{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UH6EVES4MKTFFGDLSCDLIXDRGV","short_pith_number":"pith:UH6EVES4","canonical_record":{"source":{"id":"2409.17115","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-25T17:28:13Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e304c90624d8fa5e2f939e79d343deb2fcaab825daecce8050765285acb64e5b","abstract_canon_sha256":"97339413b55ec509ad90f6ff71cdb4902157f80210240287ef220e58a508195c"},"schema_version":"1.0"},"canonical_sha256":"a1fc4a925c62a652986b9086b45c71355fa05767d07ac0c970ce7e866c5328d8","source":{"kind":"arxiv","id":"2409.17115","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.17115","created_at":"2026-07-05T10:14:24Z"},{"alias_kind":"arxiv_version","alias_value":"2409.17115v2","created_at":"2026-07-05T10:14:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17115","created_at":"2026-07-05T10:14:24Z"},{"alias_kind":"pith_short_12","alias_value":"UH6EVES4MKTF","created_at":"2026-07-05T10:14:24Z"},{"alias_kind":"pith_short_16","alias_value":"UH6EVES4MKTFFGDL","created_at":"2026-07-05T10:14:24Z"},{"alias_kind":"pith_short_8","alias_value":"UH6EVES4","created_at":"2026-07-05T10:14:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UH6EVES4MKTFFGDLSCDLIXDRGV","target":"record","payload":{"canonical_record":{"source":{"id":"2409.17115","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-25T17:28:13Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e304c90624d8fa5e2f939e79d343deb2fcaab825daecce8050765285acb64e5b","abstract_canon_sha256":"97339413b55ec509ad90f6ff71cdb4902157f80210240287ef220e58a508195c"},"schema_version":"1.0"},"canonical_sha256":"a1fc4a925c62a652986b9086b45c71355fa05767d07ac0c970ce7e866c5328d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:24.185326Z","signature_b64":"ZnPdrs0buj550wVe0x8r71c5F2TxN7yGftkeWXuaReH6aq7fh+D4xN3GGzcFDKZ/7yOHSgzLcFxnOi5FNRovBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1fc4a925c62a652986b9086b45c71355fa05767d07ac0c970ce7e866c5328d8","last_reissued_at":"2026-07-05T10:14:24.184760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:24.184760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.17115","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":"2026-07-05T10:14:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"19g9hLXzGANNomK0xUL4dve1ERjqqEbHoWpA0Bxud4xWBe+ozxStQjrrdsYHhFmG32D80lqyecilkV9wPElXAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:12:47.241027Z"},"content_sha256":"61ccaf17d82c746ea0aeee493b410d24c959b6773a9c0a9917b7c3ac76167308","schema_version":"1.0","event_id":"sha256:61ccaf17d82c746ea0aeee493b410d24c959b6773a9c0a9917b7c3ac76167308"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UH6EVES4MKTFFGDLSCDLIXDRGV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fan Zhou, Junlong Li, Pengfei Liu, Qian Liu, Zengzhi Wang","submitted_at":"2024-09-25T17:28:13Z","abstract_excerpt":"Large language model pre-training has traditionally relied on human experts to craft heuristics for improving the corpora quality, resulting in numerous rules developed to date. However, these rules lack the flexibility to address the unique characteristics of individual example effectively. Meanwhile, applying tailored rules to every example is impractical for human experts. In this paper, we demonstrate that even small language models, with as few as 0.3B parameters, can exhibit substantial data refining capabilities comparable to those of human experts. We introduce Programming Every Exampl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17115","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/2409.17115/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":"2026-07-05T10:14:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8nu1khOPhwuYAV0wS1M8sm7XgBX0rtzDxU70Nzmfmw5KaQvu64s7N3EOBYobPG85Qzx+fYhA8EZxe8UORpwpBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:12:47.241559Z"},"content_sha256":"8e68f8db843f4c89e06a5b400b928cfe736adef4cee61621925e99532515ff5c","schema_version":"1.0","event_id":"sha256:8e68f8db843f4c89e06a5b400b928cfe736adef4cee61621925e99532515ff5c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UH6EVES4MKTFFGDLSCDLIXDRGV/bundle.json","state_url":"https://pith.science/pith/UH6EVES4MKTFFGDLSCDLIXDRGV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UH6EVES4MKTFFGDLSCDLIXDRGV/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":"2026-08-07T16:12:47Z","links":{"resolver":"https://pith.science/pith/UH6EVES4MKTFFGDLSCDLIXDRGV","bundle":"https://pith.science/pith/UH6EVES4MKTFFGDLSCDLIXDRGV/bundle.json","state":"https://pith.science/pith/UH6EVES4MKTFFGDLSCDLIXDRGV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UH6EVES4MKTFFGDLSCDLIXDRGV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UH6EVES4MKTFFGDLSCDLIXDRGV","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":"97339413b55ec509ad90f6ff71cdb4902157f80210240287ef220e58a508195c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-25T17:28:13Z","title_canon_sha256":"e304c90624d8fa5e2f939e79d343deb2fcaab825daecce8050765285acb64e5b"},"schema_version":"1.0","source":{"id":"2409.17115","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.17115","created_at":"2026-07-05T10:14:24Z"},{"alias_kind":"arxiv_version","alias_value":"2409.17115v2","created_at":"2026-07-05T10:14:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17115","created_at":"2026-07-05T10:14:24Z"},{"alias_kind":"pith_short_12","alias_value":"UH6EVES4MKTF","created_at":"2026-07-05T10:14:24Z"},{"alias_kind":"pith_short_16","alias_value":"UH6EVES4MKTFFGDL","created_at":"2026-07-05T10:14:24Z"},{"alias_kind":"pith_short_8","alias_value":"UH6EVES4","created_at":"2026-07-05T10:14:24Z"}],"graph_snapshots":[{"event_id":"sha256:8e68f8db843f4c89e06a5b400b928cfe736adef4cee61621925e99532515ff5c","target":"graph","created_at":"2026-07-05T10:14:24Z","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/2409.17115/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model pre-training has traditionally relied on human experts to craft heuristics for improving the corpora quality, resulting in numerous rules developed to date. However, these rules lack the flexibility to address the unique characteristics of individual example effectively. Meanwhile, applying tailored rules to every example is impractical for human experts. In this paper, we demonstrate that even small language models, with as few as 0.3B parameters, can exhibit substantial data refining capabilities comparable to those of human experts. We introduce Programming Every Exampl","authors_text":"Fan Zhou, Junlong Li, Pengfei Liu, Qian Liu, Zengzhi Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-25T17:28:13Z","title":"Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17115","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":"sha256:61ccaf17d82c746ea0aeee493b410d24c959b6773a9c0a9917b7c3ac76167308","target":"record","created_at":"2026-07-05T10:14:24Z","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":"97339413b55ec509ad90f6ff71cdb4902157f80210240287ef220e58a508195c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-25T17:28:13Z","title_canon_sha256":"e304c90624d8fa5e2f939e79d343deb2fcaab825daecce8050765285acb64e5b"},"schema_version":"1.0","source":{"id":"2409.17115","kind":"arxiv","version":2}},"canonical_sha256":"a1fc4a925c62a652986b9086b45c71355fa05767d07ac0c970ce7e866c5328d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1fc4a925c62a652986b9086b45c71355fa05767d07ac0c970ce7e866c5328d8","first_computed_at":"2026-07-05T10:14:24.184760Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:24.184760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZnPdrs0buj550wVe0x8r71c5F2TxN7yGftkeWXuaReH6aq7fh+D4xN3GGzcFDKZ/7yOHSgzLcFxnOi5FNRovBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:24.185326Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.17115","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61ccaf17d82c746ea0aeee493b410d24c959b6773a9c0a9917b7c3ac76167308","sha256:8e68f8db843f4c89e06a5b400b928cfe736adef4cee61621925e99532515ff5c"],"state_sha256":"21f285551ddacfaf9e42367af256a51ec717d13c55191539bd5dbb5df71e0c20"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V3Oni1Ixcv4++cboRa/O5cldmGiIYM06LJgbtkV6d+gMiz22sNBiziKW1UliAuGX6TvblsRnSE2a1NKRX7l4AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:12:47.245566Z","bundle_sha256":"4624879497610b6f3b2fca2042cb0a97ea0d3d20e266c7b7aec35918261a7a88"}}