{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UNZ27MAJCHJIQFIK2NBZ6WFTQW","short_pith_number":"pith:UNZ27MAJ","canonical_record":{"source":{"id":"2506.00064","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T13:52:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"da655a633dacebb33d928cb2a5ccbb91b48209f843fade1e0047ecbb2e5dd667","abstract_canon_sha256":"a0ed6b080c4d9262a99678e4515c7e13346fc9b49c8e685ff2633c6e58de8039"},"schema_version":"1.0"},"canonical_sha256":"a373afb00911d288150ad3439f58b3858da3b08423cbc8969acee1917c8731e2","source":{"kind":"arxiv","id":"2506.00064","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00064","created_at":"2026-07-05T11:13:28Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00064v1","created_at":"2026-07-05T11:13:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00064","created_at":"2026-07-05T11:13:28Z"},{"alias_kind":"pith_short_12","alias_value":"UNZ27MAJCHJI","created_at":"2026-07-05T11:13:28Z"},{"alias_kind":"pith_short_16","alias_value":"UNZ27MAJCHJIQFIK","created_at":"2026-07-05T11:13:28Z"},{"alias_kind":"pith_short_8","alias_value":"UNZ27MAJ","created_at":"2026-07-05T11:13:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UNZ27MAJCHJIQFIK2NBZ6WFTQW","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00064","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T13:52:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"da655a633dacebb33d928cb2a5ccbb91b48209f843fade1e0047ecbb2e5dd667","abstract_canon_sha256":"a0ed6b080c4d9262a99678e4515c7e13346fc9b49c8e685ff2633c6e58de8039"},"schema_version":"1.0"},"canonical_sha256":"a373afb00911d288150ad3439f58b3858da3b08423cbc8969acee1917c8731e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:28.382298Z","signature_b64":"ifob8ynC8iuCWRH5gTO8rJAUD1TeQR1iwGdz9fma9w2WBmSvTLIsOqLMqWP7IVShuisRJ34gWZaf+p2CHJUACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a373afb00911d288150ad3439f58b3858da3b08423cbc8969acee1917c8731e2","last_reissued_at":"2026-07-05T11:13:28.381809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:28.381809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00064","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":"2026-07-05T11:13:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TzDcTb6H5E3dBQq7LmXuUBTymBxSPpQik3tWUR5Bc6rV2K+19i7eijAEhB2BFmzGaFbxA1UdFqXMWfpq1t1gDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:12:06.802297Z"},"content_sha256":"1bcc397fe03a3935fbf91e345047230a0576ae5dc5ed11713fbb76cb400f5762","schema_version":"1.0","event_id":"sha256:1bcc397fe03a3935fbf91e345047230a0576ae5dc5ed11713fbb76cb400f5762"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UNZ27MAJCHJIQFIK2NBZ6WFTQW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mis-prompt: Benchmarking Large Language Models for Proactive Error Handling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aimin Zhou, Jiayi Zeng, Mengliang He, Wei Zhang, Wenhui Lei, Xiaoming Shi, Yizhe Feng, Zeming Liu","submitted_at":"2025-05-29T13:52:58Z","abstract_excerpt":"Large language models (LLMs) have demonstrated significant advancements in error handling. Current error-handling works are performed in a passive manner, with explicit error-handling instructions. However, in real-world scenarios, explicit error-handling instructions are usually unavailable. In this paper, our work identifies this challenge as how to conduct proactive error handling without explicit error handling instructions. To promote further research, this work introduces a new benchmark, termed Mis-prompt, consisting of four evaluation tasks, an error category taxonomy, and a new evalua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00064","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/2506.00064/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":"2026-07-05T11:13:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XyqZBgon9ZvEQxRoSvwfS4SDuKfrd9aM4eABgn41Dg3CKba/E9jFsCGTCDbol0wAAFCfVhSokjCIhWrabXZfBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:12:06.802835Z"},"content_sha256":"cb0c5d7379eb6f951d1afd71af5a0166c7c29cb48b4329f4f752080447ad7c3e","schema_version":"1.0","event_id":"sha256:cb0c5d7379eb6f951d1afd71af5a0166c7c29cb48b4329f4f752080447ad7c3e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UNZ27MAJCHJIQFIK2NBZ6WFTQW/bundle.json","state_url":"https://pith.science/pith/UNZ27MAJCHJIQFIK2NBZ6WFTQW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UNZ27MAJCHJIQFIK2NBZ6WFTQW/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":"2026-08-09T20:12:06Z","links":{"resolver":"https://pith.science/pith/UNZ27MAJCHJIQFIK2NBZ6WFTQW","bundle":"https://pith.science/pith/UNZ27MAJCHJIQFIK2NBZ6WFTQW/bundle.json","state":"https://pith.science/pith/UNZ27MAJCHJIQFIK2NBZ6WFTQW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UNZ27MAJCHJIQFIK2NBZ6WFTQW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UNZ27MAJCHJIQFIK2NBZ6WFTQW","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":"a0ed6b080c4d9262a99678e4515c7e13346fc9b49c8e685ff2633c6e58de8039","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T13:52:58Z","title_canon_sha256":"da655a633dacebb33d928cb2a5ccbb91b48209f843fade1e0047ecbb2e5dd667"},"schema_version":"1.0","source":{"id":"2506.00064","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00064","created_at":"2026-07-05T11:13:28Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00064v1","created_at":"2026-07-05T11:13:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00064","created_at":"2026-07-05T11:13:28Z"},{"alias_kind":"pith_short_12","alias_value":"UNZ27MAJCHJI","created_at":"2026-07-05T11:13:28Z"},{"alias_kind":"pith_short_16","alias_value":"UNZ27MAJCHJIQFIK","created_at":"2026-07-05T11:13:28Z"},{"alias_kind":"pith_short_8","alias_value":"UNZ27MAJ","created_at":"2026-07-05T11:13:28Z"}],"graph_snapshots":[{"event_id":"sha256:cb0c5d7379eb6f951d1afd71af5a0166c7c29cb48b4329f4f752080447ad7c3e","target":"graph","created_at":"2026-07-05T11:13:28Z","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/2506.00064/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated significant advancements in error handling. Current error-handling works are performed in a passive manner, with explicit error-handling instructions. However, in real-world scenarios, explicit error-handling instructions are usually unavailable. In this paper, our work identifies this challenge as how to conduct proactive error handling without explicit error handling instructions. To promote further research, this work introduces a new benchmark, termed Mis-prompt, consisting of four evaluation tasks, an error category taxonomy, and a new evalua","authors_text":"Aimin Zhou, Jiayi Zeng, Mengliang He, Wei Zhang, Wenhui Lei, Xiaoming Shi, Yizhe Feng, Zeming Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T13:52:58Z","title":"Mis-prompt: Benchmarking Large Language Models for Proactive Error Handling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00064","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":"sha256:1bcc397fe03a3935fbf91e345047230a0576ae5dc5ed11713fbb76cb400f5762","target":"record","created_at":"2026-07-05T11:13:28Z","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":"a0ed6b080c4d9262a99678e4515c7e13346fc9b49c8e685ff2633c6e58de8039","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T13:52:58Z","title_canon_sha256":"da655a633dacebb33d928cb2a5ccbb91b48209f843fade1e0047ecbb2e5dd667"},"schema_version":"1.0","source":{"id":"2506.00064","kind":"arxiv","version":1}},"canonical_sha256":"a373afb00911d288150ad3439f58b3858da3b08423cbc8969acee1917c8731e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a373afb00911d288150ad3439f58b3858da3b08423cbc8969acee1917c8731e2","first_computed_at":"2026-07-05T11:13:28.381809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:28.381809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ifob8ynC8iuCWRH5gTO8rJAUD1TeQR1iwGdz9fma9w2WBmSvTLIsOqLMqWP7IVShuisRJ34gWZaf+p2CHJUACA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:28.382298Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00064","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bcc397fe03a3935fbf91e345047230a0576ae5dc5ed11713fbb76cb400f5762","sha256:cb0c5d7379eb6f951d1afd71af5a0166c7c29cb48b4329f4f752080447ad7c3e"],"state_sha256":"d0b73bca955df2c2e3ec1ca81a9a463ea848672e53737c0946ffc7482a417778"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xC9YQtU5Zm2qb1n3f6JxotPIqdD0VXoCzllwuXldnmeRgJZZlxATz5t62K4olHB88aa1iVb6BZXkm2LruZMCBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:12:06.808098Z","bundle_sha256":"59e3aef555121913a70268e27b0bf3736894fe8d6a17cecf8a6066f3e53b5cce"}}