{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:66E6S43ALM3KI36EDRSCP5M3RY","short_pith_number":"pith:66E6S43A","canonical_record":{"source":{"id":"2109.05535","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-12T15:12:23Z","cross_cats_sorted":[],"title_canon_sha256":"7cd084494939816f47b975238be1bec3769c3e2330f15a910dbe92ea54ad469f","abstract_canon_sha256":"59462bd30c27ac747aab60bd3d35cef5bb4408dc842426fee86b91d83274c83f"},"schema_version":"1.0"},"canonical_sha256":"f789e973605b36a46fc41c6427f59b8e145998ef36c0dce2e43f238d7abef0d2","source":{"kind":"arxiv","id":"2109.05535","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.05535","created_at":"2026-07-05T03:13:40Z"},{"alias_kind":"arxiv_version","alias_value":"2109.05535v1","created_at":"2026-07-05T03:13:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05535","created_at":"2026-07-05T03:13:40Z"},{"alias_kind":"pith_short_12","alias_value":"66E6S43ALM3K","created_at":"2026-07-05T03:13:40Z"},{"alias_kind":"pith_short_16","alias_value":"66E6S43ALM3KI36E","created_at":"2026-07-05T03:13:40Z"},{"alias_kind":"pith_short_8","alias_value":"66E6S43A","created_at":"2026-07-05T03:13:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:66E6S43ALM3KI36EDRSCP5M3RY","target":"record","payload":{"canonical_record":{"source":{"id":"2109.05535","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-12T15:12:23Z","cross_cats_sorted":[],"title_canon_sha256":"7cd084494939816f47b975238be1bec3769c3e2330f15a910dbe92ea54ad469f","abstract_canon_sha256":"59462bd30c27ac747aab60bd3d35cef5bb4408dc842426fee86b91d83274c83f"},"schema_version":"1.0"},"canonical_sha256":"f789e973605b36a46fc41c6427f59b8e145998ef36c0dce2e43f238d7abef0d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:40.047401Z","signature_b64":"MaIEUQNrsl/DBa/U9uNakUJNpWXAfdAU9jUaTVNDeBhBGEimP3LnfIrSgjOFRjnorLJFSVzRXzDNur4vfNY7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f789e973605b36a46fc41c6427f59b8e145998ef36c0dce2e43f238d7abef0d2","last_reissued_at":"2026-07-05T03:13:40.047038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:40.047038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.05535","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":"2026-07-05T03:13:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jKhFtxExLUquh2UMSJ3gwZ+c52Dey+PTK4nfnDqN5+OmB5QFUbAhMclXde6163rO32yxTACLcXMy1G8ndwMKDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:07:42.367576Z"},"content_sha256":"e3b8dc4f59e5a4250f58177404d0b72f82ad712c3b882d47320121f7be6c7073","schema_version":"1.0","event_id":"sha256:e3b8dc4f59e5a4250f58177404d0b72f82ad712c3b882d47320121f7be6c7073"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:66E6S43ALM3KI36EDRSCP5M3RY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adversarial Representation Learning With Closed-Form Solvers","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bashir Sadeghi, Lan Wang, Vishnu Naresh Boddeti","submitted_at":"2021-09-12T15:12:23Z","abstract_excerpt":"Adversarial representation learning aims to learn data representations for a target task while removing unwanted sensitive information at the same time. Existing methods learn model parameters iteratively through stochastic gradient descent-ascent, which is often unstable and unreliable in practice. To overcome this challenge, we adopt closed-form solvers for the adversary and target task. We model them as kernel ridge regressors and analytically determine an upper-bound on the optimal dimensionality of representation. Our solution, dubbed OptNet-ARL, reduces to a stable one one-shot optimizat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05535","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/2109.05535/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":"2026-07-05T03:13:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s8l21RvuJv2Miqa5+pqVyHrOtIjH1A+kpbpkLg/5FSF46Y9BKJU41M3U0XhvDMZNlFsYHN5TI2xMjTqEp9D1Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:07:42.368182Z"},"content_sha256":"faa15c3ac7183dbcc6026d5b35caba7f3cebd366d5b6a8fc471283bfc2130e7a","schema_version":"1.0","event_id":"sha256:faa15c3ac7183dbcc6026d5b35caba7f3cebd366d5b6a8fc471283bfc2130e7a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/66E6S43ALM3KI36EDRSCP5M3RY/bundle.json","state_url":"https://pith.science/pith/66E6S43ALM3KI36EDRSCP5M3RY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/66E6S43ALM3KI36EDRSCP5M3RY/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":"2026-08-06T12:07:42Z","links":{"resolver":"https://pith.science/pith/66E6S43ALM3KI36EDRSCP5M3RY","bundle":"https://pith.science/pith/66E6S43ALM3KI36EDRSCP5M3RY/bundle.json","state":"https://pith.science/pith/66E6S43ALM3KI36EDRSCP5M3RY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/66E6S43ALM3KI36EDRSCP5M3RY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:66E6S43ALM3KI36EDRSCP5M3RY","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":"59462bd30c27ac747aab60bd3d35cef5bb4408dc842426fee86b91d83274c83f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-12T15:12:23Z","title_canon_sha256":"7cd084494939816f47b975238be1bec3769c3e2330f15a910dbe92ea54ad469f"},"schema_version":"1.0","source":{"id":"2109.05535","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.05535","created_at":"2026-07-05T03:13:40Z"},{"alias_kind":"arxiv_version","alias_value":"2109.05535v1","created_at":"2026-07-05T03:13:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05535","created_at":"2026-07-05T03:13:40Z"},{"alias_kind":"pith_short_12","alias_value":"66E6S43ALM3K","created_at":"2026-07-05T03:13:40Z"},{"alias_kind":"pith_short_16","alias_value":"66E6S43ALM3KI36E","created_at":"2026-07-05T03:13:40Z"},{"alias_kind":"pith_short_8","alias_value":"66E6S43A","created_at":"2026-07-05T03:13:40Z"}],"graph_snapshots":[{"event_id":"sha256:faa15c3ac7183dbcc6026d5b35caba7f3cebd366d5b6a8fc471283bfc2130e7a","target":"graph","created_at":"2026-07-05T03:13:40Z","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/2109.05535/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adversarial representation learning aims to learn data representations for a target task while removing unwanted sensitive information at the same time. Existing methods learn model parameters iteratively through stochastic gradient descent-ascent, which is often unstable and unreliable in practice. To overcome this challenge, we adopt closed-form solvers for the adversary and target task. We model them as kernel ridge regressors and analytically determine an upper-bound on the optimal dimensionality of representation. Our solution, dubbed OptNet-ARL, reduces to a stable one one-shot optimizat","authors_text":"Bashir Sadeghi, Lan Wang, Vishnu Naresh Boddeti","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-12T15:12:23Z","title":"Adversarial Representation Learning With Closed-Form Solvers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05535","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:e3b8dc4f59e5a4250f58177404d0b72f82ad712c3b882d47320121f7be6c7073","target":"record","created_at":"2026-07-05T03:13:40Z","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":"59462bd30c27ac747aab60bd3d35cef5bb4408dc842426fee86b91d83274c83f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-12T15:12:23Z","title_canon_sha256":"7cd084494939816f47b975238be1bec3769c3e2330f15a910dbe92ea54ad469f"},"schema_version":"1.0","source":{"id":"2109.05535","kind":"arxiv","version":1}},"canonical_sha256":"f789e973605b36a46fc41c6427f59b8e145998ef36c0dce2e43f238d7abef0d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f789e973605b36a46fc41c6427f59b8e145998ef36c0dce2e43f238d7abef0d2","first_computed_at":"2026-07-05T03:13:40.047038Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:13:40.047038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MaIEUQNrsl/DBa/U9uNakUJNpWXAfdAU9jUaTVNDeBhBGEimP3LnfIrSgjOFRjnorLJFSVzRXzDNur4vfNY7DA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:13:40.047401Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.05535","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3b8dc4f59e5a4250f58177404d0b72f82ad712c3b882d47320121f7be6c7073","sha256:faa15c3ac7183dbcc6026d5b35caba7f3cebd366d5b6a8fc471283bfc2130e7a"],"state_sha256":"c64b5a456a1c0cd9c0d6c8099bb51d594dd07356ba48e495e01769fac3f54e78"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xoqYVEo57UksKMWpIgPHWwB3KpCrXgNQ2WFTS5HpkuiQf0CGsgORf/Gmvpo2lRdqZiUfY0kl4wxsrCuKEIHRBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T12:07:42.372200Z","bundle_sha256":"e9027fe465e3aa0a15fb8b9b82bcbe55372ba18b65fe02157a1c66d01ed6078f"}}