{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EFC4HP4ETHZJLFYQNH2BU6OAB3","short_pith_number":"pith:EFC4HP4E","canonical_record":{"source":{"id":"2501.06708","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-12T04:28:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c3dc8e6358dcd072fd095a2a4155549040bb07106d84d7076d50bb717ac8ae5d","abstract_canon_sha256":"379e16c78b222951dca97d86d6bbd24d7e681219a9af7f96ed8f6ab85525dc24"},"schema_version":"1.0"},"canonical_sha256":"2145c3bf8499f295971069f41a79c00eee8b0c135c36f9602985dfdc6ec39413","source":{"kind":"arxiv","id":"2501.06708","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06708","created_at":"2026-05-27T01:04:47Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06708v5","created_at":"2026-05-27T01:04:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06708","created_at":"2026-05-27T01:04:47Z"},{"alias_kind":"pith_short_12","alias_value":"EFC4HP4ETHZJ","created_at":"2026-05-27T01:04:47Z"},{"alias_kind":"pith_short_16","alias_value":"EFC4HP4ETHZJLFYQ","created_at":"2026-05-27T01:04:47Z"},{"alias_kind":"pith_short_8","alias_value":"EFC4HP4E","created_at":"2026-05-27T01:04:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EFC4HP4ETHZJLFYQNH2BU6OAB3","target":"record","payload":{"canonical_record":{"source":{"id":"2501.06708","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-12T04:28:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c3dc8e6358dcd072fd095a2a4155549040bb07106d84d7076d50bb717ac8ae5d","abstract_canon_sha256":"379e16c78b222951dca97d86d6bbd24d7e681219a9af7f96ed8f6ab85525dc24"},"schema_version":"1.0"},"canonical_sha256":"2145c3bf8499f295971069f41a79c00eee8b0c135c36f9602985dfdc6ec39413","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:04:47.730037Z","signature_b64":"FUj0LPAV1ZurPFSba+5wq3CuIeByLzeFMrp2Lj4SI+fqsHiz6OVNVU2yRTjofp3S+ApMGyURbDQMJCaCdV5QAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2145c3bf8499f295971069f41a79c00eee8b0c135c36f9602985dfdc6ec39413","last_reissued_at":"2026-05-27T01:04:47.729166Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:04:47.729166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.06708","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":"2026-05-27T01:04:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vhhYC+XcmE+iuqRcls2g2XLr3ANGUPjqHYmLgowye/ZdtNnvtwxvCWJdm1qB8pr5SxvuYqSOLXj8tthRJSUBDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T15:46:15.579068Z"},"content_sha256":"d07eccf4445d853f6641f9c26dd6e8c6158ca7010614849406d9d92c71892518","schema_version":"1.0","event_id":"sha256:d07eccf4445d853f6641f9c26dd6e8c6158ca7010614849406d9d92c71892518"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EFC4HP4ETHZJLFYQNH2BU6OAB3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Sample Utility for Efficient Data Selection by Mimicking Model Weights","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Frederic Sala, Javier Movellan, John Cooper, Manjot Bilkhu, Tzu-Heng Huang","submitted_at":"2025-01-12T04:28:14Z","abstract_excerpt":"Large-scale web-crawled datasets contain noise, bias, and irrelevant information, necessitating data selection techniques. Existing methods depend on hand-crafted heuristics, downstream datasets, or require expensive influence-based computations -- all of which limit scalability and introduce unwanted data dependencies. To address this, we introduce the Mimic Score, a simple and geometry-based data-quality metric that evaluates utility by measuring alignment between a sample's gradients and a target direction induced by a pre-trained reference model. This leverages readily available model weig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06708","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/2501.06708/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":"2026-05-27T01:04:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gtAn8pDmmtPWj2ryvMrjEYzum9ZwlvAcBXrh56zHRpMY8E8/5T1h2y/b4o59aTlj8uVznydaOE8y9FrCxTUiCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T15:46:15.579463Z"},"content_sha256":"257150095a8448b9f555c53f4aaffcb4e9cd06977f0894b6c330f0bf1d2108c4","schema_version":"1.0","event_id":"sha256:257150095a8448b9f555c53f4aaffcb4e9cd06977f0894b6c330f0bf1d2108c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EFC4HP4ETHZJLFYQNH2BU6OAB3/bundle.json","state_url":"https://pith.science/pith/EFC4HP4ETHZJLFYQNH2BU6OAB3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EFC4HP4ETHZJLFYQNH2BU6OAB3/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":"2026-06-02T15:46:15Z","links":{"resolver":"https://pith.science/pith/EFC4HP4ETHZJLFYQNH2BU6OAB3","bundle":"https://pith.science/pith/EFC4HP4ETHZJLFYQNH2BU6OAB3/bundle.json","state":"https://pith.science/pith/EFC4HP4ETHZJLFYQNH2BU6OAB3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EFC4HP4ETHZJLFYQNH2BU6OAB3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EFC4HP4ETHZJLFYQNH2BU6OAB3","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":"379e16c78b222951dca97d86d6bbd24d7e681219a9af7f96ed8f6ab85525dc24","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-12T04:28:14Z","title_canon_sha256":"c3dc8e6358dcd072fd095a2a4155549040bb07106d84d7076d50bb717ac8ae5d"},"schema_version":"1.0","source":{"id":"2501.06708","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06708","created_at":"2026-05-27T01:04:47Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06708v5","created_at":"2026-05-27T01:04:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06708","created_at":"2026-05-27T01:04:47Z"},{"alias_kind":"pith_short_12","alias_value":"EFC4HP4ETHZJ","created_at":"2026-05-27T01:04:47Z"},{"alias_kind":"pith_short_16","alias_value":"EFC4HP4ETHZJLFYQ","created_at":"2026-05-27T01:04:47Z"},{"alias_kind":"pith_short_8","alias_value":"EFC4HP4E","created_at":"2026-05-27T01:04:47Z"}],"graph_snapshots":[{"event_id":"sha256:257150095a8448b9f555c53f4aaffcb4e9cd06977f0894b6c330f0bf1d2108c4","target":"graph","created_at":"2026-05-27T01:04:47Z","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/2501.06708/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale web-crawled datasets contain noise, bias, and irrelevant information, necessitating data selection techniques. Existing methods depend on hand-crafted heuristics, downstream datasets, or require expensive influence-based computations -- all of which limit scalability and introduce unwanted data dependencies. To address this, we introduce the Mimic Score, a simple and geometry-based data-quality metric that evaluates utility by measuring alignment between a sample's gradients and a target direction induced by a pre-trained reference model. This leverages readily available model weig","authors_text":"Frederic Sala, Javier Movellan, John Cooper, Manjot Bilkhu, Tzu-Heng Huang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-12T04:28:14Z","title":"Evaluating Sample Utility for Efficient Data Selection by Mimicking Model Weights"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06708","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:d07eccf4445d853f6641f9c26dd6e8c6158ca7010614849406d9d92c71892518","target":"record","created_at":"2026-05-27T01:04:47Z","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":"379e16c78b222951dca97d86d6bbd24d7e681219a9af7f96ed8f6ab85525dc24","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-12T04:28:14Z","title_canon_sha256":"c3dc8e6358dcd072fd095a2a4155549040bb07106d84d7076d50bb717ac8ae5d"},"schema_version":"1.0","source":{"id":"2501.06708","kind":"arxiv","version":5}},"canonical_sha256":"2145c3bf8499f295971069f41a79c00eee8b0c135c36f9602985dfdc6ec39413","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2145c3bf8499f295971069f41a79c00eee8b0c135c36f9602985dfdc6ec39413","first_computed_at":"2026-05-27T01:04:47.729166Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:04:47.729166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FUj0LPAV1ZurPFSba+5wq3CuIeByLzeFMrp2Lj4SI+fqsHiz6OVNVU2yRTjofp3S+ApMGyURbDQMJCaCdV5QAQ==","signature_status":"signed_v1","signed_at":"2026-05-27T01:04:47.730037Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.06708","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d07eccf4445d853f6641f9c26dd6e8c6158ca7010614849406d9d92c71892518","sha256:257150095a8448b9f555c53f4aaffcb4e9cd06977f0894b6c330f0bf1d2108c4"],"state_sha256":"81aad56876b2b6e8887ab6746c0835f3fc4abfdb68f448e234f2871b4636ed4a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pEz2uzwPQ3nWXYVUjtvZ/lXhF0IM5OY2uY/TXu2RHzIVLnJhJPjGGRxatP7zNMDtQY6qc/p21be34XRgWBPpAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T15:46:15.581623Z","bundle_sha256":"50e72a4bc2b0b030117c32c2becfa428fac39e5d05f63b358722106f6a0100bb"}}