{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EETDTVQQDWJROU52GZV5N6V3LM","short_pith_number":"pith:EETDTVQQ","canonical_record":{"source":{"id":"2304.13169","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T22:02:09Z","cross_cats_sorted":[],"title_canon_sha256":"6802dd6e5a3d4c6b36bad39d499f8aeb6c48b8f159d97aa062d22d476b136008","abstract_canon_sha256":"b9aa3dd06e9833168c38b46e336f345b1421efa35a8cd728026da1e7a16338a0"},"schema_version":"1.0"},"canonical_sha256":"212639d6101d931753ba366bd6fabb5b2375eec56d10e9c914f2fda2b199ded4","source":{"kind":"arxiv","id":"2304.13169","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.13169","created_at":"2026-07-05T06:43:38Z"},{"alias_kind":"arxiv_version","alias_value":"2304.13169v2","created_at":"2026-07-05T06:43:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13169","created_at":"2026-07-05T06:43:38Z"},{"alias_kind":"pith_short_12","alias_value":"EETDTVQQDWJR","created_at":"2026-07-05T06:43:38Z"},{"alias_kind":"pith_short_16","alias_value":"EETDTVQQDWJROU52","created_at":"2026-07-05T06:43:38Z"},{"alias_kind":"pith_short_8","alias_value":"EETDTVQQ","created_at":"2026-07-05T06:43:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EETDTVQQDWJROU52GZV5N6V3LM","target":"record","payload":{"canonical_record":{"source":{"id":"2304.13169","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T22:02:09Z","cross_cats_sorted":[],"title_canon_sha256":"6802dd6e5a3d4c6b36bad39d499f8aeb6c48b8f159d97aa062d22d476b136008","abstract_canon_sha256":"b9aa3dd06e9833168c38b46e336f345b1421efa35a8cd728026da1e7a16338a0"},"schema_version":"1.0"},"canonical_sha256":"212639d6101d931753ba366bd6fabb5b2375eec56d10e9c914f2fda2b199ded4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:38.294134Z","signature_b64":"DFhBoqKVrfVyI925WDc9wgKz1qoqoomIipWZTTFu8+TIobALCuTO7wb4pFecSW8ktJOQRqnBimQVhNowTo4KBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"212639d6101d931753ba366bd6fabb5b2375eec56d10e9c914f2fda2b199ded4","last_reissued_at":"2026-07-05T06:43:38.293656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:38.293656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.13169","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":"2026-07-05T06:43:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EI65ogpvG5oFQ0dXrdajiuTGQztgt/4rPavZ55Ri6gdwJa0eHsLLbIKKmqINK6Sa+IdSZ9W3lMWvBe+GREIFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:30:18.469590Z"},"content_sha256":"498c3567043d6e3be64961151733cf90628e66a318a2cad452882684a5a482a4","schema_version":"1.0","event_id":"sha256:498c3567043d6e3be64961151733cf90628e66a318a2cad452882684a5a482a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EETDTVQQDWJROU52GZV5N6V3LM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SAFE: Machine Unlearning With Shard Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditya Golatkar, Alessandro Achille, Ashwin Swaminathan, Benjamin Bowman, Stefano Soatto, Yonatan Dukler","submitted_at":"2023-04-25T22:02:09Z","abstract_excerpt":"We present Synergy Aware Forgetting Ensemble (SAFE), a method to adapt large models on a diverse collection of data while minimizing the expected cost to remove the influence of training samples from the trained model. This process, also known as selective forgetting or unlearning, is often conducted by partitioning a dataset into shards, training fully independent models on each, then ensembling the resulting models. Increasing the number of shards reduces the expected cost to forget but at the same time it increases inference cost and reduces the final accuracy of the model since synergistic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13169","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/2304.13169/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":"2026-07-05T06:43:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"noI3JLYT7LnVzWGP2LIyUdqD0MMVYPYLyXNmR4sTJV0cJ6i7H1dii7bBELWq2KNIWcg56ILyTgeQtf6zY+yBBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:30:18.470109Z"},"content_sha256":"9d0d3c0ca1766b79296394a42010de2f2bb4657c5d8917ec45c8e62d6325b0b1","schema_version":"1.0","event_id":"sha256:9d0d3c0ca1766b79296394a42010de2f2bb4657c5d8917ec45c8e62d6325b0b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EETDTVQQDWJROU52GZV5N6V3LM/bundle.json","state_url":"https://pith.science/pith/EETDTVQQDWJROU52GZV5N6V3LM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EETDTVQQDWJROU52GZV5N6V3LM/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":"2026-08-11T19:30:18Z","links":{"resolver":"https://pith.science/pith/EETDTVQQDWJROU52GZV5N6V3LM","bundle":"https://pith.science/pith/EETDTVQQDWJROU52GZV5N6V3LM/bundle.json","state":"https://pith.science/pith/EETDTVQQDWJROU52GZV5N6V3LM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EETDTVQQDWJROU52GZV5N6V3LM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EETDTVQQDWJROU52GZV5N6V3LM","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":"b9aa3dd06e9833168c38b46e336f345b1421efa35a8cd728026da1e7a16338a0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T22:02:09Z","title_canon_sha256":"6802dd6e5a3d4c6b36bad39d499f8aeb6c48b8f159d97aa062d22d476b136008"},"schema_version":"1.0","source":{"id":"2304.13169","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.13169","created_at":"2026-07-05T06:43:38Z"},{"alias_kind":"arxiv_version","alias_value":"2304.13169v2","created_at":"2026-07-05T06:43:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13169","created_at":"2026-07-05T06:43:38Z"},{"alias_kind":"pith_short_12","alias_value":"EETDTVQQDWJR","created_at":"2026-07-05T06:43:38Z"},{"alias_kind":"pith_short_16","alias_value":"EETDTVQQDWJROU52","created_at":"2026-07-05T06:43:38Z"},{"alias_kind":"pith_short_8","alias_value":"EETDTVQQ","created_at":"2026-07-05T06:43:38Z"}],"graph_snapshots":[{"event_id":"sha256:9d0d3c0ca1766b79296394a42010de2f2bb4657c5d8917ec45c8e62d6325b0b1","target":"graph","created_at":"2026-07-05T06:43:38Z","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/2304.13169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Synergy Aware Forgetting Ensemble (SAFE), a method to adapt large models on a diverse collection of data while minimizing the expected cost to remove the influence of training samples from the trained model. This process, also known as selective forgetting or unlearning, is often conducted by partitioning a dataset into shards, training fully independent models on each, then ensembling the resulting models. Increasing the number of shards reduces the expected cost to forget but at the same time it increases inference cost and reduces the final accuracy of the model since synergistic","authors_text":"Aditya Golatkar, Alessandro Achille, Ashwin Swaminathan, Benjamin Bowman, Stefano Soatto, Yonatan Dukler","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T22:02:09Z","title":"SAFE: Machine Unlearning With Shard Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13169","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":"sha256:498c3567043d6e3be64961151733cf90628e66a318a2cad452882684a5a482a4","target":"record","created_at":"2026-07-05T06:43:38Z","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":"b9aa3dd06e9833168c38b46e336f345b1421efa35a8cd728026da1e7a16338a0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T22:02:09Z","title_canon_sha256":"6802dd6e5a3d4c6b36bad39d499f8aeb6c48b8f159d97aa062d22d476b136008"},"schema_version":"1.0","source":{"id":"2304.13169","kind":"arxiv","version":2}},"canonical_sha256":"212639d6101d931753ba366bd6fabb5b2375eec56d10e9c914f2fda2b199ded4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"212639d6101d931753ba366bd6fabb5b2375eec56d10e9c914f2fda2b199ded4","first_computed_at":"2026-07-05T06:43:38.293656Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:43:38.293656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DFhBoqKVrfVyI925WDc9wgKz1qoqoomIipWZTTFu8+TIobALCuTO7wb4pFecSW8ktJOQRqnBimQVhNowTo4KBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:43:38.294134Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.13169","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:498c3567043d6e3be64961151733cf90628e66a318a2cad452882684a5a482a4","sha256:9d0d3c0ca1766b79296394a42010de2f2bb4657c5d8917ec45c8e62d6325b0b1"],"state_sha256":"522ef38694ed0ead91258ba6e6dee4ad95aea867f1ae240034e8f24012649ec7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q/1qFGEft++EpPxDp4RfzfwAzbHWiTXhIiVrfqdKNHYMK2qVNjXDxxoCruyEBae5Y3V5B8Zk2ZqDDkFALiBYCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T19:30:18.476085Z","bundle_sha256":"62d622c4759edd946a8a529793162f1d644f9adea380283476775844788bf454"}}