{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NI7UYCBAT5E32KLYO2MBB4YCUI","short_pith_number":"pith:NI7UYCBA","canonical_record":{"source":{"id":"2408.08310","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T17:59:30Z","cross_cats_sorted":[],"title_canon_sha256":"c1aa6008c821c97b01c257d645885ffefff453c46f4a12c7c36c34c84a510af7","abstract_canon_sha256":"b28e9e8f8c23219a9a70075433f3f55d136917f0638b93423a7cfa9ad55b7e9e"},"schema_version":"1.0"},"canonical_sha256":"6a3f4c08209f49bd2978769810f302a22cd2266e21be27bc14559029394110f3","source":{"kind":"arxiv","id":"2408.08310","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08310","created_at":"2026-07-05T08:55:46Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08310v1","created_at":"2026-07-05T08:55:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08310","created_at":"2026-07-05T08:55:46Z"},{"alias_kind":"pith_short_12","alias_value":"NI7UYCBAT5E3","created_at":"2026-07-05T08:55:46Z"},{"alias_kind":"pith_short_16","alias_value":"NI7UYCBAT5E32KLY","created_at":"2026-07-05T08:55:46Z"},{"alias_kind":"pith_short_8","alias_value":"NI7UYCBA","created_at":"2026-07-05T08:55:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NI7UYCBAT5E32KLYO2MBB4YCUI","target":"record","payload":{"canonical_record":{"source":{"id":"2408.08310","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T17:59:30Z","cross_cats_sorted":[],"title_canon_sha256":"c1aa6008c821c97b01c257d645885ffefff453c46f4a12c7c36c34c84a510af7","abstract_canon_sha256":"b28e9e8f8c23219a9a70075433f3f55d136917f0638b93423a7cfa9ad55b7e9e"},"schema_version":"1.0"},"canonical_sha256":"6a3f4c08209f49bd2978769810f302a22cd2266e21be27bc14559029394110f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:47.000146Z","signature_b64":"VGZP+GkEJc6l4StGRLFAYUmQfA7yjQ8eOvC7NoOAl+izndg/l+dktAGCOdR5h1ZE4wy2Ve48yFq+imUaetxLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a3f4c08209f49bd2978769810f302a22cd2266e21be27bc14559029394110f3","last_reissued_at":"2026-07-05T08:55:46.999735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:46.999735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.08310","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":"2026-07-05T08:55:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UC1AXNRnpCxy7kK6pvApqjabMq3ZqSdFNaMxQe5eugqed1xwg5eiEXehlvYLw14mfpcJnIZ421ouuVCnp8n+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:37:20.770907Z"},"content_sha256":"449d226acf89e65edb46e45b3ab75503f378283a0737b7b5e6b2a09ea8264000","schema_version":"1.0","event_id":"sha256:449d226acf89e65edb46e45b3ab75503f378283a0737b7b5e6b2a09ea8264000"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NI7UYCBAT5E32KLYO2MBB4YCUI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ScalingFilter: Assessing Data Quality through Inverse Utilization of Scaling Laws","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Han Hu, Houwen Peng, Miaosen Zhang, Nenghai Yu, Ruihang Li, Yixuan Wei","submitted_at":"2024-08-15T17:59:30Z","abstract_excerpt":"High-quality data is crucial for the pre-training performance of large language models. Unfortunately, existing quality filtering methods rely on a known high-quality dataset as reference, which can introduce potential bias and compromise diversity. In this paper, we propose ScalingFilter, a novel approach that evaluates text quality based on the perplexity difference between two language models trained on the same data, thereby eliminating the influence of the reference dataset in the filtering process. An theoretical analysis shows that ScalingFilter is equivalent to an inverse utilization o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08310","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/2408.08310/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":"2026-07-05T08:55:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4wwORz4QllRRy5eBGbU0pSRPOYyzz1n30r0Sg0eywetS/cFmqru8I4FyskjjIe7ZyE1sltcIyR0YW7L827hCCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:37:20.771419Z"},"content_sha256":"3f7a926f86527f997e686d0bbbfd4a97668811425e43f39fefe2d0d53b56a385","schema_version":"1.0","event_id":"sha256:3f7a926f86527f997e686d0bbbfd4a97668811425e43f39fefe2d0d53b56a385"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NI7UYCBAT5E32KLYO2MBB4YCUI/bundle.json","state_url":"https://pith.science/pith/NI7UYCBAT5E32KLYO2MBB4YCUI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NI7UYCBAT5E32KLYO2MBB4YCUI/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":"2026-08-07T16:37:20Z","links":{"resolver":"https://pith.science/pith/NI7UYCBAT5E32KLYO2MBB4YCUI","bundle":"https://pith.science/pith/NI7UYCBAT5E32KLYO2MBB4YCUI/bundle.json","state":"https://pith.science/pith/NI7UYCBAT5E32KLYO2MBB4YCUI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NI7UYCBAT5E32KLYO2MBB4YCUI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NI7UYCBAT5E32KLYO2MBB4YCUI","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":"b28e9e8f8c23219a9a70075433f3f55d136917f0638b93423a7cfa9ad55b7e9e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T17:59:30Z","title_canon_sha256":"c1aa6008c821c97b01c257d645885ffefff453c46f4a12c7c36c34c84a510af7"},"schema_version":"1.0","source":{"id":"2408.08310","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08310","created_at":"2026-07-05T08:55:46Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08310v1","created_at":"2026-07-05T08:55:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08310","created_at":"2026-07-05T08:55:46Z"},{"alias_kind":"pith_short_12","alias_value":"NI7UYCBAT5E3","created_at":"2026-07-05T08:55:46Z"},{"alias_kind":"pith_short_16","alias_value":"NI7UYCBAT5E32KLY","created_at":"2026-07-05T08:55:46Z"},{"alias_kind":"pith_short_8","alias_value":"NI7UYCBA","created_at":"2026-07-05T08:55:46Z"}],"graph_snapshots":[{"event_id":"sha256:3f7a926f86527f997e686d0bbbfd4a97668811425e43f39fefe2d0d53b56a385","target":"graph","created_at":"2026-07-05T08:55:46Z","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/2408.08310/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-quality data is crucial for the pre-training performance of large language models. Unfortunately, existing quality filtering methods rely on a known high-quality dataset as reference, which can introduce potential bias and compromise diversity. In this paper, we propose ScalingFilter, a novel approach that evaluates text quality based on the perplexity difference between two language models trained on the same data, thereby eliminating the influence of the reference dataset in the filtering process. An theoretical analysis shows that ScalingFilter is equivalent to an inverse utilization o","authors_text":"Han Hu, Houwen Peng, Miaosen Zhang, Nenghai Yu, Ruihang Li, Yixuan Wei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T17:59:30Z","title":"ScalingFilter: Assessing Data Quality through Inverse Utilization of Scaling Laws"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08310","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":"sha256:449d226acf89e65edb46e45b3ab75503f378283a0737b7b5e6b2a09ea8264000","target":"record","created_at":"2026-07-05T08:55:46Z","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":"b28e9e8f8c23219a9a70075433f3f55d136917f0638b93423a7cfa9ad55b7e9e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T17:59:30Z","title_canon_sha256":"c1aa6008c821c97b01c257d645885ffefff453c46f4a12c7c36c34c84a510af7"},"schema_version":"1.0","source":{"id":"2408.08310","kind":"arxiv","version":1}},"canonical_sha256":"6a3f4c08209f49bd2978769810f302a22cd2266e21be27bc14559029394110f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a3f4c08209f49bd2978769810f302a22cd2266e21be27bc14559029394110f3","first_computed_at":"2026-07-05T08:55:46.999735Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:46.999735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VGZP+GkEJc6l4StGRLFAYUmQfA7yjQ8eOvC7NoOAl+izndg/l+dktAGCOdR5h1ZE4wy2Ve48yFq+imUaetxLCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:47.000146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.08310","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:449d226acf89e65edb46e45b3ab75503f378283a0737b7b5e6b2a09ea8264000","sha256:3f7a926f86527f997e686d0bbbfd4a97668811425e43f39fefe2d0d53b56a385"],"state_sha256":"c7a34af13d3afbb3dc7af39c066f5f4a1829f9f6456acc2d547a74082df8ac68"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O4d7sOPQfz3YvdQfB60TMzC0KK2IwfGN6xtwULGAU5LStXGBwhTan2o9+QqScVOd2+YpMewioGvqRzgs8NGkDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:37:20.777193Z","bundle_sha256":"5a8cbb1b27cb77247d12b5ebb39fb7c0ec3df26043f87a05fdd217054e7785c8"}}