{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4YWBXKTBCI47W263AFIHJRNHW7","short_pith_number":"pith:4YWBXKTB","canonical_record":{"source":{"id":"2606.19868","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-18T07:27:34Z","cross_cats_sorted":[],"title_canon_sha256":"86854dacec9d650466eef41f77e833850d175ee67269a24bb52242bc9f88ad08","abstract_canon_sha256":"2733b73cca97f518b926f9badb7d44472324dd557450e0879fae370f01199511"},"schema_version":"1.0"},"canonical_sha256":"e62c1baa611239fb6bdb015074c5a7b7d0c800d22afaa6ad379361b5489f9198","source":{"kind":"arxiv","id":"2606.19868","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19868","created_at":"2026-06-19T16:12:37Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19868v1","created_at":"2026-06-19T16:12:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19868","created_at":"2026-06-19T16:12:37Z"},{"alias_kind":"pith_short_12","alias_value":"4YWBXKTBCI47","created_at":"2026-06-19T16:12:37Z"},{"alias_kind":"pith_short_16","alias_value":"4YWBXKTBCI47W263","created_at":"2026-06-19T16:12:37Z"},{"alias_kind":"pith_short_8","alias_value":"4YWBXKTB","created_at":"2026-06-19T16:12:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4YWBXKTBCI47W263AFIHJRNHW7","target":"record","payload":{"canonical_record":{"source":{"id":"2606.19868","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-18T07:27:34Z","cross_cats_sorted":[],"title_canon_sha256":"86854dacec9d650466eef41f77e833850d175ee67269a24bb52242bc9f88ad08","abstract_canon_sha256":"2733b73cca97f518b926f9badb7d44472324dd557450e0879fae370f01199511"},"schema_version":"1.0"},"canonical_sha256":"e62c1baa611239fb6bdb015074c5a7b7d0c800d22afaa6ad379361b5489f9198","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:37.355495Z","signature_b64":"HcTNXg/ms5cBp4Qde3x4M09nx8xrf2zREhG2rgOmv6RuUPVVEOSBoem7UesK+zbEhmJ2sq1LO36j43c/zxnbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e62c1baa611239fb6bdb015074c5a7b7d0c800d22afaa6ad379361b5489f9198","last_reissued_at":"2026-06-19T16:12:37.355124Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:37.355124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.19868","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":"2026-06-19T16:12:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xrbGPt/qiGxhnInaqh8iVU7G+jVBURX/vAlKJyuwf+tFIzxaTi/395IdMRpjLBKiRPPrpEHjL+JOO69JkAf2Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T11:01:22.383307Z"},"content_sha256":"157f5e50c75b6a02e7b57fb561450797fc694e52386939ce1a3cf27e1f6e12fe","schema_version":"1.0","event_id":"sha256:157f5e50c75b6a02e7b57fb561450797fc694e52386939ce1a3cf27e1f6e12fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4YWBXKTBCI47W263AFIHJRNHW7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Systematic Evaluation of Black-Box Uncertainty Estimation Methods for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiayi Wang, Xu-Yao Zhang","submitted_at":"2026-06-18T07:27:34Z","abstract_excerpt":"Although large language models (LLMs) have shown strong capabilities across a wide range of tasks, their outputs often remain unreliable and may contain hallucinations, making uncertainty estimation (UE) essential for building trustworthy LLMs. In practice, many mainstream LLMs are only accessible through restricted APIs, where internal signals such as logits and hidden states are unavailable, making black-box UE especially important. However, existing work on black-box UE for LLMs remains fragmented in methodology and lacks a unified empirical comparison. To address this gap, we present a sys"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19868","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/2606.19868/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":"2026-06-19T16:12:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/7KORYCbTs2NzO5FyiAJ434gc+Evn4DHDEOY1ndRripF/xDQWdx3k2tPaTepvk6ymOJexInFrq49DQcvmVewAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T11:01:22.383713Z"},"content_sha256":"1bf5f759f8df851e77f905d060f0e13781e66282efd585ed4150c7493c87f831","schema_version":"1.0","event_id":"sha256:1bf5f759f8df851e77f905d060f0e13781e66282efd585ed4150c7493c87f831"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4YWBXKTBCI47W263AFIHJRNHW7/bundle.json","state_url":"https://pith.science/pith/4YWBXKTBCI47W263AFIHJRNHW7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4YWBXKTBCI47W263AFIHJRNHW7/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":"2026-07-04T11:01:22Z","links":{"resolver":"https://pith.science/pith/4YWBXKTBCI47W263AFIHJRNHW7","bundle":"https://pith.science/pith/4YWBXKTBCI47W263AFIHJRNHW7/bundle.json","state":"https://pith.science/pith/4YWBXKTBCI47W263AFIHJRNHW7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4YWBXKTBCI47W263AFIHJRNHW7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4YWBXKTBCI47W263AFIHJRNHW7","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":"2733b73cca97f518b926f9badb7d44472324dd557450e0879fae370f01199511","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-18T07:27:34Z","title_canon_sha256":"86854dacec9d650466eef41f77e833850d175ee67269a24bb52242bc9f88ad08"},"schema_version":"1.0","source":{"id":"2606.19868","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19868","created_at":"2026-06-19T16:12:37Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19868v1","created_at":"2026-06-19T16:12:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19868","created_at":"2026-06-19T16:12:37Z"},{"alias_kind":"pith_short_12","alias_value":"4YWBXKTBCI47","created_at":"2026-06-19T16:12:37Z"},{"alias_kind":"pith_short_16","alias_value":"4YWBXKTBCI47W263","created_at":"2026-06-19T16:12:37Z"},{"alias_kind":"pith_short_8","alias_value":"4YWBXKTB","created_at":"2026-06-19T16:12:37Z"}],"graph_snapshots":[{"event_id":"sha256:1bf5f759f8df851e77f905d060f0e13781e66282efd585ed4150c7493c87f831","target":"graph","created_at":"2026-06-19T16:12:37Z","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/2606.19868/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although large language models (LLMs) have shown strong capabilities across a wide range of tasks, their outputs often remain unreliable and may contain hallucinations, making uncertainty estimation (UE) essential for building trustworthy LLMs. In practice, many mainstream LLMs are only accessible through restricted APIs, where internal signals such as logits and hidden states are unavailable, making black-box UE especially important. However, existing work on black-box UE for LLMs remains fragmented in methodology and lacks a unified empirical comparison. To address this gap, we present a sys","authors_text":"Jiayi Wang, Xu-Yao Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-18T07:27:34Z","title":"A Systematic Evaluation of Black-Box Uncertainty Estimation Methods for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19868","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":"sha256:157f5e50c75b6a02e7b57fb561450797fc694e52386939ce1a3cf27e1f6e12fe","target":"record","created_at":"2026-06-19T16:12:37Z","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":"2733b73cca97f518b926f9badb7d44472324dd557450e0879fae370f01199511","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-18T07:27:34Z","title_canon_sha256":"86854dacec9d650466eef41f77e833850d175ee67269a24bb52242bc9f88ad08"},"schema_version":"1.0","source":{"id":"2606.19868","kind":"arxiv","version":1}},"canonical_sha256":"e62c1baa611239fb6bdb015074c5a7b7d0c800d22afaa6ad379361b5489f9198","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e62c1baa611239fb6bdb015074c5a7b7d0c800d22afaa6ad379361b5489f9198","first_computed_at":"2026-06-19T16:12:37.355124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:37.355124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HcTNXg/ms5cBp4Qde3x4M09nx8xrf2zREhG2rgOmv6RuUPVVEOSBoem7UesK+zbEhmJ2sq1LO36j43c/zxnbAg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:37.355495Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19868","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:157f5e50c75b6a02e7b57fb561450797fc694e52386939ce1a3cf27e1f6e12fe","sha256:1bf5f759f8df851e77f905d060f0e13781e66282efd585ed4150c7493c87f831"],"state_sha256":"34dc3c8bacef6ccc6d122913d5f32f75abb91eaeff6189e7b490191c78e9fba3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QMPiM4HhLnQUS2QUIk55kh9fGYMPDGSHb2p78VmXch8LXajc3tNU7OY8DGwp/akTDFzRwMhulo8fbDjWesKMCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T11:01:22.385716Z","bundle_sha256":"619674a8f080054b36e1f041fb895a195ce7233a80b4f0871ba5fb08cd4e50c6"}}