{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RSMSX67N6BWCHOTIPJMFH4MUJA","short_pith_number":"pith:RSMSX67N","canonical_record":{"source":{"id":"2401.02150","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T08:57:09Z","cross_cats_sorted":[],"title_canon_sha256":"c9cdd6a2725656ef41825d680d31ab0e9d40551b062335a06dbc7bfc23ef020d","abstract_canon_sha256":"1e431554bc070e53cc79cb5b294c942cd81664728f221db7e8044b78f2d65436"},"schema_version":"1.0"},"canonical_sha256":"8c992bfbedf06c23ba687a5853f19448161fcd6dfb3cdaed21a12040f2389e0b","source":{"kind":"arxiv","id":"2401.02150","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.02150","created_at":"2026-07-05T09:12:58Z"},{"alias_kind":"arxiv_version","alias_value":"2401.02150v2","created_at":"2026-07-05T09:12:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02150","created_at":"2026-07-05T09:12:58Z"},{"alias_kind":"pith_short_12","alias_value":"RSMSX67N6BWC","created_at":"2026-07-05T09:12:58Z"},{"alias_kind":"pith_short_16","alias_value":"RSMSX67N6BWCHOTI","created_at":"2026-07-05T09:12:58Z"},{"alias_kind":"pith_short_8","alias_value":"RSMSX67N","created_at":"2026-07-05T09:12:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RSMSX67N6BWCHOTIPJMFH4MUJA","target":"record","payload":{"canonical_record":{"source":{"id":"2401.02150","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T08:57:09Z","cross_cats_sorted":[],"title_canon_sha256":"c9cdd6a2725656ef41825d680d31ab0e9d40551b062335a06dbc7bfc23ef020d","abstract_canon_sha256":"1e431554bc070e53cc79cb5b294c942cd81664728f221db7e8044b78f2d65436"},"schema_version":"1.0"},"canonical_sha256":"8c992bfbedf06c23ba687a5853f19448161fcd6dfb3cdaed21a12040f2389e0b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:58.174696Z","signature_b64":"HTw+CdVS64sh10W/f28ZUS9RGGwpMyvzZ896Evp+ebvXVHApa/DGh5gUBM4sz/Snf/vZsrGDYmCCddflva3OBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c992bfbedf06c23ba687a5853f19448161fcd6dfb3cdaed21a12040f2389e0b","last_reissued_at":"2026-07-05T09:12:58.174096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:58.174096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.02150","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":"2026-07-05T09:12:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U0Kzv7AEPlWXrS1d8rLVDdgzrIsREU8x4klLaPWbn8fDqbHXL4BRKVbbsC8V0X878yMFvsiMoBnwqpOvSdmeCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T22:39:07.064949Z"},"content_sha256":"da6fee2dc8f8fa62dc63332aa4c954c9049b0d0391231f913937d347bf29add4","schema_version":"1.0","event_id":"sha256:da6fee2dc8f8fa62dc63332aa4c954c9049b0d0391231f913937d347bf29add4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RSMSX67N6BWCHOTIPJMFH4MUJA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Marginal Debiased Network for Fair Visual Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiani Hu, Mei Wang, Sen Su, Weihong Deng","submitted_at":"2024-01-04T08:57:09Z","abstract_excerpt":"Deep neural networks (DNNs) are often prone to learn the spurious correlations between target classes and bias attributes, like gender and race, inherent in a major portion of training data (bias-aligned samples), thus showing unfair behavior and arising controversy in the modern pluralistic and egalitarian society. In this paper, we propose a novel marginal debiased network (MDN) to learn debiased representations. More specifically, a marginal softmax loss (MSL) is designed by introducing the idea of margin penalty into the fairness problem, which assigns a larger margin for bias-conflicting "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02150","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/2401.02150/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":"2026-07-05T09:12:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y8SlXuesrmBoLCCaVbmfT6hbFXuU786F4H+4lLhuO8SLW3n6ZndPRXIzKSEQg0NVTSqIeBWxWSsOFiCMvgdUBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T22:39:07.065311Z"},"content_sha256":"00c5c39616bd3a4f5faafb9c97aeb7c0f658402f8c55c8a99fb8781d283af99d","schema_version":"1.0","event_id":"sha256:00c5c39616bd3a4f5faafb9c97aeb7c0f658402f8c55c8a99fb8781d283af99d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RSMSX67N6BWCHOTIPJMFH4MUJA/bundle.json","state_url":"https://pith.science/pith/RSMSX67N6BWCHOTIPJMFH4MUJA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RSMSX67N6BWCHOTIPJMFH4MUJA/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":"2026-07-26T22:39:07Z","links":{"resolver":"https://pith.science/pith/RSMSX67N6BWCHOTIPJMFH4MUJA","bundle":"https://pith.science/pith/RSMSX67N6BWCHOTIPJMFH4MUJA/bundle.json","state":"https://pith.science/pith/RSMSX67N6BWCHOTIPJMFH4MUJA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RSMSX67N6BWCHOTIPJMFH4MUJA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RSMSX67N6BWCHOTIPJMFH4MUJA","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":"1e431554bc070e53cc79cb5b294c942cd81664728f221db7e8044b78f2d65436","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T08:57:09Z","title_canon_sha256":"c9cdd6a2725656ef41825d680d31ab0e9d40551b062335a06dbc7bfc23ef020d"},"schema_version":"1.0","source":{"id":"2401.02150","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.02150","created_at":"2026-07-05T09:12:58Z"},{"alias_kind":"arxiv_version","alias_value":"2401.02150v2","created_at":"2026-07-05T09:12:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02150","created_at":"2026-07-05T09:12:58Z"},{"alias_kind":"pith_short_12","alias_value":"RSMSX67N6BWC","created_at":"2026-07-05T09:12:58Z"},{"alias_kind":"pith_short_16","alias_value":"RSMSX67N6BWCHOTI","created_at":"2026-07-05T09:12:58Z"},{"alias_kind":"pith_short_8","alias_value":"RSMSX67N","created_at":"2026-07-05T09:12:58Z"}],"graph_snapshots":[{"event_id":"sha256:00c5c39616bd3a4f5faafb9c97aeb7c0f658402f8c55c8a99fb8781d283af99d","target":"graph","created_at":"2026-07-05T09:12:58Z","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/2401.02150/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks (DNNs) are often prone to learn the spurious correlations between target classes and bias attributes, like gender and race, inherent in a major portion of training data (bias-aligned samples), thus showing unfair behavior and arising controversy in the modern pluralistic and egalitarian society. In this paper, we propose a novel marginal debiased network (MDN) to learn debiased representations. More specifically, a marginal softmax loss (MSL) is designed by introducing the idea of margin penalty into the fairness problem, which assigns a larger margin for bias-conflicting ","authors_text":"Jiani Hu, Mei Wang, Sen Su, Weihong Deng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T08:57:09Z","title":"Marginal Debiased Network for Fair Visual Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02150","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:da6fee2dc8f8fa62dc63332aa4c954c9049b0d0391231f913937d347bf29add4","target":"record","created_at":"2026-07-05T09:12:58Z","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":"1e431554bc070e53cc79cb5b294c942cd81664728f221db7e8044b78f2d65436","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T08:57:09Z","title_canon_sha256":"c9cdd6a2725656ef41825d680d31ab0e9d40551b062335a06dbc7bfc23ef020d"},"schema_version":"1.0","source":{"id":"2401.02150","kind":"arxiv","version":2}},"canonical_sha256":"8c992bfbedf06c23ba687a5853f19448161fcd6dfb3cdaed21a12040f2389e0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c992bfbedf06c23ba687a5853f19448161fcd6dfb3cdaed21a12040f2389e0b","first_computed_at":"2026-07-05T09:12:58.174096Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:12:58.174096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HTw+CdVS64sh10W/f28ZUS9RGGwpMyvzZ896Evp+ebvXVHApa/DGh5gUBM4sz/Snf/vZsrGDYmCCddflva3OBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:12:58.174696Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.02150","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da6fee2dc8f8fa62dc63332aa4c954c9049b0d0391231f913937d347bf29add4","sha256:00c5c39616bd3a4f5faafb9c97aeb7c0f658402f8c55c8a99fb8781d283af99d"],"state_sha256":"930cf2f287a2c5721c5ebb1df46088b8a88ffa02bc81bb07167d7aa5e197aaed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1YlcQc40kUnYB1/+07QjweTcuiVBz1K1DIc3Z8QW5qXD2q/W6nSAVeJAtBAVQV0WUc4qbGJOjuUpSGhXrI6hBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T22:39:07.067397Z","bundle_sha256":"82c61335d01fe9c886f8dfcb41383ed8955813217ee23b3f0b279340f88a03d3"}}