{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3EWGOOGZWU2ZSTPTS4QUPCGXNY","short_pith_number":"pith:3EWGOOGZ","canonical_record":{"source":{"id":"2310.03283","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T03:20:41Z","cross_cats_sorted":[],"title_canon_sha256":"86f4482451a54665c366c769c4177b264e1c694da87562854cee5d6255e6c3ba","abstract_canon_sha256":"496f55a112b07996260c9c8d9490f5a19de25e102633c098981c4dd5dbd81962"},"schema_version":"1.0"},"canonical_sha256":"d92c6738d9b535994df397214788d76e37642a4bcf471074b32187b8c0614ded","source":{"kind":"arxiv","id":"2310.03283","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03283","created_at":"2026-07-05T06:57:30Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03283v1","created_at":"2026-07-05T06:57:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03283","created_at":"2026-07-05T06:57:30Z"},{"alias_kind":"pith_short_12","alias_value":"3EWGOOGZWU2Z","created_at":"2026-07-05T06:57:30Z"},{"alias_kind":"pith_short_16","alias_value":"3EWGOOGZWU2ZSTPT","created_at":"2026-07-05T06:57:30Z"},{"alias_kind":"pith_short_8","alias_value":"3EWGOOGZ","created_at":"2026-07-05T06:57:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3EWGOOGZWU2ZSTPTS4QUPCGXNY","target":"record","payload":{"canonical_record":{"source":{"id":"2310.03283","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T03:20:41Z","cross_cats_sorted":[],"title_canon_sha256":"86f4482451a54665c366c769c4177b264e1c694da87562854cee5d6255e6c3ba","abstract_canon_sha256":"496f55a112b07996260c9c8d9490f5a19de25e102633c098981c4dd5dbd81962"},"schema_version":"1.0"},"canonical_sha256":"d92c6738d9b535994df397214788d76e37642a4bcf471074b32187b8c0614ded","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:30.995678Z","signature_b64":"VsAyL0byOm8m92UfKNLyeyUHIhcKTMsvMSN91PvcLlxhZDOrmuDcHnjbgLemkhXi4lf0jlN/aQW+KdIDItozDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d92c6738d9b535994df397214788d76e37642a4bcf471074b32187b8c0614ded","last_reissued_at":"2026-07-05T06:57:30.995074Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:30.995074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.03283","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":"2026-07-05T06:57:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tpAij8D4Olifnon+UR8cB1MnKinPm96fyMp20u5pf+n4m/OC1WAylhKma5OukDZdmAbi8/dNZBCTEZh7EaXFBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:16:03.628858Z"},"content_sha256":"3fe794ddc24a51b93a3e650fd8a9d22069d02d4a8f70156f4ab230b96e46cfe0","schema_version":"1.0","event_id":"sha256:3fe794ddc24a51b93a3e650fd8a9d22069d02d4a8f70156f4ab230b96e46cfe0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3EWGOOGZWU2ZSTPTS4QUPCGXNY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Formalism and Approach for Improving Robustness of Large Language Models Using Risk-Adjusted Confidence Scores","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ke Shen, Mayank Kejriwal","submitted_at":"2023-10-05T03:20:41Z","abstract_excerpt":"Large Language Models (LLMs), such as ChatGPT, have achieved impressive milestones in natural language processing (NLP). Despite their impressive performance, the models are known to pose important risks. As these models are deployed in real-world applications, a systematic understanding of different risks posed by these models on tasks such as natural language inference (NLI), is much needed. In this paper, we define and formalize two distinct types of risk: decision risk and composite risk. We also propose a risk-centric evaluation framework, and four novel metrics, for assessing LLMs on the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03283","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/2310.03283/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":"2026-07-05T06:57:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0K2nE4SvqxbSqR2ErJNZv4Le0a3XIL8UQ0tuIV+wSIHdSHLPYRdxtQVPfkKNtDy315YDPhETFVu37Gda3BH1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:16:03.629554Z"},"content_sha256":"7e461e2347a196ee634025ba55c695ef9fffa9767fc2c78faec05f9a2a928e04","schema_version":"1.0","event_id":"sha256:7e461e2347a196ee634025ba55c695ef9fffa9767fc2c78faec05f9a2a928e04"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3EWGOOGZWU2ZSTPTS4QUPCGXNY/bundle.json","state_url":"https://pith.science/pith/3EWGOOGZWU2ZSTPTS4QUPCGXNY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3EWGOOGZWU2ZSTPTS4QUPCGXNY/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":"2026-08-03T19:16:03Z","links":{"resolver":"https://pith.science/pith/3EWGOOGZWU2ZSTPTS4QUPCGXNY","bundle":"https://pith.science/pith/3EWGOOGZWU2ZSTPTS4QUPCGXNY/bundle.json","state":"https://pith.science/pith/3EWGOOGZWU2ZSTPTS4QUPCGXNY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3EWGOOGZWU2ZSTPTS4QUPCGXNY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3EWGOOGZWU2ZSTPTS4QUPCGXNY","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":"496f55a112b07996260c9c8d9490f5a19de25e102633c098981c4dd5dbd81962","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T03:20:41Z","title_canon_sha256":"86f4482451a54665c366c769c4177b264e1c694da87562854cee5d6255e6c3ba"},"schema_version":"1.0","source":{"id":"2310.03283","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03283","created_at":"2026-07-05T06:57:30Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03283v1","created_at":"2026-07-05T06:57:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03283","created_at":"2026-07-05T06:57:30Z"},{"alias_kind":"pith_short_12","alias_value":"3EWGOOGZWU2Z","created_at":"2026-07-05T06:57:30Z"},{"alias_kind":"pith_short_16","alias_value":"3EWGOOGZWU2ZSTPT","created_at":"2026-07-05T06:57:30Z"},{"alias_kind":"pith_short_8","alias_value":"3EWGOOGZ","created_at":"2026-07-05T06:57:30Z"}],"graph_snapshots":[{"event_id":"sha256:7e461e2347a196ee634025ba55c695ef9fffa9767fc2c78faec05f9a2a928e04","target":"graph","created_at":"2026-07-05T06:57:30Z","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/2310.03283/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs), such as ChatGPT, have achieved impressive milestones in natural language processing (NLP). Despite their impressive performance, the models are known to pose important risks. As these models are deployed in real-world applications, a systematic understanding of different risks posed by these models on tasks such as natural language inference (NLI), is much needed. In this paper, we define and formalize two distinct types of risk: decision risk and composite risk. We also propose a risk-centric evaluation framework, and four novel metrics, for assessing LLMs on the","authors_text":"Ke Shen, Mayank Kejriwal","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T03:20:41Z","title":"A Formalism and Approach for Improving Robustness of Large Language Models Using Risk-Adjusted Confidence Scores"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03283","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":"sha256:3fe794ddc24a51b93a3e650fd8a9d22069d02d4a8f70156f4ab230b96e46cfe0","target":"record","created_at":"2026-07-05T06:57:30Z","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":"496f55a112b07996260c9c8d9490f5a19de25e102633c098981c4dd5dbd81962","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T03:20:41Z","title_canon_sha256":"86f4482451a54665c366c769c4177b264e1c694da87562854cee5d6255e6c3ba"},"schema_version":"1.0","source":{"id":"2310.03283","kind":"arxiv","version":1}},"canonical_sha256":"d92c6738d9b535994df397214788d76e37642a4bcf471074b32187b8c0614ded","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d92c6738d9b535994df397214788d76e37642a4bcf471074b32187b8c0614ded","first_computed_at":"2026-07-05T06:57:30.995074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:57:30.995074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VsAyL0byOm8m92UfKNLyeyUHIhcKTMsvMSN91PvcLlxhZDOrmuDcHnjbgLemkhXi4lf0jlN/aQW+KdIDItozDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:57:30.995678Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.03283","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fe794ddc24a51b93a3e650fd8a9d22069d02d4a8f70156f4ab230b96e46cfe0","sha256:7e461e2347a196ee634025ba55c695ef9fffa9767fc2c78faec05f9a2a928e04"],"state_sha256":"92d620dc9cafe5d8b3e6420034e0427bdaef2670f9989c291978165446448e3f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hdMtVpZ+5cNkOnS/YeOP6Ifi1XdykwnKsu4IYfqblmlSYWZzMmv74q+4YetGX+H4n7wNl7eZTlDWp/YqBL6OCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:16:03.635333Z","bundle_sha256":"6f74ae02462d64fdbec1a2a0392531d8cd7466fca3076052965af04023bc2779"}}