{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5H7NH7ZD2QDZRE7IQA66NA3KHM","short_pith_number":"pith:5H7NH7ZD","canonical_record":{"source":{"id":"2310.11430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T17:40:21Z","cross_cats_sorted":[],"title_canon_sha256":"0f3655456a2874f692b86c1b6416c7b7833f5458c45ae2c0d82f594ff7325153","abstract_canon_sha256":"d747c1ad770c3ead1efffbf3711ebc7d63505debb17475832e0b2e802ac834d8"},"schema_version":"1.0"},"canonical_sha256":"e9fed3ff23d4079893e8803de6836a3b0469c00699563696ff1c7d0354542d57","source":{"kind":"arxiv","id":"2310.11430","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.11430","created_at":"2026-07-05T07:01:55Z"},{"alias_kind":"arxiv_version","alias_value":"2310.11430v1","created_at":"2026-07-05T07:01:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11430","created_at":"2026-07-05T07:01:55Z"},{"alias_kind":"pith_short_12","alias_value":"5H7NH7ZD2QDZ","created_at":"2026-07-05T07:01:55Z"},{"alias_kind":"pith_short_16","alias_value":"5H7NH7ZD2QDZRE7I","created_at":"2026-07-05T07:01:55Z"},{"alias_kind":"pith_short_8","alias_value":"5H7NH7ZD","created_at":"2026-07-05T07:01:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5H7NH7ZD2QDZRE7IQA66NA3KHM","target":"record","payload":{"canonical_record":{"source":{"id":"2310.11430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T17:40:21Z","cross_cats_sorted":[],"title_canon_sha256":"0f3655456a2874f692b86c1b6416c7b7833f5458c45ae2c0d82f594ff7325153","abstract_canon_sha256":"d747c1ad770c3ead1efffbf3711ebc7d63505debb17475832e0b2e802ac834d8"},"schema_version":"1.0"},"canonical_sha256":"e9fed3ff23d4079893e8803de6836a3b0469c00699563696ff1c7d0354542d57","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:55.239058Z","signature_b64":"mrH/wHtt3xyHtNBGMJi61oEqA820A70zZSQMEb1ATFywW9npHAqn32JaQ0e9dzMS6uC3q2mZ4yuj2MmXXdBaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9fed3ff23d4079893e8803de6836a3b0469c00699563696ff1c7d0354542d57","last_reissued_at":"2026-07-05T07:01:55.238644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:55.238644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.11430","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":"2026-07-05T07:01:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uwuAM7F3+0tILc8t1P7QIkj6z4+LO1yXxev0MNoRS6+jdt5i/dWARDTmm/a5+YCXMqLoWFU6OxVZHekCuJg5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T11:03:47.298420Z"},"content_sha256":"7200c9829f4828ba478e6e210768dc8a697a466cfd596adc056ddbee13cbfdcf","schema_version":"1.0","event_id":"sha256:7200c9829f4828ba478e6e210768dc8a697a466cfd596adc056ddbee13cbfdcf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5H7NH7ZD2QDZRE7IQA66NA3KHM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Empirical Study of Translation Hypothesis Ensembling with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andr\\'e F. T. Martins, Ant\\'onio Farinhas, Jos\\'e G. C. de Souza","submitted_at":"2023-10-17T17:40:21Z","abstract_excerpt":"Large language models (LLMs) are becoming a one-fits-many solution, but they sometimes hallucinate or produce unreliable output. In this paper, we investigate how hypothesis ensembling can improve the quality of the generated text for the specific problem of LLM-based machine translation. We experiment with several techniques for ensembling hypotheses produced by LLMs such as ChatGPT, LLaMA, and Alpaca. We provide a comprehensive study along multiple dimensions, including the method to generate hypotheses (multiple prompts, temperature-based sampling, and beam search) and the strategy to produ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11430","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/2310.11430/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":"2026-07-05T07:01:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y2KZDNCtLYcQyV4PGQCd1Pzg2KTiKbAVYOs+778MNuOMDIOJCHCqj9pkqzLkg2hi/U5r9VVsPMLjtHV3aIVzDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T11:03:47.299501Z"},"content_sha256":"b74fe2fb7f407c8d868204b2941cd7de1b988cd5ee2f26b8d1c2419b65f0dc6d","schema_version":"1.0","event_id":"sha256:b74fe2fb7f407c8d868204b2941cd7de1b988cd5ee2f26b8d1c2419b65f0dc6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5H7NH7ZD2QDZRE7IQA66NA3KHM/bundle.json","state_url":"https://pith.science/pith/5H7NH7ZD2QDZRE7IQA66NA3KHM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5H7NH7ZD2QDZRE7IQA66NA3KHM/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":"2026-08-13T11:03:47Z","links":{"resolver":"https://pith.science/pith/5H7NH7ZD2QDZRE7IQA66NA3KHM","bundle":"https://pith.science/pith/5H7NH7ZD2QDZRE7IQA66NA3KHM/bundle.json","state":"https://pith.science/pith/5H7NH7ZD2QDZRE7IQA66NA3KHM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5H7NH7ZD2QDZRE7IQA66NA3KHM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5H7NH7ZD2QDZRE7IQA66NA3KHM","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":"d747c1ad770c3ead1efffbf3711ebc7d63505debb17475832e0b2e802ac834d8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T17:40:21Z","title_canon_sha256":"0f3655456a2874f692b86c1b6416c7b7833f5458c45ae2c0d82f594ff7325153"},"schema_version":"1.0","source":{"id":"2310.11430","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.11430","created_at":"2026-07-05T07:01:55Z"},{"alias_kind":"arxiv_version","alias_value":"2310.11430v1","created_at":"2026-07-05T07:01:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11430","created_at":"2026-07-05T07:01:55Z"},{"alias_kind":"pith_short_12","alias_value":"5H7NH7ZD2QDZ","created_at":"2026-07-05T07:01:55Z"},{"alias_kind":"pith_short_16","alias_value":"5H7NH7ZD2QDZRE7I","created_at":"2026-07-05T07:01:55Z"},{"alias_kind":"pith_short_8","alias_value":"5H7NH7ZD","created_at":"2026-07-05T07:01:55Z"}],"graph_snapshots":[{"event_id":"sha256:b74fe2fb7f407c8d868204b2941cd7de1b988cd5ee2f26b8d1c2419b65f0dc6d","target":"graph","created_at":"2026-07-05T07:01:55Z","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/2310.11430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are becoming a one-fits-many solution, but they sometimes hallucinate or produce unreliable output. In this paper, we investigate how hypothesis ensembling can improve the quality of the generated text for the specific problem of LLM-based machine translation. We experiment with several techniques for ensembling hypotheses produced by LLMs such as ChatGPT, LLaMA, and Alpaca. We provide a comprehensive study along multiple dimensions, including the method to generate hypotheses (multiple prompts, temperature-based sampling, and beam search) and the strategy to produ","authors_text":"Andr\\'e F. T. Martins, Ant\\'onio Farinhas, Jos\\'e G. C. de Souza","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T17:40:21Z","title":"An Empirical Study of Translation Hypothesis Ensembling with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11430","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":"sha256:7200c9829f4828ba478e6e210768dc8a697a466cfd596adc056ddbee13cbfdcf","target":"record","created_at":"2026-07-05T07:01:55Z","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":"d747c1ad770c3ead1efffbf3711ebc7d63505debb17475832e0b2e802ac834d8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T17:40:21Z","title_canon_sha256":"0f3655456a2874f692b86c1b6416c7b7833f5458c45ae2c0d82f594ff7325153"},"schema_version":"1.0","source":{"id":"2310.11430","kind":"arxiv","version":1}},"canonical_sha256":"e9fed3ff23d4079893e8803de6836a3b0469c00699563696ff1c7d0354542d57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9fed3ff23d4079893e8803de6836a3b0469c00699563696ff1c7d0354542d57","first_computed_at":"2026-07-05T07:01:55.238644Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:55.238644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mrH/wHtt3xyHtNBGMJi61oEqA820A70zZSQMEb1ATFywW9npHAqn32JaQ0e9dzMS6uC3q2mZ4yuj2MmXXdBaCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:55.239058Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.11430","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7200c9829f4828ba478e6e210768dc8a697a466cfd596adc056ddbee13cbfdcf","sha256:b74fe2fb7f407c8d868204b2941cd7de1b988cd5ee2f26b8d1c2419b65f0dc6d"],"state_sha256":"2d7bd9fd7c4588924123d788d53be86f795e4fee8be792f07874dd5190f9553e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LjqAUjRb9zAm9gvjUh+NGfBt3yDih0GKU91rcs/DvSTLcO0j9eNN3mRMxyxIrHyTHg9HVMaOzvc9CM+BhCrvBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T11:03:47.305544Z","bundle_sha256":"e7b5d916f7eaac31c548e9e3f22acf2fd3bbcce869c3e3cef62c328c557a9888"}}