{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Z6PEKFQFNVW2QVHPEPW43BBS7P","short_pith_number":"pith:Z6PEKFQF","canonical_record":{"source":{"id":"2406.09334","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T17:15:33Z","cross_cats_sorted":[],"title_canon_sha256":"8053debd9fb6054daadb5f0afbec3c6e99d4b6bfae9e0a0ce646923d9fcb09e9","abstract_canon_sha256":"867409c66302a740f993791063d613e3baef8a15af4007d36c16c206e92d0684"},"schema_version":"1.0"},"canonical_sha256":"cf9e4516056d6da854ef23edcd8432fbd98a632606b44bedb08d9cc95629a244","source":{"kind":"arxiv","id":"2406.09334","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09334","created_at":"2026-07-05T09:49:06Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09334v3","created_at":"2026-07-05T09:49:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09334","created_at":"2026-07-05T09:49:06Z"},{"alias_kind":"pith_short_12","alias_value":"Z6PEKFQFNVW2","created_at":"2026-07-05T09:49:06Z"},{"alias_kind":"pith_short_16","alias_value":"Z6PEKFQFNVW2QVHP","created_at":"2026-07-05T09:49:06Z"},{"alias_kind":"pith_short_8","alias_value":"Z6PEKFQF","created_at":"2026-07-05T09:49:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Z6PEKFQFNVW2QVHPEPW43BBS7P","target":"record","payload":{"canonical_record":{"source":{"id":"2406.09334","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T17:15:33Z","cross_cats_sorted":[],"title_canon_sha256":"8053debd9fb6054daadb5f0afbec3c6e99d4b6bfae9e0a0ce646923d9fcb09e9","abstract_canon_sha256":"867409c66302a740f993791063d613e3baef8a15af4007d36c16c206e92d0684"},"schema_version":"1.0"},"canonical_sha256":"cf9e4516056d6da854ef23edcd8432fbd98a632606b44bedb08d9cc95629a244","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:06.475702Z","signature_b64":"A9ji+jp751PKSV+PsR1W0Ty3gbG0bGpWGVfarXOe/vPn7OxZYumnoIjCT+x5OItX8gkA8qlJluZ8ytpPlwqADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf9e4516056d6da854ef23edcd8432fbd98a632606b44bedb08d9cc95629a244","last_reissued_at":"2026-07-05T09:49:06.475169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:06.475169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.09334","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:49:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7wpNF4ROEe426zVU/iN45mCUsee6uXiDBK/r8w+EVHEzaA8VSJl+TCclXfCfrukXXVNSgwag4h8gh2yyZIrhBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:48:33.453035Z"},"content_sha256":"d3e0da24a4e1db7432fd71568fc945362c54bdff2dab7ca5e29544ca8543c5e4","schema_version":"1.0","event_id":"sha256:d3e0da24a4e1db7432fd71568fc945362c54bdff2dab7ca5e29544ca8543c5e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Z6PEKFQFNVW2QVHPEPW43BBS7P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ProxyLM: Predicting Language Model Performance on Multilingual Tasks via Proxy Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenyue Li, David Anugraha, En-Shiun Annie Lee, Genta Indra Winata, Patrick Amadeus Irawan","submitted_at":"2024-06-13T17:15:33Z","abstract_excerpt":"Performance prediction is a method to estimate the performance of Language Models (LMs) on various Natural Language Processing (NLP) tasks, mitigating computational costs associated with model capacity and data for fine-tuning. Our paper presents ProxyLM, a scalable task- and language-agnostic framework designed to predict the performance of LMs using proxy models. These proxy models act as surrogates, approximating the performance of the LM of interest. By leveraging these proxy models, ProxyLM significantly reduces computational overhead in task evaluations, achieving up to a 37.08x speedup "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09334","kind":"arxiv","version":3},"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/2406.09334/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":"2026-07-05T09:49:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"76xxvb57Ed9biNfTs4d6KHIogwiYAvMvvJyG6VFjGT+FMXhLr4BgTiHE/6iohpssJt9zpafPSxul7WMGl9ViBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:48:33.453665Z"},"content_sha256":"07373b6b4b18f6a9e50bed949a2785e15604b1592d7a1755b071be2ae57f028a","schema_version":"1.0","event_id":"sha256:07373b6b4b18f6a9e50bed949a2785e15604b1592d7a1755b071be2ae57f028a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z6PEKFQFNVW2QVHPEPW43BBS7P/bundle.json","state_url":"https://pith.science/pith/Z6PEKFQFNVW2QVHPEPW43BBS7P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z6PEKFQFNVW2QVHPEPW43BBS7P/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":"2026-08-06T14:48:33Z","links":{"resolver":"https://pith.science/pith/Z6PEKFQFNVW2QVHPEPW43BBS7P","bundle":"https://pith.science/pith/Z6PEKFQFNVW2QVHPEPW43BBS7P/bundle.json","state":"https://pith.science/pith/Z6PEKFQFNVW2QVHPEPW43BBS7P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z6PEKFQFNVW2QVHPEPW43BBS7P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z6PEKFQFNVW2QVHPEPW43BBS7P","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":"867409c66302a740f993791063d613e3baef8a15af4007d36c16c206e92d0684","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T17:15:33Z","title_canon_sha256":"8053debd9fb6054daadb5f0afbec3c6e99d4b6bfae9e0a0ce646923d9fcb09e9"},"schema_version":"1.0","source":{"id":"2406.09334","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09334","created_at":"2026-07-05T09:49:06Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09334v3","created_at":"2026-07-05T09:49:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09334","created_at":"2026-07-05T09:49:06Z"},{"alias_kind":"pith_short_12","alias_value":"Z6PEKFQFNVW2","created_at":"2026-07-05T09:49:06Z"},{"alias_kind":"pith_short_16","alias_value":"Z6PEKFQFNVW2QVHP","created_at":"2026-07-05T09:49:06Z"},{"alias_kind":"pith_short_8","alias_value":"Z6PEKFQF","created_at":"2026-07-05T09:49:06Z"}],"graph_snapshots":[{"event_id":"sha256:07373b6b4b18f6a9e50bed949a2785e15604b1592d7a1755b071be2ae57f028a","target":"graph","created_at":"2026-07-05T09:49:06Z","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/2406.09334/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Performance prediction is a method to estimate the performance of Language Models (LMs) on various Natural Language Processing (NLP) tasks, mitigating computational costs associated with model capacity and data for fine-tuning. Our paper presents ProxyLM, a scalable task- and language-agnostic framework designed to predict the performance of LMs using proxy models. These proxy models act as surrogates, approximating the performance of the LM of interest. By leveraging these proxy models, ProxyLM significantly reduces computational overhead in task evaluations, achieving up to a 37.08x speedup ","authors_text":"Chenyue Li, David Anugraha, En-Shiun Annie Lee, Genta Indra Winata, Patrick Amadeus Irawan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T17:15:33Z","title":"ProxyLM: Predicting Language Model Performance on Multilingual Tasks via Proxy Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09334","kind":"arxiv","version":3},"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:d3e0da24a4e1db7432fd71568fc945362c54bdff2dab7ca5e29544ca8543c5e4","target":"record","created_at":"2026-07-05T09:49:06Z","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":"867409c66302a740f993791063d613e3baef8a15af4007d36c16c206e92d0684","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T17:15:33Z","title_canon_sha256":"8053debd9fb6054daadb5f0afbec3c6e99d4b6bfae9e0a0ce646923d9fcb09e9"},"schema_version":"1.0","source":{"id":"2406.09334","kind":"arxiv","version":3}},"canonical_sha256":"cf9e4516056d6da854ef23edcd8432fbd98a632606b44bedb08d9cc95629a244","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf9e4516056d6da854ef23edcd8432fbd98a632606b44bedb08d9cc95629a244","first_computed_at":"2026-07-05T09:49:06.475169Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:06.475169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A9ji+jp751PKSV+PsR1W0Ty3gbG0bGpWGVfarXOe/vPn7OxZYumnoIjCT+x5OItX8gkA8qlJluZ8ytpPlwqADA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:06.475702Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09334","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3e0da24a4e1db7432fd71568fc945362c54bdff2dab7ca5e29544ca8543c5e4","sha256:07373b6b4b18f6a9e50bed949a2785e15604b1592d7a1755b071be2ae57f028a"],"state_sha256":"6ca632899b8bd4015a6ebf8e2fe26954c82adb77ecfc8d9bb9a4faeebf66f396"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ApEiBNRbhDuiHuxGBom2tiN6je8KifCWBVV9vvvoPdBVS+DNnBjf3hIEHrlR96CVDD9X09vwkwTBItGcbaDEAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T14:48:33.457062Z","bundle_sha256":"53ed0e302c5c7fe8b9bec32a5cba63aa367a4cb49b1f50d99f42f5f7a99a96e6"}}