{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2T62Q75OVDFGBXBLPJKV5BHGUP","short_pith_number":"pith:2T62Q75O","canonical_record":{"source":{"id":"2510.26714","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-30T17:13:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"642cb1a8a662815c6e5dde7cb2dc6ee321c154036608c9df0e75e85fe90fde4e","abstract_canon_sha256":"f581e47274f3bf3aedd6a1bc1d6ac68ad880c9e0cbc94045a9a900a5dd3f5a7b"},"schema_version":"1.0"},"canonical_sha256":"d4fda87faea8ca60dc2b7a555e84e6a3d71dfb1c48c73de091cf3d6118b7f284","source":{"kind":"arxiv","id":"2510.26714","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.26714","created_at":"2026-06-08T01:03:50Z"},{"alias_kind":"arxiv_version","alias_value":"2510.26714v5","created_at":"2026-06-08T01:03:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.26714","created_at":"2026-06-08T01:03:50Z"},{"alias_kind":"pith_short_12","alias_value":"2T62Q75OVDFG","created_at":"2026-06-08T01:03:50Z"},{"alias_kind":"pith_short_16","alias_value":"2T62Q75OVDFGBXBL","created_at":"2026-06-08T01:03:50Z"},{"alias_kind":"pith_short_8","alias_value":"2T62Q75O","created_at":"2026-06-08T01:03:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2T62Q75OVDFGBXBLPJKV5BHGUP","target":"record","payload":{"canonical_record":{"source":{"id":"2510.26714","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-30T17:13:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"642cb1a8a662815c6e5dde7cb2dc6ee321c154036608c9df0e75e85fe90fde4e","abstract_canon_sha256":"f581e47274f3bf3aedd6a1bc1d6ac68ad880c9e0cbc94045a9a900a5dd3f5a7b"},"schema_version":"1.0"},"canonical_sha256":"d4fda87faea8ca60dc2b7a555e84e6a3d71dfb1c48c73de091cf3d6118b7f284","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:03:50.514366Z","signature_b64":"YwoRGmUXFcqODA0v+ZuCReXGA2abOcfg5cZLCi0HwGwyNv2Lcrr5IOjXuQZkLNrkr139Cv5YcCKwcoFNm4kTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4fda87faea8ca60dc2b7a555e84e6a3d71dfb1c48c73de091cf3d6118b7f284","last_reissued_at":"2026-06-08T01:03:50.513265Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:03:50.513265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.26714","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-08T01:03:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FjY5XmyTxTYmYLPjm5inof1+TmTN5/ZXNPIYHa8SKUMw6p7FefOIzumg+fmH72BuF2IhY3EcfzR/jp3Au0XlDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T09:40:22.645905Z"},"content_sha256":"d9b75e27416de0eb8ccb8a6f8150cf43ee4f379283df75a4e61549db4a980d7e","schema_version":"1.0","event_id":"sha256:d9b75e27416de0eb8ccb8a6f8150cf43ee4f379283df75a4e61549db4a980d7e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2T62Q75OVDFGBXBLPJKV5BHGUP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the importance of multiple training seeds for evaluating machine unlearning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Axel Finke, Georgina Cosma, Jamie Lanyon, Petros Andreou","submitted_at":"2025-10-30T17:13:42Z","abstract_excerpt":"Machine unlearning aims to remove the influence of certain data points from a trained model without costly retraining. Most practical unlearning algorithms are only approximate and their performance can only be assessed empirically. Common practice is to run unlearning algorithms multiple times independently (i.e., using multiple unlearning seeds) starting from the same trained model (i.e., using only a single training seed ). In image-classification experiments, this practice can give non-representative results as unlearning performance can be sensitive to the choice of training seed. This is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.26714","kind":"arxiv","version":5},"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/2510.26714/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":"2026-06-08T01:03:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OUqyetOlY8FvhcG8+BSS8zfFjgLtX/rkLh0CUTF9zth6EnwVZMcuEmA6dyVNdAexat+sW0o2PHnmp76ybwOVBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T09:40:22.646289Z"},"content_sha256":"8a00db187ffa1767ee3168a472513b4c960f941775d58a2e18d1314b82dc058c","schema_version":"1.0","event_id":"sha256:8a00db187ffa1767ee3168a472513b4c960f941775d58a2e18d1314b82dc058c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2T62Q75OVDFGBXBLPJKV5BHGUP/bundle.json","state_url":"https://pith.science/pith/2T62Q75OVDFGBXBLPJKV5BHGUP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2T62Q75OVDFGBXBLPJKV5BHGUP/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":"2026-06-26T09:40:22Z","links":{"resolver":"https://pith.science/pith/2T62Q75OVDFGBXBLPJKV5BHGUP","bundle":"https://pith.science/pith/2T62Q75OVDFGBXBLPJKV5BHGUP/bundle.json","state":"https://pith.science/pith/2T62Q75OVDFGBXBLPJKV5BHGUP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2T62Q75OVDFGBXBLPJKV5BHGUP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2T62Q75OVDFGBXBLPJKV5BHGUP","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":"f581e47274f3bf3aedd6a1bc1d6ac68ad880c9e0cbc94045a9a900a5dd3f5a7b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-30T17:13:42Z","title_canon_sha256":"642cb1a8a662815c6e5dde7cb2dc6ee321c154036608c9df0e75e85fe90fde4e"},"schema_version":"1.0","source":{"id":"2510.26714","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.26714","created_at":"2026-06-08T01:03:50Z"},{"alias_kind":"arxiv_version","alias_value":"2510.26714v5","created_at":"2026-06-08T01:03:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.26714","created_at":"2026-06-08T01:03:50Z"},{"alias_kind":"pith_short_12","alias_value":"2T62Q75OVDFG","created_at":"2026-06-08T01:03:50Z"},{"alias_kind":"pith_short_16","alias_value":"2T62Q75OVDFGBXBL","created_at":"2026-06-08T01:03:50Z"},{"alias_kind":"pith_short_8","alias_value":"2T62Q75O","created_at":"2026-06-08T01:03:50Z"}],"graph_snapshots":[{"event_id":"sha256:8a00db187ffa1767ee3168a472513b4c960f941775d58a2e18d1314b82dc058c","target":"graph","created_at":"2026-06-08T01:03:50Z","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/2510.26714/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine unlearning aims to remove the influence of certain data points from a trained model without costly retraining. Most practical unlearning algorithms are only approximate and their performance can only be assessed empirically. Common practice is to run unlearning algorithms multiple times independently (i.e., using multiple unlearning seeds) starting from the same trained model (i.e., using only a single training seed ). In image-classification experiments, this practice can give non-representative results as unlearning performance can be sensitive to the choice of training seed. This is","authors_text":"Axel Finke, Georgina Cosma, Jamie Lanyon, Petros Andreou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-30T17:13:42Z","title":"On the importance of multiple training seeds for evaluating machine unlearning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.26714","kind":"arxiv","version":5},"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:d9b75e27416de0eb8ccb8a6f8150cf43ee4f379283df75a4e61549db4a980d7e","target":"record","created_at":"2026-06-08T01:03:50Z","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":"f581e47274f3bf3aedd6a1bc1d6ac68ad880c9e0cbc94045a9a900a5dd3f5a7b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-30T17:13:42Z","title_canon_sha256":"642cb1a8a662815c6e5dde7cb2dc6ee321c154036608c9df0e75e85fe90fde4e"},"schema_version":"1.0","source":{"id":"2510.26714","kind":"arxiv","version":5}},"canonical_sha256":"d4fda87faea8ca60dc2b7a555e84e6a3d71dfb1c48c73de091cf3d6118b7f284","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4fda87faea8ca60dc2b7a555e84e6a3d71dfb1c48c73de091cf3d6118b7f284","first_computed_at":"2026-06-08T01:03:50.513265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:03:50.513265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YwoRGmUXFcqODA0v+ZuCReXGA2abOcfg5cZLCi0HwGwyNv2Lcrr5IOjXuQZkLNrkr139Cv5YcCKwcoFNm4kTDA==","signature_status":"signed_v1","signed_at":"2026-06-08T01:03:50.514366Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.26714","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9b75e27416de0eb8ccb8a6f8150cf43ee4f379283df75a4e61549db4a980d7e","sha256:8a00db187ffa1767ee3168a472513b4c960f941775d58a2e18d1314b82dc058c"],"state_sha256":"915c76fc2dd8a220ac3938dac094259747f6c8136fdbd92b48934ee1586d3146"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p72a/+icBGmoT0tyFF1RInwYVIAo8YRJsWJ5Iw76XXZOiHUhaTLREqSxgi6cY0tNaFker8PJVN0ufG4vYc76Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T09:40:22.648406Z","bundle_sha256":"26fa3572fa0ef502cea2c2666a02995b32f950b139d4eaf73494430522a4586a"}}