{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SKELFVSAHZOQZI5JSGESTX3POQ","short_pith_number":"pith:SKELFVSA","canonical_record":{"source":{"id":"1907.03644","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-08T14:22:54Z","cross_cats_sorted":[],"title_canon_sha256":"9a36d14e824ab4482ecfa0a910f95d505cfeade2c2b917e7b2304eac496b12b9","abstract_canon_sha256":"1a217655642baa0893126e58f5aaa560458e385cde24584e242a1ec511046129"},"schema_version":"1.0"},"canonical_sha256":"9288b2d6403e5d0ca3a9918929df6f743ab13da2617a9d326a4c2e83fc03e993","source":{"kind":"arxiv","id":"1907.03644","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.03644","created_at":"2026-05-17T23:40:48Z"},{"alias_kind":"arxiv_version","alias_value":"1907.03644v2","created_at":"2026-05-17T23:40:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.03644","created_at":"2026-05-17T23:40:48Z"},{"alias_kind":"pith_short_12","alias_value":"SKELFVSAHZOQ","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SKELFVSAHZOQZI5J","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SKELFVSA","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SKELFVSAHZOQZI5JSGESTX3POQ","target":"record","payload":{"canonical_record":{"source":{"id":"1907.03644","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-08T14:22:54Z","cross_cats_sorted":[],"title_canon_sha256":"9a36d14e824ab4482ecfa0a910f95d505cfeade2c2b917e7b2304eac496b12b9","abstract_canon_sha256":"1a217655642baa0893126e58f5aaa560458e385cde24584e242a1ec511046129"},"schema_version":"1.0"},"canonical_sha256":"9288b2d6403e5d0ca3a9918929df6f743ab13da2617a9d326a4c2e83fc03e993","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:48.581082Z","signature_b64":"bsV4EpUwjN8+P/W5By/DEHs0S362wRp37ZLuEy2mttZUmGp49eTf94SK796/TQ2QqVmc3sXOuAKB6Hq26gnIBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9288b2d6403e5d0ca3a9918929df6f743ab13da2617a9d326a4c2e83fc03e993","last_reissued_at":"2026-05-17T23:40:48.580352Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:48.580352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.03644","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":"2026-05-17T23:40:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oCb2AkjVEjK6PvEBDhvbgkJtC5q4DUzAM2KTey6bKKZQKI9ACyKoZM/LBrjrrkAPZ43GOOap51jCk5264CvNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:56:17.312135Z"},"content_sha256":"3831cd3014e3ab9a3094bcb1e80bc6d4e08fe28475f123bc105f85a0bedcb307","schema_version":"1.0","event_id":"sha256:3831cd3014e3ab9a3094bcb1e80bc6d4e08fe28475f123bc105f85a0bedcb307"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SKELFVSAHZOQZI5JSGESTX3POQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Domain Alignment to Mitigate Low Level Dataset Biases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kirthi Shankar Sivamani","submitted_at":"2019-07-08T14:22:54Z","abstract_excerpt":"Dataset bias is a well-known problem in the field of computer vision. The presence of implicit bias in any image collection hinders a model trained and validated on a particular dataset to yield similar accuracies when tested on other datasets. In this paper, we propose a novel debiasing technique to reduce the effects of a biased training dataset. Our goal is to augment the training data using a generative network by learning a non-linear mapping from the source domain (training set) to the target domain (testing set) while retaining training set labels. The cycle consistency loss and adversa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.03644","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":"2026-05-17T23:40:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PH9Nd9OgjWSRP488CnDBlqFWF5eHQExJOkhoVHBAD1WmQni7cS08hFlszngfXb6jMjOa4dkm+TLaSuFltB1/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:56:17.312854Z"},"content_sha256":"5a250ab2fb0638e3b01ec43bb0b05606d2db0a91e62c1b9c33f80971c174332b","schema_version":"1.0","event_id":"sha256:5a250ab2fb0638e3b01ec43bb0b05606d2db0a91e62c1b9c33f80971c174332b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SKELFVSAHZOQZI5JSGESTX3POQ/bundle.json","state_url":"https://pith.science/pith/SKELFVSAHZOQZI5JSGESTX3POQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SKELFVSAHZOQZI5JSGESTX3POQ/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":"2026-05-25T17:56:17Z","links":{"resolver":"https://pith.science/pith/SKELFVSAHZOQZI5JSGESTX3POQ","bundle":"https://pith.science/pith/SKELFVSAHZOQZI5JSGESTX3POQ/bundle.json","state":"https://pith.science/pith/SKELFVSAHZOQZI5JSGESTX3POQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SKELFVSAHZOQZI5JSGESTX3POQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SKELFVSAHZOQZI5JSGESTX3POQ","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":"1a217655642baa0893126e58f5aaa560458e385cde24584e242a1ec511046129","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-08T14:22:54Z","title_canon_sha256":"9a36d14e824ab4482ecfa0a910f95d505cfeade2c2b917e7b2304eac496b12b9"},"schema_version":"1.0","source":{"id":"1907.03644","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.03644","created_at":"2026-05-17T23:40:48Z"},{"alias_kind":"arxiv_version","alias_value":"1907.03644v2","created_at":"2026-05-17T23:40:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.03644","created_at":"2026-05-17T23:40:48Z"},{"alias_kind":"pith_short_12","alias_value":"SKELFVSAHZOQ","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SKELFVSAHZOQZI5J","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SKELFVSA","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:5a250ab2fb0638e3b01ec43bb0b05606d2db0a91e62c1b9c33f80971c174332b","target":"graph","created_at":"2026-05-17T23:40:48Z","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":"Dataset bias is a well-known problem in the field of computer vision. The presence of implicit bias in any image collection hinders a model trained and validated on a particular dataset to yield similar accuracies when tested on other datasets. In this paper, we propose a novel debiasing technique to reduce the effects of a biased training dataset. Our goal is to augment the training data using a generative network by learning a non-linear mapping from the source domain (training set) to the target domain (testing set) while retaining training set labels. The cycle consistency loss and adversa","authors_text":"Kirthi Shankar Sivamani","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-08T14:22:54Z","title":"Unsupervised Domain Alignment to Mitigate Low Level Dataset Biases"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.03644","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":"sha256:3831cd3014e3ab9a3094bcb1e80bc6d4e08fe28475f123bc105f85a0bedcb307","target":"record","created_at":"2026-05-17T23:40:48Z","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":"1a217655642baa0893126e58f5aaa560458e385cde24584e242a1ec511046129","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-08T14:22:54Z","title_canon_sha256":"9a36d14e824ab4482ecfa0a910f95d505cfeade2c2b917e7b2304eac496b12b9"},"schema_version":"1.0","source":{"id":"1907.03644","kind":"arxiv","version":2}},"canonical_sha256":"9288b2d6403e5d0ca3a9918929df6f743ab13da2617a9d326a4c2e83fc03e993","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9288b2d6403e5d0ca3a9918929df6f743ab13da2617a9d326a4c2e83fc03e993","first_computed_at":"2026-05-17T23:40:48.580352Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:48.580352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bsV4EpUwjN8+P/W5By/DEHs0S362wRp37ZLuEy2mttZUmGp49eTf94SK796/TQ2QqVmc3sXOuAKB6Hq26gnIBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:48.581082Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.03644","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3831cd3014e3ab9a3094bcb1e80bc6d4e08fe28475f123bc105f85a0bedcb307","sha256:5a250ab2fb0638e3b01ec43bb0b05606d2db0a91e62c1b9c33f80971c174332b"],"state_sha256":"3dc4c5245866fd62a56823091499fef7b5660a3848bc67448242d14201342bc4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xg7GpufF6M0brF3iT0W1EFSpPMWB6PAPXRfZ7kl7p28hcWBOpXfEd4aLirvjZ7Fs31iTs7dnlM7FLJRUWm96BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T17:56:17.316839Z","bundle_sha256":"6d81de9f96f9aecf7de6120e29e58c9857cd77c1f56969170aa5af9234a5ddd9"}}