{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5RWBKK5HUSFIMNX36ONIZQDNAB","short_pith_number":"pith:5RWBKK5H","schema_version":"1.0","canonical_sha256":"ec6c152ba7a48a8636fbf39a8cc06d005aeab7e83a512b948d9813aa171c9698","source":{"kind":"arxiv","id":"2607.12397","version":1},"attestation_state":"computed","paper":{"title":"Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Congchao Wang, Jianhang Chen, Lu Lin, Nan Wang, Yaopei Zeng, Yurui Chang","submitted_at":"2026-07-14T06:17:09Z","abstract_excerpt":"LLM agents act in external environments where each action changes the state that later decisions condition on, and where a single wrong step can waste interaction budget or trigger irreversible side effects long before the final failure is observed. Reliable deployment therefore requires \\emph{step-level confidence estimation}: a calibrated probability that each proposed action is productive, available \\emph{before} the action is executed. Existing LLM confidence estimators are designed to score a response from the given prompt, but agent confidence also depends on execution consequences: whet"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.12397","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-14T06:17:09Z","cross_cats_sorted":[],"title_canon_sha256":"0c54679f6d782b82fcd67bb4d6f9f39c060c6ad0084ac04240ee8da18f7b5c93","abstract_canon_sha256":"fb1d30b6d53af436eb6cae4608d89f1fbc771ef5b721229341c5bc2956765617"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T01:21:32.821982Z","signature_b64":"r9bQouobhjhCLcCOILuwaPDB3fumsgqIftr1x4tbH1rWvyNcdzM2deJ8hOtYawRWT9Lsx4ul3whYWMGDRap8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec6c152ba7a48a8636fbf39a8cc06d005aeab7e83a512b948d9813aa171c9698","last_reissued_at":"2026-07-15T01:21:32.821121Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T01:21:32.821121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Congchao Wang, Jianhang Chen, Lu Lin, Nan Wang, Yaopei Zeng, Yurui Chang","submitted_at":"2026-07-14T06:17:09Z","abstract_excerpt":"LLM agents act in external environments where each action changes the state that later decisions condition on, and where a single wrong step can waste interaction budget or trigger irreversible side effects long before the final failure is observed. Reliable deployment therefore requires \\emph{step-level confidence estimation}: a calibrated probability that each proposed action is productive, available \\emph{before} the action is executed. Existing LLM confidence estimators are designed to score a response from the given prompt, but agent confidence also depends on execution consequences: whet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.12397","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/2607.12397/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.12397","created_at":"2026-07-15T01:21:32.821579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.12397v1","created_at":"2026-07-15T01:21:32.821579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.12397","created_at":"2026-07-15T01:21:32.821579+00:00"},{"alias_kind":"pith_short_12","alias_value":"5RWBKK5HUSFI","created_at":"2026-07-15T01:21:32.821579+00:00"},{"alias_kind":"pith_short_16","alias_value":"5RWBKK5HUSFIMNX3","created_at":"2026-07-15T01:21:32.821579+00:00"},{"alias_kind":"pith_short_8","alias_value":"5RWBKK5H","created_at":"2026-07-15T01:21:32.821579+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5RWBKK5HUSFIMNX36ONIZQDNAB","json":"https://pith.science/pith/5RWBKK5HUSFIMNX36ONIZQDNAB.json","graph_json":"https://pith.science/api/pith-number/5RWBKK5HUSFIMNX36ONIZQDNAB/graph.json","events_json":"https://pith.science/api/pith-number/5RWBKK5HUSFIMNX36ONIZQDNAB/events.json","paper":"https://pith.science/paper/5RWBKK5H"},"agent_actions":{"view_html":"https://pith.science/pith/5RWBKK5HUSFIMNX36ONIZQDNAB","download_json":"https://pith.science/pith/5RWBKK5HUSFIMNX36ONIZQDNAB.json","view_paper":"https://pith.science/paper/5RWBKK5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.12397&json=true","fetch_graph":"https://pith.science/api/pith-number/5RWBKK5HUSFIMNX36ONIZQDNAB/graph.json","fetch_events":"https://pith.science/api/pith-number/5RWBKK5HUSFIMNX36ONIZQDNAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5RWBKK5HUSFIMNX36ONIZQDNAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5RWBKK5HUSFIMNX36ONIZQDNAB/action/storage_attestation","attest_author":"https://pith.science/pith/5RWBKK5HUSFIMNX36ONIZQDNAB/action/author_attestation","sign_citation":"https://pith.science/pith/5RWBKK5HUSFIMNX36ONIZQDNAB/action/citation_signature","submit_replication":"https://pith.science/pith/5RWBKK5HUSFIMNX36ONIZQDNAB/action/replication_record"}},"created_at":"2026-07-15T01:21:32.821579+00:00","updated_at":"2026-07-15T01:21:32.821579+00:00"}