{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YIYOKQLHIALMZY3QEKWYNFETQQ","short_pith_number":"pith:YIYOKQLH","canonical_record":{"source":{"id":"2404.12292","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T16:12:38Z","cross_cats_sorted":[],"title_canon_sha256":"cf74d3cf322a1a3f681511301aeadc0ae9d8d4e4746908e0b15a53a4b5dbcff4","abstract_canon_sha256":"0cf3ff74c5f280eb61df7837146e2aff65d9ab49cb09514310f2ae25f03d04f8"},"schema_version":"1.0"},"canonical_sha256":"c230e541674016cce37022ad869493842d4c67cc4bd3088d1375764c6fc4419c","source":{"kind":"arxiv","id":"2404.12292","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.12292","created_at":"2026-07-05T08:09:38Z"},{"alias_kind":"arxiv_version","alias_value":"2404.12292v1","created_at":"2026-07-05T08:09:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12292","created_at":"2026-07-05T08:09:38Z"},{"alias_kind":"pith_short_12","alias_value":"YIYOKQLHIALM","created_at":"2026-07-05T08:09:38Z"},{"alias_kind":"pith_short_16","alias_value":"YIYOKQLHIALMZY3Q","created_at":"2026-07-05T08:09:38Z"},{"alias_kind":"pith_short_8","alias_value":"YIYOKQLH","created_at":"2026-07-05T08:09:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YIYOKQLHIALMZY3QEKWYNFETQQ","target":"record","payload":{"canonical_record":{"source":{"id":"2404.12292","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T16:12:38Z","cross_cats_sorted":[],"title_canon_sha256":"cf74d3cf322a1a3f681511301aeadc0ae9d8d4e4746908e0b15a53a4b5dbcff4","abstract_canon_sha256":"0cf3ff74c5f280eb61df7837146e2aff65d9ab49cb09514310f2ae25f03d04f8"},"schema_version":"1.0"},"canonical_sha256":"c230e541674016cce37022ad869493842d4c67cc4bd3088d1375764c6fc4419c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:38.082047Z","signature_b64":"4cEVxkcFp5Jm15P5wqthGEfXVyFgfsR1R+yjO5MaDyyi2VbFPrVw7MQsd1j+8sV+YPusqn1nctc3PFhzs0oJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c230e541674016cce37022ad869493842d4c67cc4bd3088d1375764c6fc4419c","last_reissued_at":"2026-07-05T08:09:38.081554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:38.081554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.12292","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":"2026-07-05T08:09:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yw3Ty/2XNDilk2fXpwKqCl91aGVoe/TCsSZ9/xswmV/eagxmKSwfbIYTA2M+ia7zoGY9mUGfIBJ3nvulmAYJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:32:15.682806Z"},"content_sha256":"09d3c841a8ea3fe1520c3e85af6cdf1ed11890a29e2cb4eb941a1cab35068185","schema_version":"1.0","event_id":"sha256:09d3c841a8ea3fe1520c3e85af6cdf1ed11890a29e2cb4eb941a1cab35068185"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YIYOKQLHIALMZY3QEKWYNFETQQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reducing Bias in Pre-trained Models by Tuning while Penalizing Change","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gideon Stein, Joachim Denzler, Niklas Penzel","submitted_at":"2024-04-18T16:12:38Z","abstract_excerpt":"Deep models trained on large amounts of data often incorporate implicit biases present during training time. If later such a bias is discovered during inference or deployment, it is often necessary to acquire new data and retrain the model. This behavior is especially problematic in critical areas such as autonomous driving or medical decision-making. In these scenarios, new data is often expensive and hard to come by. In this work, we present a method based on change penalization that takes a pre-trained model and adapts the weights to mitigate a previously detected bias. We achieve this by t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12292","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/2404.12292/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":"2026-07-05T08:09:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rt+XNED+PYf7Wkpd6MUwGAcCFsOsnYIFUkDVhsZB3IlMUDj1CxsqAugIzXaEaCThsONZ+bqAty34qW/oZjimBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:32:15.683181Z"},"content_sha256":"36509500702a6dc672099d62bae3d00c567713103f4d6d8d6bbf05e35f1f0922","schema_version":"1.0","event_id":"sha256:36509500702a6dc672099d62bae3d00c567713103f4d6d8d6bbf05e35f1f0922"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YIYOKQLHIALMZY3QEKWYNFETQQ/bundle.json","state_url":"https://pith.science/pith/YIYOKQLHIALMZY3QEKWYNFETQQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YIYOKQLHIALMZY3QEKWYNFETQQ/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":"2026-07-06T19:32:15Z","links":{"resolver":"https://pith.science/pith/YIYOKQLHIALMZY3QEKWYNFETQQ","bundle":"https://pith.science/pith/YIYOKQLHIALMZY3QEKWYNFETQQ/bundle.json","state":"https://pith.science/pith/YIYOKQLHIALMZY3QEKWYNFETQQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YIYOKQLHIALMZY3QEKWYNFETQQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YIYOKQLHIALMZY3QEKWYNFETQQ","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":"0cf3ff74c5f280eb61df7837146e2aff65d9ab49cb09514310f2ae25f03d04f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T16:12:38Z","title_canon_sha256":"cf74d3cf322a1a3f681511301aeadc0ae9d8d4e4746908e0b15a53a4b5dbcff4"},"schema_version":"1.0","source":{"id":"2404.12292","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.12292","created_at":"2026-07-05T08:09:38Z"},{"alias_kind":"arxiv_version","alias_value":"2404.12292v1","created_at":"2026-07-05T08:09:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12292","created_at":"2026-07-05T08:09:38Z"},{"alias_kind":"pith_short_12","alias_value":"YIYOKQLHIALM","created_at":"2026-07-05T08:09:38Z"},{"alias_kind":"pith_short_16","alias_value":"YIYOKQLHIALMZY3Q","created_at":"2026-07-05T08:09:38Z"},{"alias_kind":"pith_short_8","alias_value":"YIYOKQLH","created_at":"2026-07-05T08:09:38Z"}],"graph_snapshots":[{"event_id":"sha256:36509500702a6dc672099d62bae3d00c567713103f4d6d8d6bbf05e35f1f0922","target":"graph","created_at":"2026-07-05T08:09:38Z","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/2404.12292/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep models trained on large amounts of data often incorporate implicit biases present during training time. If later such a bias is discovered during inference or deployment, it is often necessary to acquire new data and retrain the model. This behavior is especially problematic in critical areas such as autonomous driving or medical decision-making. In these scenarios, new data is often expensive and hard to come by. In this work, we present a method based on change penalization that takes a pre-trained model and adapts the weights to mitigate a previously detected bias. We achieve this by t","authors_text":"Gideon Stein, Joachim Denzler, Niklas Penzel","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T16:12:38Z","title":"Reducing Bias in Pre-trained Models by Tuning while Penalizing Change"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12292","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":"sha256:09d3c841a8ea3fe1520c3e85af6cdf1ed11890a29e2cb4eb941a1cab35068185","target":"record","created_at":"2026-07-05T08:09:38Z","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":"0cf3ff74c5f280eb61df7837146e2aff65d9ab49cb09514310f2ae25f03d04f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T16:12:38Z","title_canon_sha256":"cf74d3cf322a1a3f681511301aeadc0ae9d8d4e4746908e0b15a53a4b5dbcff4"},"schema_version":"1.0","source":{"id":"2404.12292","kind":"arxiv","version":1}},"canonical_sha256":"c230e541674016cce37022ad869493842d4c67cc4bd3088d1375764c6fc4419c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c230e541674016cce37022ad869493842d4c67cc4bd3088d1375764c6fc4419c","first_computed_at":"2026-07-05T08:09:38.081554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:09:38.081554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4cEVxkcFp5Jm15P5wqthGEfXVyFgfsR1R+yjO5MaDyyi2VbFPrVw7MQsd1j+8sV+YPusqn1nctc3PFhzs0oJCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:09:38.082047Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.12292","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09d3c841a8ea3fe1520c3e85af6cdf1ed11890a29e2cb4eb941a1cab35068185","sha256:36509500702a6dc672099d62bae3d00c567713103f4d6d8d6bbf05e35f1f0922"],"state_sha256":"5b61e46312455962ee287f6133c903ee2fa1a75e00b4bd5ac10fa90cac955a01"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8XebyCp3p/xQFVHF59gUC55p03QN8gMS0tc5s9hzbAe45qz8p5FWJO0mAiVpRhdqEvMcdub2x/w2pifD400PBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:32:15.685173Z","bundle_sha256":"361741b9e436b7bf4656172a9672549d7eb5d95a0a5776973da06b7bf8516494"}}