{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TD5X57GDJIPVNRMNBZD7LZOZVA","short_pith_number":"pith:TD5X57GD","canonical_record":{"source":{"id":"2505.21941","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T03:50:19Z","cross_cats_sorted":[],"title_canon_sha256":"d3ee9114a193c58fae0f3cc02ded481a5a2da27c5f4d97868b86ba6d6ab876c0","abstract_canon_sha256":"9f708ca7de3c189e57bb525e240f15035c1bbf0bfad661d66aa6b3eff66cfc6b"},"schema_version":"1.0"},"canonical_sha256":"98fb7efcc34a1f56c58d0e47f5e5d9a821d48d252bbbdb55199fafc9651eab28","source":{"kind":"arxiv","id":"2505.21941","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21941","created_at":"2026-07-05T11:11:06Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21941v1","created_at":"2026-07-05T11:11:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21941","created_at":"2026-07-05T11:11:06Z"},{"alias_kind":"pith_short_12","alias_value":"TD5X57GDJIPV","created_at":"2026-07-05T11:11:06Z"},{"alias_kind":"pith_short_16","alias_value":"TD5X57GDJIPVNRMN","created_at":"2026-07-05T11:11:06Z"},{"alias_kind":"pith_short_8","alias_value":"TD5X57GD","created_at":"2026-07-05T11:11:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TD5X57GDJIPVNRMNBZD7LZOZVA","target":"record","payload":{"canonical_record":{"source":{"id":"2505.21941","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T03:50:19Z","cross_cats_sorted":[],"title_canon_sha256":"d3ee9114a193c58fae0f3cc02ded481a5a2da27c5f4d97868b86ba6d6ab876c0","abstract_canon_sha256":"9f708ca7de3c189e57bb525e240f15035c1bbf0bfad661d66aa6b3eff66cfc6b"},"schema_version":"1.0"},"canonical_sha256":"98fb7efcc34a1f56c58d0e47f5e5d9a821d48d252bbbdb55199fafc9651eab28","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:06.268854Z","signature_b64":"V3wr2GX28sZX1ejpwf+6hZPUbwsA73thhRKf1ErZMQQrjvTHX7LjXHzfVtDqLGIZ/IOiT08PFfEJHfrYGP+PCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98fb7efcc34a1f56c58d0e47f5e5d9a821d48d252bbbdb55199fafc9651eab28","last_reissued_at":"2026-07-05T11:11:06.268428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:06.268428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.21941","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":"2026-07-05T11:11:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mLGYJStVatvORWPyLfxKpHNbbhZSahufSGj982JWZnmI7sD144/TkNia3ZrivCuTW+uvFYtK6G6faLPY2EEtCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T09:06:53.126508Z"},"content_sha256":"95bdccc4739547c3a9a34ba051dbd903a4d115a4d3d69fa890c88066c2bec377","schema_version":"1.0","event_id":"sha256:95bdccc4739547c3a9a34ba051dbd903a4d115a4d3d69fa890c88066c2bec377"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TD5X57GDJIPVNRMNBZD7LZOZVA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Test-Time Scaling with Repeated Sampling Improves Multilingual Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashim Gupta, Vivek Srikumar","submitted_at":"2025-05-28T03:50:19Z","abstract_excerpt":"Inference-time scaling via repeated sampling has shown promise in reasoning tasks, but its effectiveness in multilingual generation remains underexplored. We evaluate this approach using perplexity- and reward-based verifiers on two multilingual benchmarks: the Aya Evaluation Suite and m-ArenaHard. Our results show consistent quality improvements, with gains exceeding 35% in some cases. While perplexity-based scoring is effective for open-ended prompts, only reward-based verifiers improve performance on tasks requiring reasoning (e.g., math, code). Our results demonstrate the broader utility o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21941","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/2505.21941/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":"2026-07-05T11:11:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Y3POXwtGmhRdpjlyOmGKmOrQZLXkKzNKpuElH1/ELOZP0c/m3mJYFt49CcG+8Lf1qTFJwCszrlXQ4wRMFzGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T09:06:53.127039Z"},"content_sha256":"c10a5426968532350701a4eff5ce1fdfd70ac4ceb13516b3e7208591baeaa93b","schema_version":"1.0","event_id":"sha256:c10a5426968532350701a4eff5ce1fdfd70ac4ceb13516b3e7208591baeaa93b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TD5X57GDJIPVNRMNBZD7LZOZVA/bundle.json","state_url":"https://pith.science/pith/TD5X57GDJIPVNRMNBZD7LZOZVA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TD5X57GDJIPVNRMNBZD7LZOZVA/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":"2026-08-15T09:06:53Z","links":{"resolver":"https://pith.science/pith/TD5X57GDJIPVNRMNBZD7LZOZVA","bundle":"https://pith.science/pith/TD5X57GDJIPVNRMNBZD7LZOZVA/bundle.json","state":"https://pith.science/pith/TD5X57GDJIPVNRMNBZD7LZOZVA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TD5X57GDJIPVNRMNBZD7LZOZVA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TD5X57GDJIPVNRMNBZD7LZOZVA","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":"9f708ca7de3c189e57bb525e240f15035c1bbf0bfad661d66aa6b3eff66cfc6b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T03:50:19Z","title_canon_sha256":"d3ee9114a193c58fae0f3cc02ded481a5a2da27c5f4d97868b86ba6d6ab876c0"},"schema_version":"1.0","source":{"id":"2505.21941","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21941","created_at":"2026-07-05T11:11:06Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21941v1","created_at":"2026-07-05T11:11:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21941","created_at":"2026-07-05T11:11:06Z"},{"alias_kind":"pith_short_12","alias_value":"TD5X57GDJIPV","created_at":"2026-07-05T11:11:06Z"},{"alias_kind":"pith_short_16","alias_value":"TD5X57GDJIPVNRMN","created_at":"2026-07-05T11:11:06Z"},{"alias_kind":"pith_short_8","alias_value":"TD5X57GD","created_at":"2026-07-05T11:11:06Z"}],"graph_snapshots":[{"event_id":"sha256:c10a5426968532350701a4eff5ce1fdfd70ac4ceb13516b3e7208591baeaa93b","target":"graph","created_at":"2026-07-05T11:11:06Z","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/2505.21941/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inference-time scaling via repeated sampling has shown promise in reasoning tasks, but its effectiveness in multilingual generation remains underexplored. We evaluate this approach using perplexity- and reward-based verifiers on two multilingual benchmarks: the Aya Evaluation Suite and m-ArenaHard. Our results show consistent quality improvements, with gains exceeding 35% in some cases. While perplexity-based scoring is effective for open-ended prompts, only reward-based verifiers improve performance on tasks requiring reasoning (e.g., math, code). Our results demonstrate the broader utility o","authors_text":"Ashim Gupta, Vivek Srikumar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T03:50:19Z","title":"Test-Time Scaling with Repeated Sampling Improves Multilingual Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21941","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":"sha256:95bdccc4739547c3a9a34ba051dbd903a4d115a4d3d69fa890c88066c2bec377","target":"record","created_at":"2026-07-05T11:11:06Z","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":"9f708ca7de3c189e57bb525e240f15035c1bbf0bfad661d66aa6b3eff66cfc6b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T03:50:19Z","title_canon_sha256":"d3ee9114a193c58fae0f3cc02ded481a5a2da27c5f4d97868b86ba6d6ab876c0"},"schema_version":"1.0","source":{"id":"2505.21941","kind":"arxiv","version":1}},"canonical_sha256":"98fb7efcc34a1f56c58d0e47f5e5d9a821d48d252bbbdb55199fafc9651eab28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98fb7efcc34a1f56c58d0e47f5e5d9a821d48d252bbbdb55199fafc9651eab28","first_computed_at":"2026-07-05T11:11:06.268428Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:06.268428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V3wr2GX28sZX1ejpwf+6hZPUbwsA73thhRKf1ErZMQQrjvTHX7LjXHzfVtDqLGIZ/IOiT08PFfEJHfrYGP+PCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:06.268854Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21941","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95bdccc4739547c3a9a34ba051dbd903a4d115a4d3d69fa890c88066c2bec377","sha256:c10a5426968532350701a4eff5ce1fdfd70ac4ceb13516b3e7208591baeaa93b"],"state_sha256":"94e704de05c7a1779529861d62c2921b85fbe63108d49f4ddebb35686f866a70"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JXVgKoDGyuB15+J+AycRtmwLGryl1+IqurAViqJYwSHhYS0kwH1IeX+MdV5lqPMv1gUQtFCilrfK4TqXSO0jCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T09:06:53.130921Z","bundle_sha256":"60ad7614c9a423e710e34efb7cca8b56eb154e0b727e8932b1be49b905e172bf"}}