{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4JG2EM55BZXAOYFUSCLFQ4NRYG","short_pith_number":"pith:4JG2EM55","schema_version":"1.0","canonical_sha256":"e24da233bd0e6e0760b490965871b1c18e5ab8b35b680df13f6675148f64c010","source":{"kind":"arxiv","id":"2410.18194","version":2},"attestation_state":"computed","paper":{"title":"ZIP-FIT: Embedding-Free Data Selection via Compression-Based Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Brando Miranda, Elyas Obbad, Iddah Mlauzi, Kamal Obbad, Rylan Schaeffer, Sanmi Koyejo, Suhana Bedi","submitted_at":"2024-10-23T18:01:06Z","abstract_excerpt":"Data selection is crucial for optimizing language model (LM) performance on specific tasks, yet most existing methods fail to effectively consider the target task distribution.\n  Current approaches either ignore task-specific requirements entirely or rely on approximations that fail to capture the nuanced patterns needed for tasks like Autoformalization or code generation.\n  Methods that do consider the target distribution often rely on simplistic, sometimes noisy, representations, like hashed n-gram features, which can lead to collisions and introduce noise.\n  We introduce ZIP-FIT, a data sel"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.18194","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T18:01:06Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"9166def66aeda3ba435e158937cdb76c8a833768334287cb88dcd21702decee8","abstract_canon_sha256":"93d7fa6768f8a0bb9e4a465190a64d39ce5959ca5750f63ae4d94ff5f90ed1a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:20.765948Z","signature_b64":"Q4OCsRh/09ZfxJwdCHukUoquJtwPHhQNX+DCiD1wdz4gYsUoN+chr6ZlWgJV6F5JysZ8AcXfyP6wF76+L/VLAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e24da233bd0e6e0760b490965871b1c18e5ab8b35b680df13f6675148f64c010","last_reissued_at":"2026-07-05T10:48:20.765475Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:20.765475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZIP-FIT: Embedding-Free Data Selection via Compression-Based Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Brando Miranda, Elyas Obbad, Iddah Mlauzi, Kamal Obbad, Rylan Schaeffer, Sanmi Koyejo, Suhana Bedi","submitted_at":"2024-10-23T18:01:06Z","abstract_excerpt":"Data selection is crucial for optimizing language model (LM) performance on specific tasks, yet most existing methods fail to effectively consider the target task distribution.\n  Current approaches either ignore task-specific requirements entirely or rely on approximations that fail to capture the nuanced patterns needed for tasks like Autoformalization or code generation.\n  Methods that do consider the target distribution often rely on simplistic, sometimes noisy, representations, like hashed n-gram features, which can lead to collisions and introduce noise.\n  We introduce ZIP-FIT, a data sel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18194","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/2410.18194/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.18194","created_at":"2026-07-05T10:48:20.765532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18194v2","created_at":"2026-07-05T10:48:20.765532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18194","created_at":"2026-07-05T10:48:20.765532+00:00"},{"alias_kind":"pith_short_12","alias_value":"4JG2EM55BZXA","created_at":"2026-07-05T10:48:20.765532+00:00"},{"alias_kind":"pith_short_16","alias_value":"4JG2EM55BZXAOYFU","created_at":"2026-07-05T10:48:20.765532+00:00"},{"alias_kind":"pith_short_8","alias_value":"4JG2EM55","created_at":"2026-07-05T10:48:20.765532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4JG2EM55BZXAOYFUSCLFQ4NRYG","json":"https://pith.science/pith/4JG2EM55BZXAOYFUSCLFQ4NRYG.json","graph_json":"https://pith.science/api/pith-number/4JG2EM55BZXAOYFUSCLFQ4NRYG/graph.json","events_json":"https://pith.science/api/pith-number/4JG2EM55BZXAOYFUSCLFQ4NRYG/events.json","paper":"https://pith.science/paper/4JG2EM55"},"agent_actions":{"view_html":"https://pith.science/pith/4JG2EM55BZXAOYFUSCLFQ4NRYG","download_json":"https://pith.science/pith/4JG2EM55BZXAOYFUSCLFQ4NRYG.json","view_paper":"https://pith.science/paper/4JG2EM55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18194&json=true","fetch_graph":"https://pith.science/api/pith-number/4JG2EM55BZXAOYFUSCLFQ4NRYG/graph.json","fetch_events":"https://pith.science/api/pith-number/4JG2EM55BZXAOYFUSCLFQ4NRYG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4JG2EM55BZXAOYFUSCLFQ4NRYG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4JG2EM55BZXAOYFUSCLFQ4NRYG/action/storage_attestation","attest_author":"https://pith.science/pith/4JG2EM55BZXAOYFUSCLFQ4NRYG/action/author_attestation","sign_citation":"https://pith.science/pith/4JG2EM55BZXAOYFUSCLFQ4NRYG/action/citation_signature","submit_replication":"https://pith.science/pith/4JG2EM55BZXAOYFUSCLFQ4NRYG/action/replication_record"}},"created_at":"2026-07-05T10:48:20.765532+00:00","updated_at":"2026-07-05T10:48:20.765532+00:00"}