{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:F6I2CF2DIDHAKIADPSZCEKFULW","short_pith_number":"pith:F6I2CF2D","canonical_record":{"source":{"id":"2208.10024","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-22T02:39:05Z","cross_cats_sorted":[],"title_canon_sha256":"fede7c4b0d93a19c4f344bd83ad5e6b4ad9d4487ef29acd741b34766ec31d862","abstract_canon_sha256":"fc4743fa1be169f462dde527ca1e552e386e41d26721f5d7932cea24e5a00637"},"schema_version":"1.0"},"canonical_sha256":"2f91a1174340ce0520037cb22228b45d8c107f8b29f05fbbcf611d9e67c49d7d","source":{"kind":"arxiv","id":"2208.10024","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.10024","created_at":"2026-07-05T05:43:14Z"},{"alias_kind":"arxiv_version","alias_value":"2208.10024v2","created_at":"2026-07-05T05:43:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.10024","created_at":"2026-07-05T05:43:14Z"},{"alias_kind":"pith_short_12","alias_value":"F6I2CF2DIDHA","created_at":"2026-07-05T05:43:14Z"},{"alias_kind":"pith_short_16","alias_value":"F6I2CF2DIDHAKIAD","created_at":"2026-07-05T05:43:14Z"},{"alias_kind":"pith_short_8","alias_value":"F6I2CF2D","created_at":"2026-07-05T05:43:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:F6I2CF2DIDHAKIADPSZCEKFULW","target":"record","payload":{"canonical_record":{"source":{"id":"2208.10024","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-22T02:39:05Z","cross_cats_sorted":[],"title_canon_sha256":"fede7c4b0d93a19c4f344bd83ad5e6b4ad9d4487ef29acd741b34766ec31d862","abstract_canon_sha256":"fc4743fa1be169f462dde527ca1e552e386e41d26721f5d7932cea24e5a00637"},"schema_version":"1.0"},"canonical_sha256":"2f91a1174340ce0520037cb22228b45d8c107f8b29f05fbbcf611d9e67c49d7d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:14.596347Z","signature_b64":"x/kU5AskxbQx1IVEkO/8PHY3lST/+IlzGulrDOhAQ2x1dZKRzzYbMm4oGU20FTevk1APFsLrlbJAik9R+xCFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f91a1174340ce0520037cb22228b45d8c107f8b29f05fbbcf611d9e67c49d7d","last_reissued_at":"2026-07-05T05:43:14.595927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:14.595927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.10024","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":"2026-07-05T05:43:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FZfjVvAExqKYR2yb05ZmTh2Ue1sd6dn0bLXaKzfzJGQJpMY/jBvhUZtCul+phKhXyJxrSjv+1hzglwZG8FiDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:41:28.547014Z"},"content_sha256":"38a70e453505e19e5edb5b2f9e95be19f736349854f21803c56d5f3971b371cb","schema_version":"1.0","event_id":"sha256:38a70e453505e19e5edb5b2f9e95be19f736349854f21803c56d5f3971b371cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:F6I2CF2DIDHAKIADPSZCEKFULW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GCISG: Guided Causal Invariant Learning for Improved Syn-to-real Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gilhyun Nam, Gyeongjae Choi, Kyungmin Lee","submitted_at":"2022-08-22T02:39:05Z","abstract_excerpt":"Training a deep learning model with artificially generated data can be an alternative when training data are scarce, yet it suffers from poor generalization performance due to a large domain gap. In this paper, we characterize the domain gap by using a causal framework for data generation. We assume that the real and synthetic data have common content variables but different style variables. Thus, a model trained on synthetic dataset might have poor generalization as the model learns the nuisance style variables. To that end, we propose causal invariance learning which encourages the model to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.10024","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/2208.10024/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":"2026-07-05T05:43:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j0lWbkj+33uTIbJMNZFG7u4o3X0fIwTfo6MNm8ChykRjMWporHsuuHbZ1MLl9dlRaeoJAGeLhr+BxLxz7tetCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:41:28.547523Z"},"content_sha256":"95a2483e5133da904831a346c132504092a6c49df10fea8f903634ab7698cadc","schema_version":"1.0","event_id":"sha256:95a2483e5133da904831a346c132504092a6c49df10fea8f903634ab7698cadc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F6I2CF2DIDHAKIADPSZCEKFULW/bundle.json","state_url":"https://pith.science/pith/F6I2CF2DIDHAKIADPSZCEKFULW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F6I2CF2DIDHAKIADPSZCEKFULW/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":"2026-08-06T20:41:28Z","links":{"resolver":"https://pith.science/pith/F6I2CF2DIDHAKIADPSZCEKFULW","bundle":"https://pith.science/pith/F6I2CF2DIDHAKIADPSZCEKFULW/bundle.json","state":"https://pith.science/pith/F6I2CF2DIDHAKIADPSZCEKFULW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F6I2CF2DIDHAKIADPSZCEKFULW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:F6I2CF2DIDHAKIADPSZCEKFULW","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":"fc4743fa1be169f462dde527ca1e552e386e41d26721f5d7932cea24e5a00637","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-22T02:39:05Z","title_canon_sha256":"fede7c4b0d93a19c4f344bd83ad5e6b4ad9d4487ef29acd741b34766ec31d862"},"schema_version":"1.0","source":{"id":"2208.10024","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.10024","created_at":"2026-07-05T05:43:14Z"},{"alias_kind":"arxiv_version","alias_value":"2208.10024v2","created_at":"2026-07-05T05:43:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.10024","created_at":"2026-07-05T05:43:14Z"},{"alias_kind":"pith_short_12","alias_value":"F6I2CF2DIDHA","created_at":"2026-07-05T05:43:14Z"},{"alias_kind":"pith_short_16","alias_value":"F6I2CF2DIDHAKIAD","created_at":"2026-07-05T05:43:14Z"},{"alias_kind":"pith_short_8","alias_value":"F6I2CF2D","created_at":"2026-07-05T05:43:14Z"}],"graph_snapshots":[{"event_id":"sha256:95a2483e5133da904831a346c132504092a6c49df10fea8f903634ab7698cadc","target":"graph","created_at":"2026-07-05T05:43:14Z","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/2208.10024/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training a deep learning model with artificially generated data can be an alternative when training data are scarce, yet it suffers from poor generalization performance due to a large domain gap. In this paper, we characterize the domain gap by using a causal framework for data generation. We assume that the real and synthetic data have common content variables but different style variables. Thus, a model trained on synthetic dataset might have poor generalization as the model learns the nuisance style variables. To that end, we propose causal invariance learning which encourages the model to ","authors_text":"Gilhyun Nam, Gyeongjae Choi, Kyungmin Lee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-22T02:39:05Z","title":"GCISG: Guided Causal Invariant Learning for Improved Syn-to-real Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.10024","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":"sha256:38a70e453505e19e5edb5b2f9e95be19f736349854f21803c56d5f3971b371cb","target":"record","created_at":"2026-07-05T05:43:14Z","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":"fc4743fa1be169f462dde527ca1e552e386e41d26721f5d7932cea24e5a00637","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-22T02:39:05Z","title_canon_sha256":"fede7c4b0d93a19c4f344bd83ad5e6b4ad9d4487ef29acd741b34766ec31d862"},"schema_version":"1.0","source":{"id":"2208.10024","kind":"arxiv","version":2}},"canonical_sha256":"2f91a1174340ce0520037cb22228b45d8c107f8b29f05fbbcf611d9e67c49d7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f91a1174340ce0520037cb22228b45d8c107f8b29f05fbbcf611d9e67c49d7d","first_computed_at":"2026-07-05T05:43:14.595927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:43:14.595927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x/kU5AskxbQx1IVEkO/8PHY3lST/+IlzGulrDOhAQ2x1dZKRzzYbMm4oGU20FTevk1APFsLrlbJAik9R+xCFCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:43:14.596347Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.10024","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38a70e453505e19e5edb5b2f9e95be19f736349854f21803c56d5f3971b371cb","sha256:95a2483e5133da904831a346c132504092a6c49df10fea8f903634ab7698cadc"],"state_sha256":"61e59965f1d765e0159bd1a005b61ed2b1dcd22964f490f23b92490dbd216b8b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YT02PndNqTmdDxX2fEQ4F6Sw5X0YI27gmkY5cCg+eyx/RSolfpR2ew4p8OvdBhADSUNOKWG74pEN091sWdXzDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T20:41:28.550926Z","bundle_sha256":"5ae584833d3eea431d1f082fd78e40b915e5ddcc12e054933b79de3621709ff5"}}