{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VGJA5P5ZORG2SQ2A4GWBTGSD4Q","short_pith_number":"pith:VGJA5P5Z","canonical_record":{"source":{"id":"2606.30365","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T14:28:22Z","cross_cats_sorted":[],"title_canon_sha256":"2ece46af116a1e9f5abdc9ce9ab1bbd239613e6793b16f4d952469dd2da089ae","abstract_canon_sha256":"fb0b163bc8b47af28fbf97680ef506a33de6342e925fba173be9f4afc296844e"},"schema_version":"1.0"},"canonical_sha256":"a9920ebfb9744da94340e1ac199a43e405bdb086f4e238714ac3ce6ba072ad02","source":{"kind":"arxiv","id":"2606.30365","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30365","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30365v1","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30365","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"pith_short_12","alias_value":"VGJA5P5ZORG2","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"pith_short_16","alias_value":"VGJA5P5ZORG2SQ2A","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"pith_short_8","alias_value":"VGJA5P5Z","created_at":"2026-06-30T02:18:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VGJA5P5ZORG2SQ2A4GWBTGSD4Q","target":"record","payload":{"canonical_record":{"source":{"id":"2606.30365","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T14:28:22Z","cross_cats_sorted":[],"title_canon_sha256":"2ece46af116a1e9f5abdc9ce9ab1bbd239613e6793b16f4d952469dd2da089ae","abstract_canon_sha256":"fb0b163bc8b47af28fbf97680ef506a33de6342e925fba173be9f4afc296844e"},"schema_version":"1.0"},"canonical_sha256":"a9920ebfb9744da94340e1ac199a43e405bdb086f4e238714ac3ce6ba072ad02","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:18:12.104131Z","signature_b64":"qqN9baCwvXAOlQcNu1RmewzZUcQVhafxHAbTheDuS2gwhB5otR5xqT4KnBox4pRggA/Nj67OoQH4ZkAxsVvPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9920ebfb9744da94340e1ac199a43e405bdb086f4e238714ac3ce6ba072ad02","last_reissued_at":"2026-06-30T02:18:12.103452Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:18:12.103452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.30365","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T02:18:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hJhVjAxULgcBauP0PIxF5MhrBwz+r+4n2DM8GT/4nVN6FNjnecbBXx3KINT5k+Uz0g1Vs87VUrqNGgkR/ggHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T12:06:48.108952Z"},"content_sha256":"3c21c8627f70f47697625077580e2e045b589a1188bbaab41a05846e4d4a85bd","schema_version":"1.0","event_id":"sha256:3c21c8627f70f47697625077580e2e045b589a1188bbaab41a05846e4d4a85bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VGJA5P5ZORG2SQ2A4GWBTGSD4Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CouCE: A Unified Causal Framework for Debiased Deep Metric Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huilin Zhu, Kui Jiang, Meiqi Wan, Xin Xu, Xin Yuan, Zhenyang Niu","submitted_at":"2026-06-29T14:28:22Z","abstract_excerpt":"Deep Metric Learning (DML) often struggles with zero-shot generalization because standard objectives inherently capture what co-occurs rather than what causes similarity. Consequently, DML models are vulnerable to shortcut learning driven by two structurally distinct confounders: background spurious correlations (which create backdoor paths via scene context) and foreground nuisance perturbations (which inject non-semantic variations like pose or illumination). Although existing methods have proposed targeted solutions for each pathway individually, none can simultaneously address both due to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30365","kind":"arxiv","version":1},"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/2606.30365/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":"2026-06-30T02:18:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mw7UMBwjuWYVv1ohuAY/+jd91Y14ijVSYYwA3hMQP/D5AzlCMA2Oq4zZ79VJh2ODdNr4nOCH3JgWA+xR1U6BBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T12:06:48.109342Z"},"content_sha256":"497efd2664a881c7fb9836d8f99d414293b3f24ad5ad595a42ef0f328a938bfb","schema_version":"1.0","event_id":"sha256:497efd2664a881c7fb9836d8f99d414293b3f24ad5ad595a42ef0f328a938bfb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VGJA5P5ZORG2SQ2A4GWBTGSD4Q/bundle.json","state_url":"https://pith.science/pith/VGJA5P5ZORG2SQ2A4GWBTGSD4Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VGJA5P5ZORG2SQ2A4GWBTGSD4Q/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":"2026-06-30T12:06:48Z","links":{"resolver":"https://pith.science/pith/VGJA5P5ZORG2SQ2A4GWBTGSD4Q","bundle":"https://pith.science/pith/VGJA5P5ZORG2SQ2A4GWBTGSD4Q/bundle.json","state":"https://pith.science/pith/VGJA5P5ZORG2SQ2A4GWBTGSD4Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VGJA5P5ZORG2SQ2A4GWBTGSD4Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VGJA5P5ZORG2SQ2A4GWBTGSD4Q","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":"fb0b163bc8b47af28fbf97680ef506a33de6342e925fba173be9f4afc296844e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T14:28:22Z","title_canon_sha256":"2ece46af116a1e9f5abdc9ce9ab1bbd239613e6793b16f4d952469dd2da089ae"},"schema_version":"1.0","source":{"id":"2606.30365","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30365","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30365v1","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30365","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"pith_short_12","alias_value":"VGJA5P5ZORG2","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"pith_short_16","alias_value":"VGJA5P5ZORG2SQ2A","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"pith_short_8","alias_value":"VGJA5P5Z","created_at":"2026-06-30T02:18:12Z"}],"graph_snapshots":[{"event_id":"sha256:497efd2664a881c7fb9836d8f99d414293b3f24ad5ad595a42ef0f328a938bfb","target":"graph","created_at":"2026-06-30T02:18:12Z","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/2606.30365/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Metric Learning (DML) often struggles with zero-shot generalization because standard objectives inherently capture what co-occurs rather than what causes similarity. Consequently, DML models are vulnerable to shortcut learning driven by two structurally distinct confounders: background spurious correlations (which create backdoor paths via scene context) and foreground nuisance perturbations (which inject non-semantic variations like pose or illumination). Although existing methods have proposed targeted solutions for each pathway individually, none can simultaneously address both due to ","authors_text":"Huilin Zhu, Kui Jiang, Meiqi Wan, Xin Xu, Xin Yuan, Zhenyang Niu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T14:28:22Z","title":"CouCE: A Unified Causal Framework for Debiased Deep Metric Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30365","kind":"arxiv","version":1},"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":"sha256:3c21c8627f70f47697625077580e2e045b589a1188bbaab41a05846e4d4a85bd","target":"record","created_at":"2026-06-30T02:18:12Z","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":"fb0b163bc8b47af28fbf97680ef506a33de6342e925fba173be9f4afc296844e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T14:28:22Z","title_canon_sha256":"2ece46af116a1e9f5abdc9ce9ab1bbd239613e6793b16f4d952469dd2da089ae"},"schema_version":"1.0","source":{"id":"2606.30365","kind":"arxiv","version":1}},"canonical_sha256":"a9920ebfb9744da94340e1ac199a43e405bdb086f4e238714ac3ce6ba072ad02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9920ebfb9744da94340e1ac199a43e405bdb086f4e238714ac3ce6ba072ad02","first_computed_at":"2026-06-30T02:18:12.103452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:18:12.103452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qqN9baCwvXAOlQcNu1RmewzZUcQVhafxHAbTheDuS2gwhB5otR5xqT4KnBox4pRggA/Nj67OoQH4ZkAxsVvPDw==","signature_status":"signed_v1","signed_at":"2026-06-30T02:18:12.104131Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.30365","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c21c8627f70f47697625077580e2e045b589a1188bbaab41a05846e4d4a85bd","sha256:497efd2664a881c7fb9836d8f99d414293b3f24ad5ad595a42ef0f328a938bfb"],"state_sha256":"ae0757063bebf8a90ab722bdf2c16f033d4f0f7a0a853454f1c4ca17f69d6347"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8rZiEe7HxQevtGR8TWtRAXYZZJ9m6/NwMGFeliu4vCDBxiK5I4RnCN/eShKOKx/vXg/MITMFzfdtQvu+IgEvAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T12:06:48.111510Z","bundle_sha256":"05531c366261bca7552cf118bc011cd43d7fe6f0aa490442df6839e8b9c61589"}}