{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AE5DZZFHMCMKKBWXDFSDI7MVQF","short_pith_number":"pith:AE5DZZFH","canonical_record":{"source":{"id":"2501.03826","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-07T14:38:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b0538340f87dad7722adbf0eb223e9dcc6b35a33d2a0decaf4d72e4c75f32fb6","abstract_canon_sha256":"7237da83f6f8476a2fc03eeced930a0bb7af509eaa1721148af7994e36183d3d"},"schema_version":"1.0"},"canonical_sha256":"013a3ce4a76098a506d71964347d9581460ecf3ec6341b64591c445b541d87b6","source":{"kind":"arxiv","id":"2501.03826","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03826","created_at":"2026-07-05T09:58:00Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03826v1","created_at":"2026-07-05T09:58:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03826","created_at":"2026-07-05T09:58:00Z"},{"alias_kind":"pith_short_12","alias_value":"AE5DZZFHMCMK","created_at":"2026-07-05T09:58:00Z"},{"alias_kind":"pith_short_16","alias_value":"AE5DZZFHMCMKKBWX","created_at":"2026-07-05T09:58:00Z"},{"alias_kind":"pith_short_8","alias_value":"AE5DZZFH","created_at":"2026-07-05T09:58:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AE5DZZFHMCMKKBWXDFSDI7MVQF","target":"record","payload":{"canonical_record":{"source":{"id":"2501.03826","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-07T14:38:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b0538340f87dad7722adbf0eb223e9dcc6b35a33d2a0decaf4d72e4c75f32fb6","abstract_canon_sha256":"7237da83f6f8476a2fc03eeced930a0bb7af509eaa1721148af7994e36183d3d"},"schema_version":"1.0"},"canonical_sha256":"013a3ce4a76098a506d71964347d9581460ecf3ec6341b64591c445b541d87b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:00.140826Z","signature_b64":"nej4wOZ7sf6xYNNdTIkj20YdKft746UQXTqC7ckediOVcKt1TEsYMvbp6VhXM0RrdWMh7gCZV0fpEZvO77jEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"013a3ce4a76098a506d71964347d9581460ecf3ec6341b64591c445b541d87b6","last_reissued_at":"2026-07-05T09:58:00.140350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:00.140350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.03826","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":"2026-07-05T09:58:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lyx9u/JyVr70QUigXuOAmz+pxt8e44vEtVQVGZmg88tLEWRo/Kuzgfiycbf7WdycumjcZrudi1OvnzSbaRVdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:48:09.057150Z"},"content_sha256":"ea8ac1dee85ee1ff5b024be8a81ee74e42c8f43de4af8a3e3f51fe5422e438f3","schema_version":"1.0","event_id":"sha256:ea8ac1dee85ee1ff5b024be8a81ee74e42c8f43de4af8a3e3f51fe5422e438f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AE5DZZFHMCMKKBWXDFSDI7MVQF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating the Impact of Data Selection Strategies on Language Model Performance","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiayao Gu, Liting Chen, Yihong Li","submitted_at":"2025-01-07T14:38:49Z","abstract_excerpt":"Data selection is critical for enhancing the performance of language models, particularly when aligning training datasets with a desired target distribution. This study explores the effects of different data selection methods and feature types on model performance. We evaluate whether selecting data subsets can influence downstream tasks, whether n-gram features improve alignment with target distributions, and whether embedding-based neural features provide complementary benefits. Through comparative experiments using baseline random selection methods and distribution aligned approaches, we pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03826","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/2501.03826/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":"2026-07-05T09:58:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JBjHr4c7PwB4IUfO+ekD42uPIgFblXzTY786a83O+A47MzMWrLwCdVjurhVSMVYr/5vwMeeGe22amWgHy+xODw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:48:09.058132Z"},"content_sha256":"aac4e870a3e95cd7532f1f90564152c392d5c48f21c0e6b29c9a9dbca191025e","schema_version":"1.0","event_id":"sha256:aac4e870a3e95cd7532f1f90564152c392d5c48f21c0e6b29c9a9dbca191025e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AE5DZZFHMCMKKBWXDFSDI7MVQF/bundle.json","state_url":"https://pith.science/pith/AE5DZZFHMCMKKBWXDFSDI7MVQF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AE5DZZFHMCMKKBWXDFSDI7MVQF/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":"2026-08-11T15:48:09Z","links":{"resolver":"https://pith.science/pith/AE5DZZFHMCMKKBWXDFSDI7MVQF","bundle":"https://pith.science/pith/AE5DZZFHMCMKKBWXDFSDI7MVQF/bundle.json","state":"https://pith.science/pith/AE5DZZFHMCMKKBWXDFSDI7MVQF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AE5DZZFHMCMKKBWXDFSDI7MVQF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AE5DZZFHMCMKKBWXDFSDI7MVQF","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":"7237da83f6f8476a2fc03eeced930a0bb7af509eaa1721148af7994e36183d3d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-07T14:38:49Z","title_canon_sha256":"b0538340f87dad7722adbf0eb223e9dcc6b35a33d2a0decaf4d72e4c75f32fb6"},"schema_version":"1.0","source":{"id":"2501.03826","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03826","created_at":"2026-07-05T09:58:00Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03826v1","created_at":"2026-07-05T09:58:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03826","created_at":"2026-07-05T09:58:00Z"},{"alias_kind":"pith_short_12","alias_value":"AE5DZZFHMCMK","created_at":"2026-07-05T09:58:00Z"},{"alias_kind":"pith_short_16","alias_value":"AE5DZZFHMCMKKBWX","created_at":"2026-07-05T09:58:00Z"},{"alias_kind":"pith_short_8","alias_value":"AE5DZZFH","created_at":"2026-07-05T09:58:00Z"}],"graph_snapshots":[{"event_id":"sha256:aac4e870a3e95cd7532f1f90564152c392d5c48f21c0e6b29c9a9dbca191025e","target":"graph","created_at":"2026-07-05T09:58:00Z","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/2501.03826/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data selection is critical for enhancing the performance of language models, particularly when aligning training datasets with a desired target distribution. This study explores the effects of different data selection methods and feature types on model performance. We evaluate whether selecting data subsets can influence downstream tasks, whether n-gram features improve alignment with target distributions, and whether embedding-based neural features provide complementary benefits. Through comparative experiments using baseline random selection methods and distribution aligned approaches, we pr","authors_text":"Jiayao Gu, Liting Chen, Yihong Li","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-07T14:38:49Z","title":"Investigating the Impact of Data Selection Strategies on Language Model Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03826","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:ea8ac1dee85ee1ff5b024be8a81ee74e42c8f43de4af8a3e3f51fe5422e438f3","target":"record","created_at":"2026-07-05T09:58:00Z","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":"7237da83f6f8476a2fc03eeced930a0bb7af509eaa1721148af7994e36183d3d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-07T14:38:49Z","title_canon_sha256":"b0538340f87dad7722adbf0eb223e9dcc6b35a33d2a0decaf4d72e4c75f32fb6"},"schema_version":"1.0","source":{"id":"2501.03826","kind":"arxiv","version":1}},"canonical_sha256":"013a3ce4a76098a506d71964347d9581460ecf3ec6341b64591c445b541d87b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"013a3ce4a76098a506d71964347d9581460ecf3ec6341b64591c445b541d87b6","first_computed_at":"2026-07-05T09:58:00.140350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:00.140350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nej4wOZ7sf6xYNNdTIkj20YdKft746UQXTqC7ckediOVcKt1TEsYMvbp6VhXM0RrdWMh7gCZV0fpEZvO77jEBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:00.140826Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.03826","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea8ac1dee85ee1ff5b024be8a81ee74e42c8f43de4af8a3e3f51fe5422e438f3","sha256:aac4e870a3e95cd7532f1f90564152c392d5c48f21c0e6b29c9a9dbca191025e"],"state_sha256":"a177570784099b77a9be32191d444e6149e3e283383f33ffa53098313cae9568"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9+pYzpktdiR8kevwdUL7FBrjy13PmNzbEtPi9aLs7fwiiqbCss2cghKdOoNoFANWH7aXDnHtaErMMBkDZaYjDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T15:48:09.063560Z","bundle_sha256":"8457116c636ae99d39f64491bbaba0c1e26d2b29d5a6166e42ef239ebb9c9ff4"}}