{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LJNLCYJGBDGVHYNMC75CACBHWD","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":"241fe045c600f9836224c56d8778880ef40ff327cb9514b58978b2fe2998e984","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T06:56:54Z","title_canon_sha256":"175b6e7345324165af029bea5ffa6bbe751d4d77d6ac871c5f1fa5c2863937a7"},"schema_version":"1.0","source":{"id":"2407.16221","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.16221","created_at":"2026-07-05T09:10:48Z"},{"alias_kind":"arxiv_version","alias_value":"2407.16221v2","created_at":"2026-07-05T09:10:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16221","created_at":"2026-07-05T09:10:48Z"},{"alias_kind":"pith_short_12","alias_value":"LJNLCYJGBDGV","created_at":"2026-07-05T09:10:48Z"},{"alias_kind":"pith_short_16","alias_value":"LJNLCYJGBDGVHYNM","created_at":"2026-07-05T09:10:48Z"},{"alias_kind":"pith_short_8","alias_value":"LJNLCYJG","created_at":"2026-07-05T09:10:48Z"}],"graph_snapshots":[{"event_id":"sha256:af1ce4e46ca7ee13ec31149b4e56b1d958f2800c68f18ff35f72b22d97c039bf","target":"graph","created_at":"2026-07-05T09:10:48Z","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/2407.16221/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Abstention Ability (AA) is a critical aspect of Large Language Model (LLM) reliability, referring to an LLM's capability to withhold responses when uncertain or lacking a definitive answer, without compromising performance. Although previous studies have attempted to improve AA, they lack a standardised evaluation method and remain unsuitable for black-box models where token prediction probabilities are inaccessible. This makes comparative analysis challenging, especially for state-of-the-art closed-source commercial LLMs. This paper bridges this gap by introducing a black-box evaluation appro","authors_text":"Masoud Hashemi, Nishanth Madhusudhan, Sathwik Tejaswi Madhusudhan, Vikas Yadav","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T06:56:54Z","title":"Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16221","kind":"arxiv","version":2},"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:ba8d6d6bcb3d80e3e27599d29a6ef5f9f52fec80112a10d0db05d20f4b6e9103","target":"record","created_at":"2026-07-05T09:10:48Z","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":"241fe045c600f9836224c56d8778880ef40ff327cb9514b58978b2fe2998e984","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T06:56:54Z","title_canon_sha256":"175b6e7345324165af029bea5ffa6bbe751d4d77d6ac871c5f1fa5c2863937a7"},"schema_version":"1.0","source":{"id":"2407.16221","kind":"arxiv","version":2}},"canonical_sha256":"5a5ab1612608cd53e1ac17fa200827b0ed8fa8f801d97a9fe8045d1d0dbe42c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a5ab1612608cd53e1ac17fa200827b0ed8fa8f801d97a9fe8045d1d0dbe42c3","first_computed_at":"2026-07-05T09:10:48.992157Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:48.992157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"idxZFx66AcVDBEDi31j6/rsrBs862sDD+pcubF4/NauWifpmJR4DSAU9s2qJXsfbvB6m1k2hsjewDaJtHmLLAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:48.992692Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.16221","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba8d6d6bcb3d80e3e27599d29a6ef5f9f52fec80112a10d0db05d20f4b6e9103","sha256:af1ce4e46ca7ee13ec31149b4e56b1d958f2800c68f18ff35f72b22d97c039bf"],"state_sha256":"5a1d1ad9da51f2004e113dd012f629e93f2acf132926dd70bbd7e6b3314c67b7"}