{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:I43F4EOQA25IYADRHUXDCIJD4W","short_pith_number":"pith:I43F4EOQ","canonical_record":{"source":{"id":"2405.17293","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T15:58:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8d60fc3f9e2afe10e340e173d537dce7d952045953f6eac0f4655c7fec204dcc","abstract_canon_sha256":"d8ece56a1f0c48e7023895c6d42a725ff2ab7ee8596204381f788f4b5d45ed36"},"schema_version":"1.0"},"canonical_sha256":"47365e11d006ba8c00713d2e312123e5a469278de023962bf25a62515c4296b9","source":{"kind":"arxiv","id":"2405.17293","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17293","created_at":"2026-07-05T08:23:42Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17293v1","created_at":"2026-07-05T08:23:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17293","created_at":"2026-07-05T08:23:42Z"},{"alias_kind":"pith_short_12","alias_value":"I43F4EOQA25I","created_at":"2026-07-05T08:23:42Z"},{"alias_kind":"pith_short_16","alias_value":"I43F4EOQA25IYADR","created_at":"2026-07-05T08:23:42Z"},{"alias_kind":"pith_short_8","alias_value":"I43F4EOQ","created_at":"2026-07-05T08:23:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:I43F4EOQA25IYADRHUXDCIJD4W","target":"record","payload":{"canonical_record":{"source":{"id":"2405.17293","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T15:58:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8d60fc3f9e2afe10e340e173d537dce7d952045953f6eac0f4655c7fec204dcc","abstract_canon_sha256":"d8ece56a1f0c48e7023895c6d42a725ff2ab7ee8596204381f788f4b5d45ed36"},"schema_version":"1.0"},"canonical_sha256":"47365e11d006ba8c00713d2e312123e5a469278de023962bf25a62515c4296b9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:42.458864Z","signature_b64":"WnnQUvL6SVQ6WPZjAXOwdKJsCD8nCHJnBk3W65ux9NO7uhPFxYDLPHKmKqNC6lfJY83tdTAZ/jb1tptnFU/5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47365e11d006ba8c00713d2e312123e5a469278de023962bf25a62515c4296b9","last_reissued_at":"2026-07-05T08:23:42.458429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:42.458429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.17293","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":"2026-07-05T08:23:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pso/v00fUJHHiMRuAnoQ0jK7EB8H3OMVu4LSQQKbhCeXfLrkWBdFJolYOEaa2483ZWFOSmtSDR49aFyRyX8MAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:48:59.208627Z"},"content_sha256":"3f45004ec0ba3e38af026150630e1b5741b7859f81807e7aae3ff4f02fbab6cd","schema_version":"1.0","event_id":"sha256:3f45004ec0ba3e38af026150630e1b5741b7859f81807e7aae3ff4f02fbab6cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:I43F4EOQA25IYADRHUXDCIJD4W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Ensembles Improve Training Data Attribution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiaqi Ma, Junwei Deng, Shichang Zhang, Ting-Wei Li","submitted_at":"2024-05-27T15:58:34Z","abstract_excerpt":"Training data attribution (TDA) methods aim to quantify the influence of individual training data points on the model predictions, with broad applications in data-centric AI, such as mislabel detection, data selection, and copyright compensation. However, existing methods in this field, which can be categorized as retraining-based and gradient-based, have struggled with the trade-off between computational efficiency and attribution efficacy. Retraining-based methods can accurately attribute complex non-convex models but are computationally prohibitive, while gradient-based methods are efficien"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17293","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/2405.17293/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":"2026-07-05T08:23:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"61FfYKt+qWlIQZziX+DhEZ6RwmxfvFWRZRv/LXmXs3jVDiY8eQqNrbEm0OOXXLOfu0rmmrK2s+Tmy/qxZBGgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:48:59.209160Z"},"content_sha256":"65ed7eebca0f88bf6a61fdd1ea576e7fdf6f3961c473ce5718fb451b3451775f","schema_version":"1.0","event_id":"sha256:65ed7eebca0f88bf6a61fdd1ea576e7fdf6f3961c473ce5718fb451b3451775f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I43F4EOQA25IYADRHUXDCIJD4W/bundle.json","state_url":"https://pith.science/pith/I43F4EOQA25IYADRHUXDCIJD4W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I43F4EOQA25IYADRHUXDCIJD4W/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":"2026-08-17T13:48:59Z","links":{"resolver":"https://pith.science/pith/I43F4EOQA25IYADRHUXDCIJD4W","bundle":"https://pith.science/pith/I43F4EOQA25IYADRHUXDCIJD4W/bundle.json","state":"https://pith.science/pith/I43F4EOQA25IYADRHUXDCIJD4W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I43F4EOQA25IYADRHUXDCIJD4W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I43F4EOQA25IYADRHUXDCIJD4W","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":"d8ece56a1f0c48e7023895c6d42a725ff2ab7ee8596204381f788f4b5d45ed36","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T15:58:34Z","title_canon_sha256":"8d60fc3f9e2afe10e340e173d537dce7d952045953f6eac0f4655c7fec204dcc"},"schema_version":"1.0","source":{"id":"2405.17293","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17293","created_at":"2026-07-05T08:23:42Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17293v1","created_at":"2026-07-05T08:23:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17293","created_at":"2026-07-05T08:23:42Z"},{"alias_kind":"pith_short_12","alias_value":"I43F4EOQA25I","created_at":"2026-07-05T08:23:42Z"},{"alias_kind":"pith_short_16","alias_value":"I43F4EOQA25IYADR","created_at":"2026-07-05T08:23:42Z"},{"alias_kind":"pith_short_8","alias_value":"I43F4EOQ","created_at":"2026-07-05T08:23:42Z"}],"graph_snapshots":[{"event_id":"sha256:65ed7eebca0f88bf6a61fdd1ea576e7fdf6f3961c473ce5718fb451b3451775f","target":"graph","created_at":"2026-07-05T08:23:42Z","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/2405.17293/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training data attribution (TDA) methods aim to quantify the influence of individual training data points on the model predictions, with broad applications in data-centric AI, such as mislabel detection, data selection, and copyright compensation. However, existing methods in this field, which can be categorized as retraining-based and gradient-based, have struggled with the trade-off between computational efficiency and attribution efficacy. Retraining-based methods can accurately attribute complex non-convex models but are computationally prohibitive, while gradient-based methods are efficien","authors_text":"Jiaqi Ma, Junwei Deng, Shichang Zhang, Ting-Wei Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T15:58:34Z","title":"Efficient Ensembles Improve Training Data Attribution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17293","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":"sha256:3f45004ec0ba3e38af026150630e1b5741b7859f81807e7aae3ff4f02fbab6cd","target":"record","created_at":"2026-07-05T08:23:42Z","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":"d8ece56a1f0c48e7023895c6d42a725ff2ab7ee8596204381f788f4b5d45ed36","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T15:58:34Z","title_canon_sha256":"8d60fc3f9e2afe10e340e173d537dce7d952045953f6eac0f4655c7fec204dcc"},"schema_version":"1.0","source":{"id":"2405.17293","kind":"arxiv","version":1}},"canonical_sha256":"47365e11d006ba8c00713d2e312123e5a469278de023962bf25a62515c4296b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47365e11d006ba8c00713d2e312123e5a469278de023962bf25a62515c4296b9","first_computed_at":"2026-07-05T08:23:42.458429Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:42.458429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WnnQUvL6SVQ6WPZjAXOwdKJsCD8nCHJnBk3W65ux9NO7uhPFxYDLPHKmKqNC6lfJY83tdTAZ/jb1tptnFU/5Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:42.458864Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17293","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f45004ec0ba3e38af026150630e1b5741b7859f81807e7aae3ff4f02fbab6cd","sha256:65ed7eebca0f88bf6a61fdd1ea576e7fdf6f3961c473ce5718fb451b3451775f"],"state_sha256":"88ca85c87f07ef085fc8eb69cef244d20cb2e53c7273ef05b372713883d2aeac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rB5LfZMwW9UVyibaJbuIllvskANloFnh4y4cjj9hMyxi0v4lCLMhDsqXBCCE0eubj+ITclljxDa9JoaZYCfoDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T13:48:59.213143Z","bundle_sha256":"dc3c280fbaba9873736f395b25e8f0ed1553c9363134efb14125b47e5fc16dcc"}}