{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PMFOP6XH6GYGJNX5EUDPSO4EP5","short_pith_number":"pith:PMFOP6XH","canonical_record":{"source":{"id":"2302.06960","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-02-14T10:38:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0e35c71e130edb5a1cb242764c04fd353d470257430a2ffeb68699b327acbbbe","abstract_canon_sha256":"3d50de7852d7610fb7cd457273a17203ae1c294e57196d8cf9612781ba28a915"},"schema_version":"1.0"},"canonical_sha256":"7b0ae7fae7f1b064b6fd2506f93b847f4e1113680fcdce9a4c1162144e74912b","source":{"kind":"arxiv","id":"2302.06960","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.06960","created_at":"2026-07-05T07:08:54Z"},{"alias_kind":"arxiv_version","alias_value":"2302.06960v3","created_at":"2026-07-05T07:08:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06960","created_at":"2026-07-05T07:08:54Z"},{"alias_kind":"pith_short_12","alias_value":"PMFOP6XH6GYG","created_at":"2026-07-05T07:08:54Z"},{"alias_kind":"pith_short_16","alias_value":"PMFOP6XH6GYGJNX5","created_at":"2026-07-05T07:08:54Z"},{"alias_kind":"pith_short_8","alias_value":"PMFOP6XH","created_at":"2026-07-05T07:08:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PMFOP6XH6GYGJNX5EUDPSO4EP5","target":"record","payload":{"canonical_record":{"source":{"id":"2302.06960","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-02-14T10:38:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0e35c71e130edb5a1cb242764c04fd353d470257430a2ffeb68699b327acbbbe","abstract_canon_sha256":"3d50de7852d7610fb7cd457273a17203ae1c294e57196d8cf9612781ba28a915"},"schema_version":"1.0"},"canonical_sha256":"7b0ae7fae7f1b064b6fd2506f93b847f4e1113680fcdce9a4c1162144e74912b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:54.908582Z","signature_b64":"fGf0P9TGv271yT7+YmmvGYO7d8z6UyBXBOgwcad9nk6wiC9hUgMXQyW6VhCa4x+raLVPZyKx/fwaYCKHhvaHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b0ae7fae7f1b064b6fd2506f93b847f4e1113680fcdce9a4c1162144e74912b","last_reissued_at":"2026-07-05T07:08:54.908077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:54.908077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.06960","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:08:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"inmJzBDFkfDMUsXrg7x5XM9AEvdS+sPqRnuNNXBaloaQamK2sqkhnmRZIsCH3yZ0yh1PZICg1SvqO2ZphttGAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T09:35:05.940360Z"},"content_sha256":"97591dd117c107cf0bbfd630586596d9da5370434f390ac824be4185bd0c45f3","schema_version":"1.0","event_id":"sha256:97591dd117c107cf0bbfd630586596d9da5370434f390ac824be4185bd0c45f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PMFOP6XH6GYGJNX5EUDPSO4EP5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data pruning and neural scaling laws: fundamental limitations of score-based algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Fadhel Ayed, Soufiane Hayou","submitted_at":"2023-02-14T10:38:40Z","abstract_excerpt":"Data pruning algorithms are commonly used to reduce the memory and computational cost of the optimization process. Recent empirical results reveal that random data pruning remains a strong baseline and outperforms most existing data pruning methods in the high compression regime, i.e., where a fraction of $30\\%$ or less of the data is kept. This regime has recently attracted a lot of interest as a result of the role of data pruning in improving the so-called neural scaling laws; in [Sorscher et al.], the authors showed the need for high-quality data pruning algorithms in order to beat the samp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06960","kind":"arxiv","version":3},"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/2302.06960/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":"2026-07-05T07:08:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XVlX99b0Gn0gcwAfq+vEiYowNUcqLdcwxfYiwuShlF94wen2JFQ81zy6CF1rKOefab3CiGCIbTdR0A7lOpwbDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T09:35:05.940865Z"},"content_sha256":"970fa57e655eb193a6f76ef5e6f19f97c908a8e1f6b8907acd58055ece043542","schema_version":"1.0","event_id":"sha256:970fa57e655eb193a6f76ef5e6f19f97c908a8e1f6b8907acd58055ece043542"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PMFOP6XH6GYGJNX5EUDPSO4EP5/bundle.json","state_url":"https://pith.science/pith/PMFOP6XH6GYGJNX5EUDPSO4EP5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PMFOP6XH6GYGJNX5EUDPSO4EP5/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":"2026-08-15T09:35:05Z","links":{"resolver":"https://pith.science/pith/PMFOP6XH6GYGJNX5EUDPSO4EP5","bundle":"https://pith.science/pith/PMFOP6XH6GYGJNX5EUDPSO4EP5/bundle.json","state":"https://pith.science/pith/PMFOP6XH6GYGJNX5EUDPSO4EP5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PMFOP6XH6GYGJNX5EUDPSO4EP5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PMFOP6XH6GYGJNX5EUDPSO4EP5","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":"3d50de7852d7610fb7cd457273a17203ae1c294e57196d8cf9612781ba28a915","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-02-14T10:38:40Z","title_canon_sha256":"0e35c71e130edb5a1cb242764c04fd353d470257430a2ffeb68699b327acbbbe"},"schema_version":"1.0","source":{"id":"2302.06960","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.06960","created_at":"2026-07-05T07:08:54Z"},{"alias_kind":"arxiv_version","alias_value":"2302.06960v3","created_at":"2026-07-05T07:08:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06960","created_at":"2026-07-05T07:08:54Z"},{"alias_kind":"pith_short_12","alias_value":"PMFOP6XH6GYG","created_at":"2026-07-05T07:08:54Z"},{"alias_kind":"pith_short_16","alias_value":"PMFOP6XH6GYGJNX5","created_at":"2026-07-05T07:08:54Z"},{"alias_kind":"pith_short_8","alias_value":"PMFOP6XH","created_at":"2026-07-05T07:08:54Z"}],"graph_snapshots":[{"event_id":"sha256:970fa57e655eb193a6f76ef5e6f19f97c908a8e1f6b8907acd58055ece043542","target":"graph","created_at":"2026-07-05T07:08:54Z","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/2302.06960/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data pruning algorithms are commonly used to reduce the memory and computational cost of the optimization process. Recent empirical results reveal that random data pruning remains a strong baseline and outperforms most existing data pruning methods in the high compression regime, i.e., where a fraction of $30\\%$ or less of the data is kept. This regime has recently attracted a lot of interest as a result of the role of data pruning in improving the so-called neural scaling laws; in [Sorscher et al.], the authors showed the need for high-quality data pruning algorithms in order to beat the samp","authors_text":"Fadhel Ayed, Soufiane Hayou","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-02-14T10:38:40Z","title":"Data pruning and neural scaling laws: fundamental limitations of score-based algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06960","kind":"arxiv","version":3},"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":"sha256:97591dd117c107cf0bbfd630586596d9da5370434f390ac824be4185bd0c45f3","target":"record","created_at":"2026-07-05T07:08:54Z","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":"3d50de7852d7610fb7cd457273a17203ae1c294e57196d8cf9612781ba28a915","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-02-14T10:38:40Z","title_canon_sha256":"0e35c71e130edb5a1cb242764c04fd353d470257430a2ffeb68699b327acbbbe"},"schema_version":"1.0","source":{"id":"2302.06960","kind":"arxiv","version":3}},"canonical_sha256":"7b0ae7fae7f1b064b6fd2506f93b847f4e1113680fcdce9a4c1162144e74912b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b0ae7fae7f1b064b6fd2506f93b847f4e1113680fcdce9a4c1162144e74912b","first_computed_at":"2026-07-05T07:08:54.908077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:54.908077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fGf0P9TGv271yT7+YmmvGYO7d8z6UyBXBOgwcad9nk6wiC9hUgMXQyW6VhCa4x+raLVPZyKx/fwaYCKHhvaHAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:54.908582Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.06960","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97591dd117c107cf0bbfd630586596d9da5370434f390ac824be4185bd0c45f3","sha256:970fa57e655eb193a6f76ef5e6f19f97c908a8e1f6b8907acd58055ece043542"],"state_sha256":"0d53972d782b7a0b2b62cce2250a8e9688ec2acded3633c5da5f140a42009a04"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d7xEfynZdCg5RyLS7oHtXuKtzw7eMPWxjS619ddfx5HZgX3wAJ+Y0+X9RinfDnmOEA2//cyesBpufvyy60owCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T09:35:05.945970Z","bundle_sha256":"1e4a1b3bc46ad56a52181ffa6d9f631c1d9b355d1c6943b8d289675807f8e6ca"}}