6","bundle":"https://pith.science/pith/PACWRXSEYRDSMQB7BCUR3DLAE6/bundle.json","state":"https://pith.science/pith/PACWRXSEYRDSMQB7BCUR3DLAE6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PACWRXSEYRDSMQB7BCUR3DLAE6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PACWRXSEYRDSMQB7BCUR3DLAE6","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":"3293f672e6f651d0d5102839bd7efeb02a0aefff02dc880d408bfbb9ae16cda9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-16T17:53:21Z","title_canon_sha256":"b8af0624d84b3b3b472adda9cc7c1ea7f6e0953196216de7d1c22e6939a67e4c"},"schema_version":"1.0","source":{"id":"1805.06447","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.06447","created_at":"2026-07-05T01:13:40Z"},{"alias_kind":"arxiv_version","alias_value":"1805.06447v3","created_at":"2026-07-05T01:13:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.06447","created_at":"2026-07-05T01:13:40Z"},{"alias_kind":"pith_short_12","alias_value":"PACWRXSEYRDS","created_at":"2026-07-05T01:13:40Z"},{"alias_kind":"pith_short_16","alias_value":"PACWRXSEYRDSMQB7","created_at":"2026-07-05T01:13:40Z"},{"alias_kind":"pith_short_8","alias_value":"PACWRXSE","created_at":"2026-07-05T01:13:40Z"}],"graph_snapshots":[{"event_id":"sha256:8c139e00dadf50da0f37c361f0d128061f4e1e43c0fd963c78622cae83f130e4","target":"graph","created_at":"2026-07-05T01:13:40Z","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/1805.06447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training deep networks that generalize to a wide range of variations in test data is essential to building accurate and robust image classifiers. One standard strategy is to apply data augmentation to synthetically enlarge the training set. However, data augmentation is essentially a brute-force method which generates uniform samples from some pre-defined set of transformations. In this paper, we propose a principled approach to train networks with significantly improved resistance to large variations between training and testing data. This is achieved by embedding a learnable transformation m","authors_text":"Alan Yuille, Charless Fowlkes, Wei Shen, Ye Tian, Yunhan Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-16T17:53:21Z","title":"Resisting Large Data Variations via Introspective Transformation Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.06447","kind":"arxiv","version":3},"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":"sha256:9fa17817de5acc9d960605555e806088bbb5958ecf8dd5f3d630cc6523012a33","target":"record","created_at":"2026-07-05T01:13:40Z","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":"3293f672e6f651d0d5102839bd7efeb02a0aefff02dc880d408bfbb9ae16cda9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-16T17:53:21Z","title_canon_sha256":"b8af0624d84b3b3b472adda9cc7c1ea7f6e0953196216de7d1c22e6939a67e4c"},"schema_version":"1.0","source":{"id":"1805.06447","kind":"arxiv","version":3}},"canonical_sha256":"780568de44c44726403f08a91d8d60279b24f61ee19409e08605e8a73a4203fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"780568de44c44726403f08a91d8d60279b24f61ee19409e08605e8a73a4203fe","first_computed_at":"2026-07-05T01:13:40.979873Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:13:40.979873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JSrg97HOgZRFwA9Ky764fD4AcCBQ2u+aVxQBR8TAITTE5aIOMhzTab4E6T5HLiVNMUTZKKLy1fLlB5VuUXwQAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:13:40.980296Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.06447","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fa17817de5acc9d960605555e806088bbb5958ecf8dd5f3d630cc6523012a33","sha256:8c139e00dadf50da0f37c361f0d128061f4e1e43c0fd963c78622cae83f130e4"],"state_sha256":"312ce3de1b3bbf8eddd4a22c68ad764ee86d215bbd635247df198961aa36853b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ae+NilDjmhBbag0BS/LFJzXVAvNOWE5DTYJMtcv5m+igLz6/46oH37PWWvNuBML0WS4s7QeVYznI2I8944iSAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T08:03:42.901572Z","bundle_sha256":"9e7b0e4e36893a5e44744ca5208d81cd69bf6216302d23259dc9ddf9d2fd5dd4"}}