{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TCJ6EJPLYXXFDHJK4GMPRJRLA3","short_pith_number":"pith:TCJ6EJPL","canonical_record":{"source":{"id":"2403.04182","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-07T03:24:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"742d8176775b3dc2fbe491a0125c80c6288cb2b86b4c6f80e8de4fe62442a991","abstract_canon_sha256":"241691244a2578cf98035cb005fd947d060e7b86fceb1c5fda7e2f3834736fae"},"schema_version":"1.0"},"canonical_sha256":"9893e225ebc5ee519d2ae198f8a62b06f34865b6bc21aecbaef65bb5254db0c4","source":{"kind":"arxiv","id":"2403.04182","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.04182","created_at":"2026-07-05T09:29:26Z"},{"alias_kind":"arxiv_version","alias_value":"2403.04182v3","created_at":"2026-07-05T09:29:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04182","created_at":"2026-07-05T09:29:26Z"},{"alias_kind":"pith_short_12","alias_value":"TCJ6EJPLYXXF","created_at":"2026-07-05T09:29:26Z"},{"alias_kind":"pith_short_16","alias_value":"TCJ6EJPLYXXFDHJK","created_at":"2026-07-05T09:29:26Z"},{"alias_kind":"pith_short_8","alias_value":"TCJ6EJPL","created_at":"2026-07-05T09:29:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TCJ6EJPLYXXFDHJK4GMPRJRLA3","target":"record","payload":{"canonical_record":{"source":{"id":"2403.04182","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-07T03:24:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"742d8176775b3dc2fbe491a0125c80c6288cb2b86b4c6f80e8de4fe62442a991","abstract_canon_sha256":"241691244a2578cf98035cb005fd947d060e7b86fceb1c5fda7e2f3834736fae"},"schema_version":"1.0"},"canonical_sha256":"9893e225ebc5ee519d2ae198f8a62b06f34865b6bc21aecbaef65bb5254db0c4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:26.843119Z","signature_b64":"bRHk7dopmXM9uacBozAo79iyQNQdfN5oXbWs2CmLpg12EHFkX2jRqSFKcr7dLkcz3+oXu9qSGCpvh1jTCFtmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9893e225ebc5ee519d2ae198f8a62b06f34865b6bc21aecbaef65bb5254db0c4","last_reissued_at":"2026-07-05T09:29:26.842606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:26.842606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.04182","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":"2026-07-05T09:29:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nsbHt37wE7SXwul9g3AJoeSTfipoggKmNShsVBvAjgIU1Y8M278nof68rbXEqIUPzJW8Hr8woAJ5vMq0SYz7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:10:06.048707Z"},"content_sha256":"5309a21e5f22bf0ba92ea521ea5c072ce284a23242089c2c6d24ed561a70d1b0","schema_version":"1.0","event_id":"sha256:5309a21e5f22bf0ba92ea521ea5c072ce284a23242089c2c6d24ed561a70d1b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TCJ6EJPLYXXFDHJK4GMPRJRLA3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regression-aware Inference with LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aditya Krishna Menon, Felix Yu, Harikrishna Narasimhan, Michal Lukasik, Sanjiv Kumar","submitted_at":"2024-03-07T03:24:34Z","abstract_excerpt":"Large language models (LLMs) have shown strong results on a range of applications, including regression and scoring tasks. Typically, one obtains outputs from an LLM via autoregressive sampling from the model's output distribution. We show that this inference strategy can be sub-optimal for common regression and scoring evaluation metrics. As a remedy, we build on prior work on Minimum Bayes Risk decoding, and propose alternate inference strategies that estimate the Bayes-optimal solution for regression and scoring metrics in closed-form from sampled responses. We show that our proposal signif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04182","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/2403.04182/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":"2026-07-05T09:29:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f9qMb0NTEYyvvT26iP9MSNpaSYZBqKdaBDCFMCyceGKhndvacT3qeqI0v3HDFsoXZ4qzIEsV5d1hnbHbXc0wAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:10:06.049016Z"},"content_sha256":"1668ccfff9659e0db6c928aba417ea20483a7ef1ddadc56ffbf8653068c1e80d","schema_version":"1.0","event_id":"sha256:1668ccfff9659e0db6c928aba417ea20483a7ef1ddadc56ffbf8653068c1e80d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TCJ6EJPLYXXFDHJK4GMPRJRLA3/bundle.json","state_url":"https://pith.science/pith/TCJ6EJPLYXXFDHJK4GMPRJRLA3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TCJ6EJPLYXXFDHJK4GMPRJRLA3/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":"2026-08-14T08:10:06Z","links":{"resolver":"https://pith.science/pith/TCJ6EJPLYXXFDHJK4GMPRJRLA3","bundle":"https://pith.science/pith/TCJ6EJPLYXXFDHJK4GMPRJRLA3/bundle.json","state":"https://pith.science/pith/TCJ6EJPLYXXFDHJK4GMPRJRLA3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TCJ6EJPLYXXFDHJK4GMPRJRLA3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TCJ6EJPLYXXFDHJK4GMPRJRLA3","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":"241691244a2578cf98035cb005fd947d060e7b86fceb1c5fda7e2f3834736fae","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-07T03:24:34Z","title_canon_sha256":"742d8176775b3dc2fbe491a0125c80c6288cb2b86b4c6f80e8de4fe62442a991"},"schema_version":"1.0","source":{"id":"2403.04182","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.04182","created_at":"2026-07-05T09:29:26Z"},{"alias_kind":"arxiv_version","alias_value":"2403.04182v3","created_at":"2026-07-05T09:29:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04182","created_at":"2026-07-05T09:29:26Z"},{"alias_kind":"pith_short_12","alias_value":"TCJ6EJPLYXXF","created_at":"2026-07-05T09:29:26Z"},{"alias_kind":"pith_short_16","alias_value":"TCJ6EJPLYXXFDHJK","created_at":"2026-07-05T09:29:26Z"},{"alias_kind":"pith_short_8","alias_value":"TCJ6EJPL","created_at":"2026-07-05T09:29:26Z"}],"graph_snapshots":[{"event_id":"sha256:1668ccfff9659e0db6c928aba417ea20483a7ef1ddadc56ffbf8653068c1e80d","target":"graph","created_at":"2026-07-05T09:29:26Z","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/2403.04182/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown strong results on a range of applications, including regression and scoring tasks. Typically, one obtains outputs from an LLM via autoregressive sampling from the model's output distribution. We show that this inference strategy can be sub-optimal for common regression and scoring evaluation metrics. As a remedy, we build on prior work on Minimum Bayes Risk decoding, and propose alternate inference strategies that estimate the Bayes-optimal solution for regression and scoring metrics in closed-form from sampled responses. We show that our proposal signif","authors_text":"Aditya Krishna Menon, Felix Yu, Harikrishna Narasimhan, Michal Lukasik, Sanjiv Kumar","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-07T03:24:34Z","title":"Regression-aware Inference with LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04182","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":"sha256:5309a21e5f22bf0ba92ea521ea5c072ce284a23242089c2c6d24ed561a70d1b0","target":"record","created_at":"2026-07-05T09:29:26Z","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":"241691244a2578cf98035cb005fd947d060e7b86fceb1c5fda7e2f3834736fae","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-07T03:24:34Z","title_canon_sha256":"742d8176775b3dc2fbe491a0125c80c6288cb2b86b4c6f80e8de4fe62442a991"},"schema_version":"1.0","source":{"id":"2403.04182","kind":"arxiv","version":3}},"canonical_sha256":"9893e225ebc5ee519d2ae198f8a62b06f34865b6bc21aecbaef65bb5254db0c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9893e225ebc5ee519d2ae198f8a62b06f34865b6bc21aecbaef65bb5254db0c4","first_computed_at":"2026-07-05T09:29:26.842606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:26.842606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bRHk7dopmXM9uacBozAo79iyQNQdfN5oXbWs2CmLpg12EHFkX2jRqSFKcr7dLkcz3+oXu9qSGCpvh1jTCFtmDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:26.843119Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.04182","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5309a21e5f22bf0ba92ea521ea5c072ce284a23242089c2c6d24ed561a70d1b0","sha256:1668ccfff9659e0db6c928aba417ea20483a7ef1ddadc56ffbf8653068c1e80d"],"state_sha256":"de11720823ca4b2311957589e9e03dbc17c77c8ddc6d0c3f50a26ec7b2970476"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Di1XjyuBptOLY+W96+HiQ+PBG6pTj0YyP7TvyMhYJO/sXvvpJXuhVuP8F0po2mlj8ODIndZf7Sz2XlZC9GoPBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T08:10:06.051250Z","bundle_sha256":"fb9697f814378e4aeb3fc68a2b30465545a83d77939138353423256f1c49691c"}}