{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5J4277FJO3LYJBBFVNWGDZB7DO","short_pith_number":"pith:5J4277FJ","canonical_record":{"source":{"id":"2506.09038","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-10T17:57:30Z","cross_cats_sorted":[],"title_canon_sha256":"78ee2fdf094f88ac736853006dbc14a0e87178f3e2d4740f0231fd88c4f31f7f","abstract_canon_sha256":"eb053ef42e49bcb74b9f35ac96a1605dd4e8baaf4fed3d75b820f7ff8c6085a6"},"schema_version":"1.0"},"canonical_sha256":"ea79affca976d7848425ab6c61e43f1bb3281ff46fe24501cb5d7b09ddb12c55","source":{"kind":"arxiv","id":"2506.09038","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.09038","created_at":"2026-07-05T11:19:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.09038v1","created_at":"2026-07-05T11:19:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09038","created_at":"2026-07-05T11:19:16Z"},{"alias_kind":"pith_short_12","alias_value":"5J4277FJO3LY","created_at":"2026-07-05T11:19:16Z"},{"alias_kind":"pith_short_16","alias_value":"5J4277FJO3LYJBBF","created_at":"2026-07-05T11:19:16Z"},{"alias_kind":"pith_short_8","alias_value":"5J4277FJ","created_at":"2026-07-05T11:19:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5J4277FJO3LYJBBFVNWGDZB7DO","target":"record","payload":{"canonical_record":{"source":{"id":"2506.09038","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-10T17:57:30Z","cross_cats_sorted":[],"title_canon_sha256":"78ee2fdf094f88ac736853006dbc14a0e87178f3e2d4740f0231fd88c4f31f7f","abstract_canon_sha256":"eb053ef42e49bcb74b9f35ac96a1605dd4e8baaf4fed3d75b820f7ff8c6085a6"},"schema_version":"1.0"},"canonical_sha256":"ea79affca976d7848425ab6c61e43f1bb3281ff46fe24501cb5d7b09ddb12c55","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:16.899136Z","signature_b64":"p/mHNqo6Lyjus3/FZsgjkWs9pDdOUSfEMUS27+BhltVeRwfDretFz6cEmnUrCPmNy5EUatOrKvaIs3yKnel/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea79affca976d7848425ab6c61e43f1bb3281ff46fe24501cb5d7b09ddb12c55","last_reissued_at":"2026-07-05T11:19:16.898646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:16.898646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.09038","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":"2026-07-05T11:19:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bMfns6sK6gDT89BsidZSDSZFxn0jrSU0xB459tm3ctghrwyxQOpcxS+zRNMIebwYWamGDIzsCcezdkipt4COAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:04:27.783505Z"},"content_sha256":"84cea50dcf4a6a261572a5d90faa438b19938fc2257717b6872853eb67efac95","schema_version":"1.0","event_id":"sha256:84cea50dcf4a6a261572a5d90faa438b19938fc2257717b6872853eb67efac95"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5J4277FJO3LYJBBFVNWGDZB7DO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Kamalika Chaudhuri, Mark Ibrahim, Polina Kirichenko, Samuel J. Bell","submitted_at":"2025-06-10T17:57:30Z","abstract_excerpt":"For Large Language Models (LLMs) to be reliably deployed in both everyday and high-stakes domains, knowing when not to answer is equally critical as answering correctly. Real-world user queries, which can be underspecified, ill-posed, or fundamentally unanswerable, require LLMs to reason about uncertainty and selectively abstain -- i.e., refuse to answer definitively. However, abstention remains understudied, without a systematic evaluation framework for modern LLMs. In this work, we introduce AbstentionBench, a large-scale benchmark for holistically evaluating abstention across 20 diverse dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09038","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/2506.09038/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":"2026-07-05T11:19:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hMIMOysWT0bOGcUd2Y+Fdbyf/47Um23dBlXROSqm+OJWU3dVLYwM9bDWlkf64Dg/T+SiEzZIXMmd9zX+GBbIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:04:27.784058Z"},"content_sha256":"c3cc899b4da0f40456fd962b79b5b5d359bf75c17a688502f19fd9c9a68eb9f0","schema_version":"1.0","event_id":"sha256:c3cc899b4da0f40456fd962b79b5b5d359bf75c17a688502f19fd9c9a68eb9f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5J4277FJO3LYJBBFVNWGDZB7DO/bundle.json","state_url":"https://pith.science/pith/5J4277FJO3LYJBBFVNWGDZB7DO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5J4277FJO3LYJBBFVNWGDZB7DO/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":"2026-08-04T21:04:27Z","links":{"resolver":"https://pith.science/pith/5J4277FJO3LYJBBFVNWGDZB7DO","bundle":"https://pith.science/pith/5J4277FJO3LYJBBFVNWGDZB7DO/bundle.json","state":"https://pith.science/pith/5J4277FJO3LYJBBFVNWGDZB7DO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5J4277FJO3LYJBBFVNWGDZB7DO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5J4277FJO3LYJBBFVNWGDZB7DO","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":"eb053ef42e49bcb74b9f35ac96a1605dd4e8baaf4fed3d75b820f7ff8c6085a6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-10T17:57:30Z","title_canon_sha256":"78ee2fdf094f88ac736853006dbc14a0e87178f3e2d4740f0231fd88c4f31f7f"},"schema_version":"1.0","source":{"id":"2506.09038","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.09038","created_at":"2026-07-05T11:19:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.09038v1","created_at":"2026-07-05T11:19:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09038","created_at":"2026-07-05T11:19:16Z"},{"alias_kind":"pith_short_12","alias_value":"5J4277FJO3LY","created_at":"2026-07-05T11:19:16Z"},{"alias_kind":"pith_short_16","alias_value":"5J4277FJO3LYJBBF","created_at":"2026-07-05T11:19:16Z"},{"alias_kind":"pith_short_8","alias_value":"5J4277FJ","created_at":"2026-07-05T11:19:16Z"}],"graph_snapshots":[{"event_id":"sha256:c3cc899b4da0f40456fd962b79b5b5d359bf75c17a688502f19fd9c9a68eb9f0","target":"graph","created_at":"2026-07-05T11:19:16Z","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/2506.09038/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For Large Language Models (LLMs) to be reliably deployed in both everyday and high-stakes domains, knowing when not to answer is equally critical as answering correctly. Real-world user queries, which can be underspecified, ill-posed, or fundamentally unanswerable, require LLMs to reason about uncertainty and selectively abstain -- i.e., refuse to answer definitively. However, abstention remains understudied, without a systematic evaluation framework for modern LLMs. In this work, we introduce AbstentionBench, a large-scale benchmark for holistically evaluating abstention across 20 diverse dat","authors_text":"Kamalika Chaudhuri, Mark Ibrahim, Polina Kirichenko, Samuel J. Bell","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-10T17:57:30Z","title":"AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09038","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":"sha256:84cea50dcf4a6a261572a5d90faa438b19938fc2257717b6872853eb67efac95","target":"record","created_at":"2026-07-05T11:19:16Z","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":"eb053ef42e49bcb74b9f35ac96a1605dd4e8baaf4fed3d75b820f7ff8c6085a6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-10T17:57:30Z","title_canon_sha256":"78ee2fdf094f88ac736853006dbc14a0e87178f3e2d4740f0231fd88c4f31f7f"},"schema_version":"1.0","source":{"id":"2506.09038","kind":"arxiv","version":1}},"canonical_sha256":"ea79affca976d7848425ab6c61e43f1bb3281ff46fe24501cb5d7b09ddb12c55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea79affca976d7848425ab6c61e43f1bb3281ff46fe24501cb5d7b09ddb12c55","first_computed_at":"2026-07-05T11:19:16.898646Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:16.898646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p/mHNqo6Lyjus3/FZsgjkWs9pDdOUSfEMUS27+BhltVeRwfDretFz6cEmnUrCPmNy5EUatOrKvaIs3yKnel/Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:16.899136Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.09038","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84cea50dcf4a6a261572a5d90faa438b19938fc2257717b6872853eb67efac95","sha256:c3cc899b4da0f40456fd962b79b5b5d359bf75c17a688502f19fd9c9a68eb9f0"],"state_sha256":"6c6df714f112728fc00a15143fc1ec78430f8d1f546edfa8d58c5358608f9432"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o/9akpAt5Ifvzz3rkiG2UKCsRxNenB/EzvuUw97+orBNjkbTQcNBLFyH8CkJeXZ9bDA7ePejcIlwWrVo1XzbBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:04:27.787253Z","bundle_sha256":"b76055fd3714e93dab74bd9c4d758ddbac12040c010c9c401f5639b7da69ba52"}}