{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YO66GPDNNE5ZSEGHPIJUDCJ5Y6","short_pith_number":"pith:YO66GPDN","canonical_record":{"source":{"id":"2312.15576","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-25T01:17:01Z","cross_cats_sorted":[],"title_canon_sha256":"988ba22f5d623b503e8df045b2075a3c2d47caa4b26b74880522ca74e15683f3","abstract_canon_sha256":"fa5e9a240782144ce9093a79c7a0760e66968f668bd241ea47af110b9d1be5fc"},"schema_version":"1.0"},"canonical_sha256":"c3bde33c6d693b9910c77a1341893dc7a13cfe766e19c102baf28d1a9c82827c","source":{"kind":"arxiv","id":"2312.15576","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.15576","created_at":"2026-07-05T07:27:58Z"},{"alias_kind":"arxiv_version","alias_value":"2312.15576v1","created_at":"2026-07-05T07:27:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15576","created_at":"2026-07-05T07:27:58Z"},{"alias_kind":"pith_short_12","alias_value":"YO66GPDNNE5Z","created_at":"2026-07-05T07:27:58Z"},{"alias_kind":"pith_short_16","alias_value":"YO66GPDNNE5ZSEGH","created_at":"2026-07-05T07:27:58Z"},{"alias_kind":"pith_short_8","alias_value":"YO66GPDN","created_at":"2026-07-05T07:27:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YO66GPDNNE5ZSEGHPIJUDCJ5Y6","target":"record","payload":{"canonical_record":{"source":{"id":"2312.15576","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-25T01:17:01Z","cross_cats_sorted":[],"title_canon_sha256":"988ba22f5d623b503e8df045b2075a3c2d47caa4b26b74880522ca74e15683f3","abstract_canon_sha256":"fa5e9a240782144ce9093a79c7a0760e66968f668bd241ea47af110b9d1be5fc"},"schema_version":"1.0"},"canonical_sha256":"c3bde33c6d693b9910c77a1341893dc7a13cfe766e19c102baf28d1a9c82827c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:58.284088Z","signature_b64":"A3RLLXiw6jW6X9F6bYGtnFYZVIVgCaIrHEoooKIn3EgYffIuSgmJfBW8vtYNUFCjS0buNNRjJQK+0XDuZNFqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3bde33c6d693b9910c77a1341893dc7a13cfe766e19c102baf28d1a9c82827c","last_reissued_at":"2026-07-05T07:27:58.283646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:58.283646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.15576","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":"2026-07-05T07:27:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FxgW3dtuZ0LoRmsvRsb7uNPwPwabOxeQ70DbwwPrkCSIXl5cVaYxfLt1vAp4TS+EVGRkhmNBgyjnxgaTO6asCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:04:21.820715Z"},"content_sha256":"fb197561c7daeea7591e24c7f87c3617952a5ada572528f2475abb6c5ed542ce","schema_version":"1.0","event_id":"sha256:fb197561c7daeea7591e24c7f87c3617952a5ada572528f2475abb6c5ed542ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YO66GPDNNE5ZSEGHPIJUDCJ5Y6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reducing LLM Hallucinations using Epistemic Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guangyu Min, Kien Tran, Shreyas Verma, Yusuf Ali","submitted_at":"2023-12-25T01:17:01Z","abstract_excerpt":"Reducing and detecting hallucinations in large language models is an open research problem. In this project, we attempt to leverage recent advances in the field of uncertainty estimation to reduce hallucinations in frozen large language models. Epistemic neural networks have recently been proposed to improve output joint distributions for large pre-trained models. ENNs are small networks attached to large, frozen models to improve the model's joint distributions and uncertainty estimates. In this work, we train an epistemic neural network on top of the Llama-2 7B model combined with a contrast"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15576","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/2312.15576/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":"2026-07-05T07:27:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jkQefdUpi7qLQLV0wvxSEuk6vs4XQcKmz0NQCYaaHpfbwBP+YZYjmbF0/aJZdVI7abQoDPiyWZXwBUkPsjUcAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:04:21.821233Z"},"content_sha256":"4c844c29a53ff9b53ad8e6a0ac7052097dadc127175f47b2ed5ad34783ffc6fe","schema_version":"1.0","event_id":"sha256:4c844c29a53ff9b53ad8e6a0ac7052097dadc127175f47b2ed5ad34783ffc6fe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YO66GPDNNE5ZSEGHPIJUDCJ5Y6/bundle.json","state_url":"https://pith.science/pith/YO66GPDNNE5ZSEGHPIJUDCJ5Y6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YO66GPDNNE5ZSEGHPIJUDCJ5Y6/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":"2026-08-09T21:04:21Z","links":{"resolver":"https://pith.science/pith/YO66GPDNNE5ZSEGHPIJUDCJ5Y6","bundle":"https://pith.science/pith/YO66GPDNNE5ZSEGHPIJUDCJ5Y6/bundle.json","state":"https://pith.science/pith/YO66GPDNNE5ZSEGHPIJUDCJ5Y6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YO66GPDNNE5ZSEGHPIJUDCJ5Y6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YO66GPDNNE5ZSEGHPIJUDCJ5Y6","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":"fa5e9a240782144ce9093a79c7a0760e66968f668bd241ea47af110b9d1be5fc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-25T01:17:01Z","title_canon_sha256":"988ba22f5d623b503e8df045b2075a3c2d47caa4b26b74880522ca74e15683f3"},"schema_version":"1.0","source":{"id":"2312.15576","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.15576","created_at":"2026-07-05T07:27:58Z"},{"alias_kind":"arxiv_version","alias_value":"2312.15576v1","created_at":"2026-07-05T07:27:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15576","created_at":"2026-07-05T07:27:58Z"},{"alias_kind":"pith_short_12","alias_value":"YO66GPDNNE5Z","created_at":"2026-07-05T07:27:58Z"},{"alias_kind":"pith_short_16","alias_value":"YO66GPDNNE5ZSEGH","created_at":"2026-07-05T07:27:58Z"},{"alias_kind":"pith_short_8","alias_value":"YO66GPDN","created_at":"2026-07-05T07:27:58Z"}],"graph_snapshots":[{"event_id":"sha256:4c844c29a53ff9b53ad8e6a0ac7052097dadc127175f47b2ed5ad34783ffc6fe","target":"graph","created_at":"2026-07-05T07:27:58Z","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/2312.15576/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reducing and detecting hallucinations in large language models is an open research problem. In this project, we attempt to leverage recent advances in the field of uncertainty estimation to reduce hallucinations in frozen large language models. Epistemic neural networks have recently been proposed to improve output joint distributions for large pre-trained models. ENNs are small networks attached to large, frozen models to improve the model's joint distributions and uncertainty estimates. In this work, we train an epistemic neural network on top of the Llama-2 7B model combined with a contrast","authors_text":"Guangyu Min, Kien Tran, Shreyas Verma, Yusuf Ali","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-25T01:17:01Z","title":"Reducing LLM Hallucinations using Epistemic Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15576","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:fb197561c7daeea7591e24c7f87c3617952a5ada572528f2475abb6c5ed542ce","target":"record","created_at":"2026-07-05T07:27:58Z","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":"fa5e9a240782144ce9093a79c7a0760e66968f668bd241ea47af110b9d1be5fc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-25T01:17:01Z","title_canon_sha256":"988ba22f5d623b503e8df045b2075a3c2d47caa4b26b74880522ca74e15683f3"},"schema_version":"1.0","source":{"id":"2312.15576","kind":"arxiv","version":1}},"canonical_sha256":"c3bde33c6d693b9910c77a1341893dc7a13cfe766e19c102baf28d1a9c82827c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3bde33c6d693b9910c77a1341893dc7a13cfe766e19c102baf28d1a9c82827c","first_computed_at":"2026-07-05T07:27:58.283646Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:27:58.283646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A3RLLXiw6jW6X9F6bYGtnFYZVIVgCaIrHEoooKIn3EgYffIuSgmJfBW8vtYNUFCjS0buNNRjJQK+0XDuZNFqAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:27:58.284088Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.15576","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb197561c7daeea7591e24c7f87c3617952a5ada572528f2475abb6c5ed542ce","sha256:4c844c29a53ff9b53ad8e6a0ac7052097dadc127175f47b2ed5ad34783ffc6fe"],"state_sha256":"fd8c813e4545e31fceb028d25b326d096bd4a1d68e24d7a83eb03898437fbb56"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gh1SRUp3HJKXfEOuec2tCbu4xDG+4HViQhz3oJZAJNIobmABNOA9leij+yNdsNRpddMW5gYxtLLXQS17LiZ9Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T21:04:21.824985Z","bundle_sha256":"ab0dc6ebca74e7f8b37ca0ecee9b7670f79d644213ed9bd629d4c8130f86d72e"}}