{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5Y6YZ5RFKT2NRMVM3P634FGUI6","short_pith_number":"pith:5Y6YZ5RF","canonical_record":{"source":{"id":"2405.02774","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-05T00:08:00Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a36845e821a9fcf54dff432bfd64ca59b3cafc1a37dc5ba3baad9bbfb172cb8a","abstract_canon_sha256":"2f980f494db408d996e34c2890a3f3bf1e8540a60574d9392bf84ab4bdd7cb0f"},"schema_version":"1.0"},"canonical_sha256":"ee3d8cf62554f4d8b2acdbfdbe14d447abf8d8550305b3fde58fb0d93b09efd3","source":{"kind":"arxiv","id":"2405.02774","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.02774","created_at":"2026-07-05T08:15:53Z"},{"alias_kind":"arxiv_version","alias_value":"2405.02774v1","created_at":"2026-07-05T08:15:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02774","created_at":"2026-07-05T08:15:53Z"},{"alias_kind":"pith_short_12","alias_value":"5Y6YZ5RFKT2N","created_at":"2026-07-05T08:15:53Z"},{"alias_kind":"pith_short_16","alias_value":"5Y6YZ5RFKT2NRMVM","created_at":"2026-07-05T08:15:53Z"},{"alias_kind":"pith_short_8","alias_value":"5Y6YZ5RF","created_at":"2026-07-05T08:15:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5Y6YZ5RFKT2NRMVM3P634FGUI6","target":"record","payload":{"canonical_record":{"source":{"id":"2405.02774","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-05T00:08:00Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a36845e821a9fcf54dff432bfd64ca59b3cafc1a37dc5ba3baad9bbfb172cb8a","abstract_canon_sha256":"2f980f494db408d996e34c2890a3f3bf1e8540a60574d9392bf84ab4bdd7cb0f"},"schema_version":"1.0"},"canonical_sha256":"ee3d8cf62554f4d8b2acdbfdbe14d447abf8d8550305b3fde58fb0d93b09efd3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:53.563490Z","signature_b64":"ibVAXfqdBXPUW7PnwfIoPmqOQhVnfKiMm73o/bwGWqrGjqisFifl3cNUwSHN0jCtJEJX5DTKvSuP8ZPpPc98AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee3d8cf62554f4d8b2acdbfdbe14d447abf8d8550305b3fde58fb0d93b09efd3","last_reissued_at":"2026-07-05T08:15:53.563033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:53.563033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.02774","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":"2026-07-05T08:15:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vvgWWr2XvE3ayocN2I+JExkP9FR/b4D8WTkzn4ZjR05j9wzz8InN6RUyKwkyliOPP0lyEWVi53wIvWy9LUvBCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:04:27.360571Z"},"content_sha256":"70bafb4c14957890e637357ab6c4f70e64f146dc20870fffff0c11c19ddc2870","schema_version":"1.0","event_id":"sha256:70bafb4c14957890e637357ab6c4f70e64f146dc20870fffff0c11c19ddc2870"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5Y6YZ5RFKT2NRMVM3P634FGUI6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Anit Kumar Sahu, Feiyang Kang, Himanshu Jahagirdar, Hoang Anh Just, Rongxing Du, Ruoxi Jia, Yifan Sun, Yuanzhi Zhang","submitted_at":"2024-05-05T00:08:00Z","abstract_excerpt":"This work focuses on leveraging and selecting from vast, unlabeled, open data to pre-fine-tune a pre-trained language model. The goal is to minimize the need for costly domain-specific data for subsequent fine-tuning while achieving desired performance levels. While many data selection algorithms have been designed for small-scale applications, rendering them unsuitable for our context, some emerging methods do cater to language data scales. However, they often prioritize data that aligns with the target distribution. While this strategy may be effective when training a model from scratch, it "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02774","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/2405.02774/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":"2026-07-05T08:15:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2B+WYv6FOCLX/kr0ypidpo+G5E4sRxKFhk75YhaWpeuZi4h3iPYDeewgXGEFzhaWrPgI5JKkNcQNmkgzI3FVCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:04:27.361090Z"},"content_sha256":"eb0a47fac36e24fc908ac1c2384e799fa10aa1096e2de5dc4ac46a62b52156db","schema_version":"1.0","event_id":"sha256:eb0a47fac36e24fc908ac1c2384e799fa10aa1096e2de5dc4ac46a62b52156db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5Y6YZ5RFKT2NRMVM3P634FGUI6/bundle.json","state_url":"https://pith.science/pith/5Y6YZ5RFKT2NRMVM3P634FGUI6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5Y6YZ5RFKT2NRMVM3P634FGUI6/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":"2026-08-06T05:04:27Z","links":{"resolver":"https://pith.science/pith/5Y6YZ5RFKT2NRMVM3P634FGUI6","bundle":"https://pith.science/pith/5Y6YZ5RFKT2NRMVM3P634FGUI6/bundle.json","state":"https://pith.science/pith/5Y6YZ5RFKT2NRMVM3P634FGUI6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5Y6YZ5RFKT2NRMVM3P634FGUI6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5Y6YZ5RFKT2NRMVM3P634FGUI6","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":"2f980f494db408d996e34c2890a3f3bf1e8540a60574d9392bf84ab4bdd7cb0f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-05T00:08:00Z","title_canon_sha256":"a36845e821a9fcf54dff432bfd64ca59b3cafc1a37dc5ba3baad9bbfb172cb8a"},"schema_version":"1.0","source":{"id":"2405.02774","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.02774","created_at":"2026-07-05T08:15:53Z"},{"alias_kind":"arxiv_version","alias_value":"2405.02774v1","created_at":"2026-07-05T08:15:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02774","created_at":"2026-07-05T08:15:53Z"},{"alias_kind":"pith_short_12","alias_value":"5Y6YZ5RFKT2N","created_at":"2026-07-05T08:15:53Z"},{"alias_kind":"pith_short_16","alias_value":"5Y6YZ5RFKT2NRMVM","created_at":"2026-07-05T08:15:53Z"},{"alias_kind":"pith_short_8","alias_value":"5Y6YZ5RF","created_at":"2026-07-05T08:15:53Z"}],"graph_snapshots":[{"event_id":"sha256:eb0a47fac36e24fc908ac1c2384e799fa10aa1096e2de5dc4ac46a62b52156db","target":"graph","created_at":"2026-07-05T08:15:53Z","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/2405.02774/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work focuses on leveraging and selecting from vast, unlabeled, open data to pre-fine-tune a pre-trained language model. The goal is to minimize the need for costly domain-specific data for subsequent fine-tuning while achieving desired performance levels. While many data selection algorithms have been designed for small-scale applications, rendering them unsuitable for our context, some emerging methods do cater to language data scales. However, they often prioritize data that aligns with the target distribution. While this strategy may be effective when training a model from scratch, it ","authors_text":"Anit Kumar Sahu, Feiyang Kang, Himanshu Jahagirdar, Hoang Anh Just, Rongxing Du, Ruoxi Jia, Yifan Sun, Yuanzhi Zhang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-05T00:08:00Z","title":"Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02774","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":"sha256:70bafb4c14957890e637357ab6c4f70e64f146dc20870fffff0c11c19ddc2870","target":"record","created_at":"2026-07-05T08:15:53Z","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":"2f980f494db408d996e34c2890a3f3bf1e8540a60574d9392bf84ab4bdd7cb0f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-05T00:08:00Z","title_canon_sha256":"a36845e821a9fcf54dff432bfd64ca59b3cafc1a37dc5ba3baad9bbfb172cb8a"},"schema_version":"1.0","source":{"id":"2405.02774","kind":"arxiv","version":1}},"canonical_sha256":"ee3d8cf62554f4d8b2acdbfdbe14d447abf8d8550305b3fde58fb0d93b09efd3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee3d8cf62554f4d8b2acdbfdbe14d447abf8d8550305b3fde58fb0d93b09efd3","first_computed_at":"2026-07-05T08:15:53.563033Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:15:53.563033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ibVAXfqdBXPUW7PnwfIoPmqOQhVnfKiMm73o/bwGWqrGjqisFifl3cNUwSHN0jCtJEJX5DTKvSuP8ZPpPc98AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:15:53.563490Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.02774","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70bafb4c14957890e637357ab6c4f70e64f146dc20870fffff0c11c19ddc2870","sha256:eb0a47fac36e24fc908ac1c2384e799fa10aa1096e2de5dc4ac46a62b52156db"],"state_sha256":"343063962f75d8eb6b2ef2b1fb9756bf5d1aad04902954d4519f51d1f62dee85"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ePuKXfG9CYozbrRb7nv/ciiBnE7Pa/WygqwVdS8bDFDEJDTY6hY4j3rypVIzlHg8hR5HGEbF2Y+/x2pbl3CnDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:04:27.366134Z","bundle_sha256":"8c3aa530a5e1de91084971ad9ba025f8f02f4c55f7bc05c65e3ea9660c9da820"}}