{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:N7GCV265G4PZNBQEB654QR636O","short_pith_number":"pith:N7GCV265","canonical_record":{"source":{"id":"2410.16208","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-21T17:11:21Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"63602bde42e74168df4e3bc6f9399585014689c66a5f3920e60765551961ac1c","abstract_canon_sha256":"1c42ad511ec1bb418032054690619acdd4b9915f7a11795be397c4cf2d449e72"},"schema_version":"1.0"},"canonical_sha256":"6fcc2aebdd371f9686040fbbc847dbf38d9ee478c105331c0bae01fd2c7a5d3e","source":{"kind":"arxiv","id":"2410.16208","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16208","created_at":"2026-07-05T10:45:38Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16208v4","created_at":"2026-07-05T10:45:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16208","created_at":"2026-07-05T10:45:38Z"},{"alias_kind":"pith_short_12","alias_value":"N7GCV265G4PZ","created_at":"2026-07-05T10:45:38Z"},{"alias_kind":"pith_short_16","alias_value":"N7GCV265G4PZNBQE","created_at":"2026-07-05T10:45:38Z"},{"alias_kind":"pith_short_8","alias_value":"N7GCV265","created_at":"2026-07-05T10:45:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:N7GCV265G4PZNBQEB654QR636O","target":"record","payload":{"canonical_record":{"source":{"id":"2410.16208","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-21T17:11:21Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"63602bde42e74168df4e3bc6f9399585014689c66a5f3920e60765551961ac1c","abstract_canon_sha256":"1c42ad511ec1bb418032054690619acdd4b9915f7a11795be397c4cf2d449e72"},"schema_version":"1.0"},"canonical_sha256":"6fcc2aebdd371f9686040fbbc847dbf38d9ee478c105331c0bae01fd2c7a5d3e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:38.345435Z","signature_b64":"kCqVbCl8uVA2TPFFbSTjmrFP5612hDaxvYKpkAr+rddLBAmMTikwdaAawc7I1VrcD0XmhFP+Ai0QnXKXRiK7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fcc2aebdd371f9686040fbbc847dbf38d9ee478c105331c0bae01fd2c7a5d3e","last_reissued_at":"2026-07-05T10:45:38.344899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:38.344899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.16208","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:45:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"feYgcwuQJ3NlFGmWn5sWyToVXRBt0gklYY64D/vkLBPrw9WjNEYgWmHyq1EBedIfD31LbuOU5IN9YNYUm3zXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:10:36.371953Z"},"content_sha256":"d4308979c1e9a4c01ed3558adbca5717087b540884541ba9c94e0b0e170a2b8b","schema_version":"1.0","event_id":"sha256:d4308979c1e9a4c01ed3558adbca5717087b540884541ba9c94e0b0e170a2b8b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:N7GCV265G4PZNBQEB654QR636O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compute-Constrained Data Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Alexander M. Rush, Junjie Oscar Yin","submitted_at":"2024-10-21T17:11:21Z","abstract_excerpt":"Data selection can reduce the amount of training data needed to finetune LLMs; however, the efficacy of data selection scales directly with its compute. Motivated by the practical challenge of compute-constrained finetuning, we consider the setting in which both the cost of selecting data and training are budgeted for. We first formalize the problem of data selection with a cost-aware utility function, and model the data selection problem as trading off initial-selection cost for training gain. We run a comprehensive sweep of experiments across multiple tasks, varying compute budget by scaling"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16208","kind":"arxiv","version":4},"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/2410.16208/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":"2026-07-05T10:45:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MFKTNwC3H0QE7s81MM45Uno5hbU1M3oUmB3POqSMqZGtII1uwGan42Hipuq9Ossy3jbtkQA6qjOeh497w6Y7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:10:36.372453Z"},"content_sha256":"8080f8f86826e14a309a33b4e91b96a170125d242817a6d4e68fac13161be54d","schema_version":"1.0","event_id":"sha256:8080f8f86826e14a309a33b4e91b96a170125d242817a6d4e68fac13161be54d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N7GCV265G4PZNBQEB654QR636O/bundle.json","state_url":"https://pith.science/pith/N7GCV265G4PZNBQEB654QR636O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N7GCV265G4PZNBQEB654QR636O/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":"2026-08-09T01:10:36Z","links":{"resolver":"https://pith.science/pith/N7GCV265G4PZNBQEB654QR636O","bundle":"https://pith.science/pith/N7GCV265G4PZNBQEB654QR636O/bundle.json","state":"https://pith.science/pith/N7GCV265G4PZNBQEB654QR636O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N7GCV265G4PZNBQEB654QR636O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N7GCV265G4PZNBQEB654QR636O","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":"1c42ad511ec1bb418032054690619acdd4b9915f7a11795be397c4cf2d449e72","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-21T17:11:21Z","title_canon_sha256":"63602bde42e74168df4e3bc6f9399585014689c66a5f3920e60765551961ac1c"},"schema_version":"1.0","source":{"id":"2410.16208","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16208","created_at":"2026-07-05T10:45:38Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16208v4","created_at":"2026-07-05T10:45:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16208","created_at":"2026-07-05T10:45:38Z"},{"alias_kind":"pith_short_12","alias_value":"N7GCV265G4PZ","created_at":"2026-07-05T10:45:38Z"},{"alias_kind":"pith_short_16","alias_value":"N7GCV265G4PZNBQE","created_at":"2026-07-05T10:45:38Z"},{"alias_kind":"pith_short_8","alias_value":"N7GCV265","created_at":"2026-07-05T10:45:38Z"}],"graph_snapshots":[{"event_id":"sha256:8080f8f86826e14a309a33b4e91b96a170125d242817a6d4e68fac13161be54d","target":"graph","created_at":"2026-07-05T10:45:38Z","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/2410.16208/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data selection can reduce the amount of training data needed to finetune LLMs; however, the efficacy of data selection scales directly with its compute. Motivated by the practical challenge of compute-constrained finetuning, we consider the setting in which both the cost of selecting data and training are budgeted for. We first formalize the problem of data selection with a cost-aware utility function, and model the data selection problem as trading off initial-selection cost for training gain. We run a comprehensive sweep of experiments across multiple tasks, varying compute budget by scaling","authors_text":"Alexander M. Rush, Junjie Oscar Yin","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-21T17:11:21Z","title":"Compute-Constrained Data Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16208","kind":"arxiv","version":4},"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:d4308979c1e9a4c01ed3558adbca5717087b540884541ba9c94e0b0e170a2b8b","target":"record","created_at":"2026-07-05T10:45:38Z","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":"1c42ad511ec1bb418032054690619acdd4b9915f7a11795be397c4cf2d449e72","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-21T17:11:21Z","title_canon_sha256":"63602bde42e74168df4e3bc6f9399585014689c66a5f3920e60765551961ac1c"},"schema_version":"1.0","source":{"id":"2410.16208","kind":"arxiv","version":4}},"canonical_sha256":"6fcc2aebdd371f9686040fbbc847dbf38d9ee478c105331c0bae01fd2c7a5d3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fcc2aebdd371f9686040fbbc847dbf38d9ee478c105331c0bae01fd2c7a5d3e","first_computed_at":"2026-07-05T10:45:38.344899Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:38.344899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kCqVbCl8uVA2TPFFbSTjmrFP5612hDaxvYKpkAr+rddLBAmMTikwdaAawc7I1VrcD0XmhFP+Ai0QnXKXRiK7Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:38.345435Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16208","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4308979c1e9a4c01ed3558adbca5717087b540884541ba9c94e0b0e170a2b8b","sha256:8080f8f86826e14a309a33b4e91b96a170125d242817a6d4e68fac13161be54d"],"state_sha256":"f8a3cf082e5b0ee098cf9ae2295f343083d79e9ae7d92f49d7fe6233967540ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kGTeSxkUb34fZGhtH2eIlK8tg8WUvd52YBUiqY3SCkeE6WgwB0x3qv06v/V+PrJ1YDGB6hnOMVZ6hcHb4TD4BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T01:10:36.376312Z","bundle_sha256":"f83f20201ab22f471cc59de36ecd58873b9aa95e6d8f655f61fa2274dafdb72f"}}