{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:R5WNUQXTRVNE6DNUPFUXVOMK37","short_pith_number":"pith:R5WNUQXT","canonical_record":{"source":{"id":"2606.06976","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-05T07:08:34Z","cross_cats_sorted":[],"title_canon_sha256":"012f61c6a1e764491eaa1fe0c5bd92bca1583833008b05104516c661087803cb","abstract_canon_sha256":"e858c08c760ab6271845e92409a5bb5922e57c1756908423e84f53bea5aaf788"},"schema_version":"1.0"},"canonical_sha256":"8f6cda42f38d5a4f0db479697ab98adfe5cf14f6cdecf35467e4618627c1931a","source":{"kind":"arxiv","id":"2606.06976","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06976","created_at":"2026-06-08T01:04:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06976v1","created_at":"2026-06-08T01:04:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06976","created_at":"2026-06-08T01:04:39Z"},{"alias_kind":"pith_short_12","alias_value":"R5WNUQXTRVNE","created_at":"2026-06-08T01:04:39Z"},{"alias_kind":"pith_short_16","alias_value":"R5WNUQXTRVNE6DNU","created_at":"2026-06-08T01:04:39Z"},{"alias_kind":"pith_short_8","alias_value":"R5WNUQXT","created_at":"2026-06-08T01:04:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:R5WNUQXTRVNE6DNUPFUXVOMK37","target":"record","payload":{"canonical_record":{"source":{"id":"2606.06976","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-05T07:08:34Z","cross_cats_sorted":[],"title_canon_sha256":"012f61c6a1e764491eaa1fe0c5bd92bca1583833008b05104516c661087803cb","abstract_canon_sha256":"e858c08c760ab6271845e92409a5bb5922e57c1756908423e84f53bea5aaf788"},"schema_version":"1.0"},"canonical_sha256":"8f6cda42f38d5a4f0db479697ab98adfe5cf14f6cdecf35467e4618627c1931a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:39.054856Z","signature_b64":"3U27gtp73SMGwt3ZETz6X4mTPNrMdn0ZQXhJGXCLQpHZMd4ozD1vSxjL0WAHc2JPYmbrFuq5B9zSQjtSmbGdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f6cda42f38d5a4f0db479697ab98adfe5cf14f6cdecf35467e4618627c1931a","last_reissued_at":"2026-06-08T01:04:39.054284Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:39.054284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.06976","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":"2026-06-08T01:04:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HiGgc8fBzmrMy0fCGY2poJ3BxbOC7EAl77FGs/1EQKqbeS7AiR5S9p6PU945imeZRDMjRY51JVOIxnzjMPicBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T01:33:52.068397Z"},"content_sha256":"7bb63599e5f1627609ed00730677305ff8d6fcbf0fbc7c5dd6f8ee89d35e5253","schema_version":"1.0","event_id":"sha256:7bb63599e5f1627609ed00730677305ff8d6fcbf0fbc7c5dd6f8ee89d35e5253"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:R5WNUQXTRVNE6DNUPFUXVOMK37","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dongrui Liu, Jing Shao, Junchi Yan, Linqian Zeng, Wenyuan Xie, Xiaoya Lu, Yijin Zhou","submitted_at":"2026-06-05T07:08:34Z","abstract_excerpt":"Large language model (LLM)-based agents often make suboptimal tool-use decisions, including unsupported tool invocation and hallucinated direct responses, which may accumulate errors throughout multi-step interactions. Existing approaches mainly improve these behaviors through inference-time correction or coarse-grained reward signals based on decision outcomes and structured checklists, leaving the uncertainty characteristics of agent decisions underexplored. We observe that decision-oriented reinforcement learning tends to weaken the uncertainty separation between correct and incorrect actio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06976","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/2606.06976/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":"2026-06-08T01:04:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h6Ma0dhH1Lc6XCd7Pn0f3NR+9CfQL0Kg9teH86Wv5sGFTsXahbKwL+g6QuBZI6ZM3Pg3bPeVEkYkI1f0NVuCBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T01:33:52.068782Z"},"content_sha256":"ad697cfa4ebb5bb72d99555f5134f240192b3b94f8254955e3bf0609ffaa79f8","schema_version":"1.0","event_id":"sha256:ad697cfa4ebb5bb72d99555f5134f240192b3b94f8254955e3bf0609ffaa79f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R5WNUQXTRVNE6DNUPFUXVOMK37/bundle.json","state_url":"https://pith.science/pith/R5WNUQXTRVNE6DNUPFUXVOMK37/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R5WNUQXTRVNE6DNUPFUXVOMK37/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":"2026-07-03T01:33:52Z","links":{"resolver":"https://pith.science/pith/R5WNUQXTRVNE6DNUPFUXVOMK37","bundle":"https://pith.science/pith/R5WNUQXTRVNE6DNUPFUXVOMK37/bundle.json","state":"https://pith.science/pith/R5WNUQXTRVNE6DNUPFUXVOMK37/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R5WNUQXTRVNE6DNUPFUXVOMK37/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:R5WNUQXTRVNE6DNUPFUXVOMK37","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":"e858c08c760ab6271845e92409a5bb5922e57c1756908423e84f53bea5aaf788","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-05T07:08:34Z","title_canon_sha256":"012f61c6a1e764491eaa1fe0c5bd92bca1583833008b05104516c661087803cb"},"schema_version":"1.0","source":{"id":"2606.06976","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06976","created_at":"2026-06-08T01:04:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06976v1","created_at":"2026-06-08T01:04:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06976","created_at":"2026-06-08T01:04:39Z"},{"alias_kind":"pith_short_12","alias_value":"R5WNUQXTRVNE","created_at":"2026-06-08T01:04:39Z"},{"alias_kind":"pith_short_16","alias_value":"R5WNUQXTRVNE6DNU","created_at":"2026-06-08T01:04:39Z"},{"alias_kind":"pith_short_8","alias_value":"R5WNUQXT","created_at":"2026-06-08T01:04:39Z"}],"graph_snapshots":[{"event_id":"sha256:ad697cfa4ebb5bb72d99555f5134f240192b3b94f8254955e3bf0609ffaa79f8","target":"graph","created_at":"2026-06-08T01:04:39Z","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/2606.06976/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM)-based agents often make suboptimal tool-use decisions, including unsupported tool invocation and hallucinated direct responses, which may accumulate errors throughout multi-step interactions. Existing approaches mainly improve these behaviors through inference-time correction or coarse-grained reward signals based on decision outcomes and structured checklists, leaving the uncertainty characteristics of agent decisions underexplored. We observe that decision-oriented reinforcement learning tends to weaken the uncertainty separation between correct and incorrect actio","authors_text":"Dongrui Liu, Jing Shao, Junchi Yan, Linqian Zeng, Wenyuan Xie, Xiaoya Lu, Yijin Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-05T07:08:34Z","title":"Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06976","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":"sha256:7bb63599e5f1627609ed00730677305ff8d6fcbf0fbc7c5dd6f8ee89d35e5253","target":"record","created_at":"2026-06-08T01:04:39Z","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":"e858c08c760ab6271845e92409a5bb5922e57c1756908423e84f53bea5aaf788","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-05T07:08:34Z","title_canon_sha256":"012f61c6a1e764491eaa1fe0c5bd92bca1583833008b05104516c661087803cb"},"schema_version":"1.0","source":{"id":"2606.06976","kind":"arxiv","version":1}},"canonical_sha256":"8f6cda42f38d5a4f0db479697ab98adfe5cf14f6cdecf35467e4618627c1931a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f6cda42f38d5a4f0db479697ab98adfe5cf14f6cdecf35467e4618627c1931a","first_computed_at":"2026-06-08T01:04:39.054284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:04:39.054284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3U27gtp73SMGwt3ZETz6X4mTPNrMdn0ZQXhJGXCLQpHZMd4ozD1vSxjL0WAHc2JPYmbrFuq5B9zSQjtSmbGdCw==","signature_status":"signed_v1","signed_at":"2026-06-08T01:04:39.054856Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.06976","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7bb63599e5f1627609ed00730677305ff8d6fcbf0fbc7c5dd6f8ee89d35e5253","sha256:ad697cfa4ebb5bb72d99555f5134f240192b3b94f8254955e3bf0609ffaa79f8"],"state_sha256":"fb2ca8b0e56b4039343a222a5c127e4696b156b34ae7894a34600bd42923ffa0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ww/JtzzBAoqMAIhZRkeTZFpo2Pfn8k98+VwhlzWQvwUl2/iEIOB2tezZWGWFyvFTbXapNqV+os6wtqDEw/4dDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T01:33:52.070837Z","bundle_sha256":"840c9473c4708f1d0780c3d0921d0c3b61df06cc3aadf884fb02eea9c4517585"}}