{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:M3RBKC6BFFXMLWYCW4QUVBQMUU","short_pith_number":"pith:M3RBKC6B","canonical_record":{"source":{"id":"2506.11615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-13T09:37:11Z","cross_cats_sorted":[],"title_canon_sha256":"2005723f0da987ec87a04d0a481e1cdaa38ee3e5b16c1c0c15c4cc8c2205ba3c","abstract_canon_sha256":"a2b500668d4b4dd7f04bcbbfa0bce66d58591716e9db05da526f71ed64097f12"},"schema_version":"1.0"},"canonical_sha256":"66e2150bc1296ec5db02b7214a860ca50a8b8707912bca3c8e72841375881b6e","source":{"kind":"arxiv","id":"2506.11615","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11615","created_at":"2026-07-05T11:21:07Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11615v1","created_at":"2026-07-05T11:21:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11615","created_at":"2026-07-05T11:21:07Z"},{"alias_kind":"pith_short_12","alias_value":"M3RBKC6BFFXM","created_at":"2026-07-05T11:21:07Z"},{"alias_kind":"pith_short_16","alias_value":"M3RBKC6BFFXMLWYC","created_at":"2026-07-05T11:21:07Z"},{"alias_kind":"pith_short_8","alias_value":"M3RBKC6B","created_at":"2026-07-05T11:21:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:M3RBKC6BFFXMLWYCW4QUVBQMUU","target":"record","payload":{"canonical_record":{"source":{"id":"2506.11615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-13T09:37:11Z","cross_cats_sorted":[],"title_canon_sha256":"2005723f0da987ec87a04d0a481e1cdaa38ee3e5b16c1c0c15c4cc8c2205ba3c","abstract_canon_sha256":"a2b500668d4b4dd7f04bcbbfa0bce66d58591716e9db05da526f71ed64097f12"},"schema_version":"1.0"},"canonical_sha256":"66e2150bc1296ec5db02b7214a860ca50a8b8707912bca3c8e72841375881b6e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:07.719199Z","signature_b64":"VcANuMCnc6z3FSQ2cfedQZcwBvjhlPnK9yneqhhnp1RZYc8BRmsdJJ0RHBvWUiMrFSRfIZ6FHdiqCjxNsOenBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66e2150bc1296ec5db02b7214a860ca50a8b8707912bca3c8e72841375881b6e","last_reissued_at":"2026-07-05T11:21:07.718794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:07.718794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.11615","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":"2026-07-05T11:21:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7gW13uhTGsiYd1Q+fN3JXFN9fCw06o3EkbPgZwGQEwxukXAlqRvC7H/08sFGqmc8i4vbYZhuN1Ngu06AXKAwDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:20:03.425463Z"},"content_sha256":"57c7c5951bbbbbf149f6be2cde3fd46f53315e0e3ca39b1e25bf00605c285d47","schema_version":"1.0","event_id":"sha256:57c7c5951bbbbbf149f6be2cde3fd46f53315e0e3ca39b1e25bf00605c285d47"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:M3RBKC6BFFXMLWYCW4QUVBQMUU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Machine Unlearning for Robust DNNs: Attribution-Guided Partitioning and Neuron Pruning in Noisy Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Deliang Jin, Gang Chen, Haoran Zhu, Shuo Feng, Yufeng Ling","submitted_at":"2025-06-13T09:37:11Z","abstract_excerpt":"Deep neural networks (DNNs) have achieved remarkable success across diverse domains, but their performance can be severely degraded by noisy or corrupted training data. Conventional noise mitigation methods often rely on explicit assumptions about noise distributions or require extensive retraining, which can be impractical for large-scale models. Inspired by the principles of machine unlearning, we propose a novel framework that integrates attribution-guided data partitioning, discriminative neuron pruning, and targeted fine-tuning to mitigate the impact of noisy samples. Our approach employs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11615","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/2506.11615/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":"2026-07-05T11:21:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JVdibwbqDnqiB4RoG85SsHQ0cJZFbJm+wVHC4guQyapcKq6SsEOjcCoSSPi94lAgb0wQihYOCxDwqA9SBPXADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:20:03.426377Z"},"content_sha256":"47af93d751ff6499afd58bdd16beae51886e92b6968ef25a197afaca76fa250a","schema_version":"1.0","event_id":"sha256:47af93d751ff6499afd58bdd16beae51886e92b6968ef25a197afaca76fa250a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M3RBKC6BFFXMLWYCW4QUVBQMUU/bundle.json","state_url":"https://pith.science/pith/M3RBKC6BFFXMLWYCW4QUVBQMUU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M3RBKC6BFFXMLWYCW4QUVBQMUU/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":"2026-08-10T04:20:03Z","links":{"resolver":"https://pith.science/pith/M3RBKC6BFFXMLWYCW4QUVBQMUU","bundle":"https://pith.science/pith/M3RBKC6BFFXMLWYCW4QUVBQMUU/bundle.json","state":"https://pith.science/pith/M3RBKC6BFFXMLWYCW4QUVBQMUU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M3RBKC6BFFXMLWYCW4QUVBQMUU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:M3RBKC6BFFXMLWYCW4QUVBQMUU","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":"a2b500668d4b4dd7f04bcbbfa0bce66d58591716e9db05da526f71ed64097f12","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-13T09:37:11Z","title_canon_sha256":"2005723f0da987ec87a04d0a481e1cdaa38ee3e5b16c1c0c15c4cc8c2205ba3c"},"schema_version":"1.0","source":{"id":"2506.11615","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11615","created_at":"2026-07-05T11:21:07Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11615v1","created_at":"2026-07-05T11:21:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11615","created_at":"2026-07-05T11:21:07Z"},{"alias_kind":"pith_short_12","alias_value":"M3RBKC6BFFXM","created_at":"2026-07-05T11:21:07Z"},{"alias_kind":"pith_short_16","alias_value":"M3RBKC6BFFXMLWYC","created_at":"2026-07-05T11:21:07Z"},{"alias_kind":"pith_short_8","alias_value":"M3RBKC6B","created_at":"2026-07-05T11:21:07Z"}],"graph_snapshots":[{"event_id":"sha256:47af93d751ff6499afd58bdd16beae51886e92b6968ef25a197afaca76fa250a","target":"graph","created_at":"2026-07-05T11:21:07Z","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/2506.11615/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks (DNNs) have achieved remarkable success across diverse domains, but their performance can be severely degraded by noisy or corrupted training data. Conventional noise mitigation methods often rely on explicit assumptions about noise distributions or require extensive retraining, which can be impractical for large-scale models. Inspired by the principles of machine unlearning, we propose a novel framework that integrates attribution-guided data partitioning, discriminative neuron pruning, and targeted fine-tuning to mitigate the impact of noisy samples. Our approach employs","authors_text":"Deliang Jin, Gang Chen, Haoran Zhu, Shuo Feng, Yufeng Ling","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-13T09:37:11Z","title":"Machine Unlearning for Robust DNNs: Attribution-Guided Partitioning and Neuron Pruning in Noisy Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11615","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":"sha256:57c7c5951bbbbbf149f6be2cde3fd46f53315e0e3ca39b1e25bf00605c285d47","target":"record","created_at":"2026-07-05T11:21:07Z","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":"a2b500668d4b4dd7f04bcbbfa0bce66d58591716e9db05da526f71ed64097f12","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-13T09:37:11Z","title_canon_sha256":"2005723f0da987ec87a04d0a481e1cdaa38ee3e5b16c1c0c15c4cc8c2205ba3c"},"schema_version":"1.0","source":{"id":"2506.11615","kind":"arxiv","version":1}},"canonical_sha256":"66e2150bc1296ec5db02b7214a860ca50a8b8707912bca3c8e72841375881b6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66e2150bc1296ec5db02b7214a860ca50a8b8707912bca3c8e72841375881b6e","first_computed_at":"2026-07-05T11:21:07.718794Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:07.718794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VcANuMCnc6z3FSQ2cfedQZcwBvjhlPnK9yneqhhnp1RZYc8BRmsdJJ0RHBvWUiMrFSRfIZ6FHdiqCjxNsOenBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:07.719199Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11615","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57c7c5951bbbbbf149f6be2cde3fd46f53315e0e3ca39b1e25bf00605c285d47","sha256:47af93d751ff6499afd58bdd16beae51886e92b6968ef25a197afaca76fa250a"],"state_sha256":"4a507290f1970798e3afea5a1e24540a68335da65e0eaaa9f3e4089cc98d58c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K+FmqN9kjdlCeLyPgVBBI3v+5g5IIqCyJONjvcB871hk6sniEVlyZkfLFqToOw1jfX5kHRqx2IstBB0sVBNcBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T04:20:03.432467Z","bundle_sha256":"114cc81e2fb51874350c4eba760452c058902caf4560050a9b5cccf1d325b82d"}}