{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:USGW3XWWVYOOI4K6WBWWM7Q37H","short_pith_number":"pith:USGW3XWW","canonical_record":{"source":{"id":"2503.05757","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-22T10:48:18Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0bf4d7d4997fe22199e2c1987ef0f702569588fa1ee6c1df56666624bdbf4d6c","abstract_canon_sha256":"b53bc2e3119f30b6fe71b56ffd2498102e6663eed9abc1afe3bda1616f351bef"},"schema_version":"1.0"},"canonical_sha256":"a48d6dded6ae1ce4715eb06d667e1bf9e9b5a57d058806574eeae55e7955ab22","source":{"kind":"arxiv","id":"2503.05757","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.05757","created_at":"2026-07-05T10:26:46Z"},{"alias_kind":"arxiv_version","alias_value":"2503.05757v1","created_at":"2026-07-05T10:26:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05757","created_at":"2026-07-05T10:26:46Z"},{"alias_kind":"pith_short_12","alias_value":"USGW3XWWVYOO","created_at":"2026-07-05T10:26:46Z"},{"alias_kind":"pith_short_16","alias_value":"USGW3XWWVYOOI4K6","created_at":"2026-07-05T10:26:46Z"},{"alias_kind":"pith_short_8","alias_value":"USGW3XWW","created_at":"2026-07-05T10:26:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:USGW3XWWVYOOI4K6WBWWM7Q37H","target":"record","payload":{"canonical_record":{"source":{"id":"2503.05757","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-22T10:48:18Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0bf4d7d4997fe22199e2c1987ef0f702569588fa1ee6c1df56666624bdbf4d6c","abstract_canon_sha256":"b53bc2e3119f30b6fe71b56ffd2498102e6663eed9abc1afe3bda1616f351bef"},"schema_version":"1.0"},"canonical_sha256":"a48d6dded6ae1ce4715eb06d667e1bf9e9b5a57d058806574eeae55e7955ab22","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:46.186667Z","signature_b64":"tS55ZAfYBr8VnzBY3cUA/27KjZEyUpqddvcHviWON44/7Hap+Kx3iSuVqPvEj9CN2YeVhBp04tizD+1F5PNODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a48d6dded6ae1ce4715eb06d667e1bf9e9b5a57d058806574eeae55e7955ab22","last_reissued_at":"2026-07-05T10:26:46.186239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:46.186239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.05757","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":"2026-07-05T10:26:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EE5PppkfFhYrTS+sOtZfaKx0uQkUqOw5mTF5cQPfLC1pWiz5sOsTju/tgkP6nSbeA2do43vI+SsyMQbkpT3KAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:40:33.902330Z"},"content_sha256":"166de53d156b5d209776fa3d90120960309e9249b409192074a50efa013a21eb","schema_version":"1.0","event_id":"sha256:166de53d156b5d209776fa3d90120960309e9249b409192074a50efa013a21eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:USGW3XWWVYOOI4K6WBWWM7Q37H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uncertainty-Aware Fusion: An Ensemble Framework for Mitigating Hallucinations in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Prasenjit Dey, Sivaramakrishnan Kaveri, Srujana Merugu","submitted_at":"2025-02-22T10:48:18Z","abstract_excerpt":"Large Language Models (LLMs) are known to hallucinate and generate non-factual outputs which can undermine user trust. Traditional methods to directly mitigate hallucinations, such as representation editing and contrastive decoding, often require additional training data and involve high implementation complexity. While ensemble-based approaches harness multiple LLMs to tap into the \"wisdom of crowds\", these methods overlook uncertainties in individual model responses. Recent studies reveal that uncertainty estimation can enable LLMs to self-assess the likelihood of generating hallucinations. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05757","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/2503.05757/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":"2026-07-05T10:26:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MyRBl3QEgvsG6ItYhglJyEc/BzDBCIjX8j9se/weqv29xTIQcQeCRaRE/6mH74W5oUmH6XdO/Crq2bC5D9S0BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:40:33.902830Z"},"content_sha256":"c78160506a51f5576b40a8403e361406204bd34c9a3a780a9190836578f0f436","schema_version":"1.0","event_id":"sha256:c78160506a51f5576b40a8403e361406204bd34c9a3a780a9190836578f0f436"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/USGW3XWWVYOOI4K6WBWWM7Q37H/bundle.json","state_url":"https://pith.science/pith/USGW3XWWVYOOI4K6WBWWM7Q37H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/USGW3XWWVYOOI4K6WBWWM7Q37H/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":"2026-08-09T02:40:33Z","links":{"resolver":"https://pith.science/pith/USGW3XWWVYOOI4K6WBWWM7Q37H","bundle":"https://pith.science/pith/USGW3XWWVYOOI4K6WBWWM7Q37H/bundle.json","state":"https://pith.science/pith/USGW3XWWVYOOI4K6WBWWM7Q37H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/USGW3XWWVYOOI4K6WBWWM7Q37H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:USGW3XWWVYOOI4K6WBWWM7Q37H","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":"b53bc2e3119f30b6fe71b56ffd2498102e6663eed9abc1afe3bda1616f351bef","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-22T10:48:18Z","title_canon_sha256":"0bf4d7d4997fe22199e2c1987ef0f702569588fa1ee6c1df56666624bdbf4d6c"},"schema_version":"1.0","source":{"id":"2503.05757","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.05757","created_at":"2026-07-05T10:26:46Z"},{"alias_kind":"arxiv_version","alias_value":"2503.05757v1","created_at":"2026-07-05T10:26:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05757","created_at":"2026-07-05T10:26:46Z"},{"alias_kind":"pith_short_12","alias_value":"USGW3XWWVYOO","created_at":"2026-07-05T10:26:46Z"},{"alias_kind":"pith_short_16","alias_value":"USGW3XWWVYOOI4K6","created_at":"2026-07-05T10:26:46Z"},{"alias_kind":"pith_short_8","alias_value":"USGW3XWW","created_at":"2026-07-05T10:26:46Z"}],"graph_snapshots":[{"event_id":"sha256:c78160506a51f5576b40a8403e361406204bd34c9a3a780a9190836578f0f436","target":"graph","created_at":"2026-07-05T10:26:46Z","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/2503.05757/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are known to hallucinate and generate non-factual outputs which can undermine user trust. Traditional methods to directly mitigate hallucinations, such as representation editing and contrastive decoding, often require additional training data and involve high implementation complexity. While ensemble-based approaches harness multiple LLMs to tap into the \"wisdom of crowds\", these methods overlook uncertainties in individual model responses. Recent studies reveal that uncertainty estimation can enable LLMs to self-assess the likelihood of generating hallucinations. ","authors_text":"Prasenjit Dey, Sivaramakrishnan Kaveri, Srujana Merugu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-22T10:48:18Z","title":"Uncertainty-Aware Fusion: An Ensemble Framework for Mitigating Hallucinations in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05757","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":"sha256:166de53d156b5d209776fa3d90120960309e9249b409192074a50efa013a21eb","target":"record","created_at":"2026-07-05T10:26:46Z","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":"b53bc2e3119f30b6fe71b56ffd2498102e6663eed9abc1afe3bda1616f351bef","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-22T10:48:18Z","title_canon_sha256":"0bf4d7d4997fe22199e2c1987ef0f702569588fa1ee6c1df56666624bdbf4d6c"},"schema_version":"1.0","source":{"id":"2503.05757","kind":"arxiv","version":1}},"canonical_sha256":"a48d6dded6ae1ce4715eb06d667e1bf9e9b5a57d058806574eeae55e7955ab22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a48d6dded6ae1ce4715eb06d667e1bf9e9b5a57d058806574eeae55e7955ab22","first_computed_at":"2026-07-05T10:26:46.186239Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:26:46.186239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tS55ZAfYBr8VnzBY3cUA/27KjZEyUpqddvcHviWON44/7Hap+Kx3iSuVqPvEj9CN2YeVhBp04tizD+1F5PNODA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:26:46.186667Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.05757","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:166de53d156b5d209776fa3d90120960309e9249b409192074a50efa013a21eb","sha256:c78160506a51f5576b40a8403e361406204bd34c9a3a780a9190836578f0f436"],"state_sha256":"c34b1d92552693808a66b516c2b68a7c4ff7ee4d878da133ac01c48567821e3a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z6/2cxNr/Vyx1Dd/BmL7UIv8EOpq3Be3TjQekLQRXJkPfipwSaI0aNHCoarmw8izwY9E+OhTYR2Wt37c7a+tBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T02:40:33.907154Z","bundle_sha256":"b96d08d56b0c39f0b04a3e1e3452f748805ea0b99e89708e0307fd7e76abe1b1"}}