{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BU53BNGYEC3OBNX35JCENCUR6P","short_pith_number":"pith:BU53BNGY","canonical_record":{"source":{"id":"2606.06514","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T09:42:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b376847bfb6f8920140e478d744204a5e8e813acfdbd59922ad1cc08c6a42769","abstract_canon_sha256":"7f8bfbf680475826aaa0f618066e859064f4ee26f1f026d3fd7307711857d19f"},"schema_version":"1.0"},"canonical_sha256":"0d3bb0b4d820b6e0b6fbea44468a91f3eb9abbfb7bf72149f23d54a1dc6d4bb8","source":{"kind":"arxiv","id":"2606.06514","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06514","created_at":"2026-06-08T00:03:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06514v1","created_at":"2026-06-08T00:03:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06514","created_at":"2026-06-08T00:03:40Z"},{"alias_kind":"pith_short_12","alias_value":"BU53BNGYEC3O","created_at":"2026-06-08T00:03:40Z"},{"alias_kind":"pith_short_16","alias_value":"BU53BNGYEC3OBNX3","created_at":"2026-06-08T00:03:40Z"},{"alias_kind":"pith_short_8","alias_value":"BU53BNGY","created_at":"2026-06-08T00:03:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BU53BNGYEC3OBNX35JCENCUR6P","target":"record","payload":{"canonical_record":{"source":{"id":"2606.06514","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T09:42:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b376847bfb6f8920140e478d744204a5e8e813acfdbd59922ad1cc08c6a42769","abstract_canon_sha256":"7f8bfbf680475826aaa0f618066e859064f4ee26f1f026d3fd7307711857d19f"},"schema_version":"1.0"},"canonical_sha256":"0d3bb0b4d820b6e0b6fbea44468a91f3eb9abbfb7bf72149f23d54a1dc6d4bb8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T00:03:40.267486Z","signature_b64":"9SROCbSrjYP8RjMqqA41txVsdAbQnaJQh+YxDhsqQWqept54Pg2TBzGhk9vaKDCSPdscaViyPMZ0eVHjSVQpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d3bb0b4d820b6e0b6fbea44468a91f3eb9abbfb7bf72149f23d54a1dc6d4bb8","last_reissued_at":"2026-06-08T00:03:40.266583Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T00:03:40.266583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.06514","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":"2026-06-08T00:03:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VmQPa/tGTd9kab4iXskql9ysfAfERsTZMAbCDlxh7o7W/CwHexlyhiWeSefvf9PtH9j7XMfqhfm0FlZu/184Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T02:41:15.788642Z"},"content_sha256":"63509b838087b739b00a0597ba7a28f216c874836c01f70cfbe5204ae769b59e","schema_version":"1.0","event_id":"sha256:63509b838087b739b00a0597ba7a28f216c874836c01f70cfbe5204ae769b59e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BU53BNGYEC3OBNX35JCENCUR6P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Detecting and Mitigating Bias by Treating Fairness as a Symmetry Operation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Nishit Singh","submitted_at":"2026-06-02T09:42:54Z","abstract_excerpt":"Machine learning systems deployed in high stakes socioeconomic settings routinely display bias. We formalize bias as a symmetry breaking operation: a classifier is fair if its outputs remain invariant under the counterfactual operation of switching a sensitive attribute, with merit features held fixed. We implement loss based regularization as a symmetry restoring mechanism and evaluate the framework on four synthetic datasets with varying levels of noise, correlation, and bias. The framework achieves upwards of 90\\% violation reduction, with accuracy costs around 5\\%. This framework does not "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06514","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/2606.06514/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":"2026-06-08T00:03:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h9wzajyxlb8ZgbrLtMmBbfOp5xB4kuaHDIFwwDPMaQAZ0ib4gfGPeTKCqHzyQjuFIs04kfOH5nADZ7fiKnR5Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T02:41:15.789026Z"},"content_sha256":"a5d86452c53057c8c1893d1a5fae882cd4f4bb690a68d9040b6dbbddc38b3945","schema_version":"1.0","event_id":"sha256:a5d86452c53057c8c1893d1a5fae882cd4f4bb690a68d9040b6dbbddc38b3945"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BU53BNGYEC3OBNX35JCENCUR6P/bundle.json","state_url":"https://pith.science/pith/BU53BNGYEC3OBNX35JCENCUR6P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BU53BNGYEC3OBNX35JCENCUR6P/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":"2026-06-30T02:41:15Z","links":{"resolver":"https://pith.science/pith/BU53BNGYEC3OBNX35JCENCUR6P","bundle":"https://pith.science/pith/BU53BNGYEC3OBNX35JCENCUR6P/bundle.json","state":"https://pith.science/pith/BU53BNGYEC3OBNX35JCENCUR6P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BU53BNGYEC3OBNX35JCENCUR6P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BU53BNGYEC3OBNX35JCENCUR6P","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":"7f8bfbf680475826aaa0f618066e859064f4ee26f1f026d3fd7307711857d19f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T09:42:54Z","title_canon_sha256":"b376847bfb6f8920140e478d744204a5e8e813acfdbd59922ad1cc08c6a42769"},"schema_version":"1.0","source":{"id":"2606.06514","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06514","created_at":"2026-06-08T00:03:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06514v1","created_at":"2026-06-08T00:03:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06514","created_at":"2026-06-08T00:03:40Z"},{"alias_kind":"pith_short_12","alias_value":"BU53BNGYEC3O","created_at":"2026-06-08T00:03:40Z"},{"alias_kind":"pith_short_16","alias_value":"BU53BNGYEC3OBNX3","created_at":"2026-06-08T00:03:40Z"},{"alias_kind":"pith_short_8","alias_value":"BU53BNGY","created_at":"2026-06-08T00:03:40Z"}],"graph_snapshots":[{"event_id":"sha256:a5d86452c53057c8c1893d1a5fae882cd4f4bb690a68d9040b6dbbddc38b3945","target":"graph","created_at":"2026-06-08T00:03:40Z","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/2606.06514/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning systems deployed in high stakes socioeconomic settings routinely display bias. We formalize bias as a symmetry breaking operation: a classifier is fair if its outputs remain invariant under the counterfactual operation of switching a sensitive attribute, with merit features held fixed. We implement loss based regularization as a symmetry restoring mechanism and evaluate the framework on four synthetic datasets with varying levels of noise, correlation, and bias. The framework achieves upwards of 90\\% violation reduction, with accuracy costs around 5\\%. This framework does not ","authors_text":"Nishit Singh","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T09:42:54Z","title":"Detecting and Mitigating Bias by Treating Fairness as a Symmetry Operation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06514","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":"sha256:63509b838087b739b00a0597ba7a28f216c874836c01f70cfbe5204ae769b59e","target":"record","created_at":"2026-06-08T00:03:40Z","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":"7f8bfbf680475826aaa0f618066e859064f4ee26f1f026d3fd7307711857d19f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T09:42:54Z","title_canon_sha256":"b376847bfb6f8920140e478d744204a5e8e813acfdbd59922ad1cc08c6a42769"},"schema_version":"1.0","source":{"id":"2606.06514","kind":"arxiv","version":1}},"canonical_sha256":"0d3bb0b4d820b6e0b6fbea44468a91f3eb9abbfb7bf72149f23d54a1dc6d4bb8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d3bb0b4d820b6e0b6fbea44468a91f3eb9abbfb7bf72149f23d54a1dc6d4bb8","first_computed_at":"2026-06-08T00:03:40.266583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T00:03:40.266583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9SROCbSrjYP8RjMqqA41txVsdAbQnaJQh+YxDhsqQWqept54Pg2TBzGhk9vaKDCSPdscaViyPMZ0eVHjSVQpDw==","signature_status":"signed_v1","signed_at":"2026-06-08T00:03:40.267486Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.06514","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63509b838087b739b00a0597ba7a28f216c874836c01f70cfbe5204ae769b59e","sha256:a5d86452c53057c8c1893d1a5fae882cd4f4bb690a68d9040b6dbbddc38b3945"],"state_sha256":"a94327b7b81fb3d1f4a44976eab3a47fc1f75e39141453f02153e6b03ac61906"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HSup3arIuCP0Anfybqols2ER/jdp7mp5wTCdKcpl8QzXw4qQLZUXRO/5cFMaVMzlrjUMYoswEFFEjvwOs8QiAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T02:41:15.791438Z","bundle_sha256":"3d26f0ace42b2d9f4b5523f5582629f487f4132d01b402613eab75da03eb5bf3"}}