{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HB56OC7WJGE3OFQGUQHCQTLCLZ","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":"65a8514e976d073e5ebb9d6d9ed522b52ba439c80c1058a40574844acb7c0c6f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-26T16:29:18Z","title_canon_sha256":"32ac9abeb4d04305c94077236f611cf32c9943d848013ee2167f62d3ec688c21"},"schema_version":"1.0","source":{"id":"2303.14770","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.14770","created_at":"2026-07-05T05:54:45Z"},{"alias_kind":"arxiv_version","alias_value":"2303.14770v1","created_at":"2026-07-05T05:54:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14770","created_at":"2026-07-05T05:54:45Z"},{"alias_kind":"pith_short_12","alias_value":"HB56OC7WJGE3","created_at":"2026-07-05T05:54:45Z"},{"alias_kind":"pith_short_16","alias_value":"HB56OC7WJGE3OFQG","created_at":"2026-07-05T05:54:45Z"},{"alias_kind":"pith_short_8","alias_value":"HB56OC7W","created_at":"2026-07-05T05:54:45Z"}],"graph_snapshots":[{"event_id":"sha256:14f8a8d6ee8a26e94bfee505790e4b88e21570dd2734765dcf60fcb6cae505f2","target":"graph","created_at":"2026-07-05T05:54:45Z","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/2303.14770/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In very recent years more attention has been placed on probing the role of pre-training data in Large Language Models (LLMs) downstream behaviour. Despite the importance, there is no public tool that supports such analysis of pre-training corpora at large scale. To help research in this space, we launch Koala, a searchable index over large pre-training corpora using compressed suffix arrays with highly efficient compression rate and search support. In its first release we index the public proportion of OPT 175B pre-training data. Koala provides a framework to do forensic analysis on the curren","authors_text":"Ehsan Shareghi, Gholamreza Haffari, Thuy-Trang Vu, Xuanli He","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-26T16:29:18Z","title":"Koala: An Index for Quantifying Overlaps with Pre-training Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14770","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:bf4a7922952772cc2e602e3eeb177c79515dba2c5be2689498350946311cb057","target":"record","created_at":"2026-07-05T05:54:45Z","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":"65a8514e976d073e5ebb9d6d9ed522b52ba439c80c1058a40574844acb7c0c6f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-26T16:29:18Z","title_canon_sha256":"32ac9abeb4d04305c94077236f611cf32c9943d848013ee2167f62d3ec688c21"},"schema_version":"1.0","source":{"id":"2303.14770","kind":"arxiv","version":1}},"canonical_sha256":"387be70bf64989b71606a40e284d625e769ef0c7819de0ca7a7c5fff68121bd0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"387be70bf64989b71606a40e284d625e769ef0c7819de0ca7a7c5fff68121bd0","first_computed_at":"2026-07-05T05:54:45.898163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:54:45.898163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"etYhsiqNDa0KYczdgWSD2IaUcwYf5gEA6KZMLOOxDbSJ1habUa0BfhhiFCQW6MqKfYT9BL8ZtcETZQstsJdhCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:54:45.898669Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.14770","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf4a7922952772cc2e602e3eeb177c79515dba2c5be2689498350946311cb057","sha256:14f8a8d6ee8a26e94bfee505790e4b88e21570dd2734765dcf60fcb6cae505f2"],"state_sha256":"fa83e12cc6e36ea8bf539f93bbb6e1280a1f05433df1b7373e96b80b58badb33"}