{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YLCZUBGOX4ACDFSAT667BP36CG","short_pith_number":"pith:YLCZUBGO","canonical_record":{"source":{"id":"2606.03762","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T15:16:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ba18d1513462ea056ca4699cdb59b95bb7be60ead6b71d88f89545c2dae659bf","abstract_canon_sha256":"61f5c796d69717c52e54f15d5d0c305b55ebe5d717187db73eedb576d1142b65"},"schema_version":"1.0"},"canonical_sha256":"c2c59a04cebf002196409fbdf0bf7e118194f97e9575eaef8880d293ea7c9b1c","source":{"kind":"arxiv","id":"2606.03762","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03762","created_at":"2026-06-03T02:06:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03762v1","created_at":"2026-06-03T02:06:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03762","created_at":"2026-06-03T02:06:01Z"},{"alias_kind":"pith_short_12","alias_value":"YLCZUBGOX4AC","created_at":"2026-06-03T02:06:01Z"},{"alias_kind":"pith_short_16","alias_value":"YLCZUBGOX4ACDFSA","created_at":"2026-06-03T02:06:01Z"},{"alias_kind":"pith_short_8","alias_value":"YLCZUBGO","created_at":"2026-06-03T02:06:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YLCZUBGOX4ACDFSAT667BP36CG","target":"record","payload":{"canonical_record":{"source":{"id":"2606.03762","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T15:16:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ba18d1513462ea056ca4699cdb59b95bb7be60ead6b71d88f89545c2dae659bf","abstract_canon_sha256":"61f5c796d69717c52e54f15d5d0c305b55ebe5d717187db73eedb576d1142b65"},"schema_version":"1.0"},"canonical_sha256":"c2c59a04cebf002196409fbdf0bf7e118194f97e9575eaef8880d293ea7c9b1c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T02:06:01.764642Z","signature_b64":"0nmSEdjp7WVxckT3ic1gic2kTMVCEZUA12DbeeNpmV8qLiHoqiiA80BYWucIQjWtKGBmRdXDBvrVhe5dPqiEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2c59a04cebf002196409fbdf0bf7e118194f97e9575eaef8880d293ea7c9b1c","last_reissued_at":"2026-06-03T02:06:01.764197Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T02:06:01.764197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.03762","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":"2026-06-03T02:06:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WV6m/99eKTaLkp9hBYF0qs7sgxDV+enB/2KF2/+sEzoAgouKt3PqZU8RDYarGUp4c/L3+JpwTsJcmb5MBekJAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T20:34:25.427562Z"},"content_sha256":"93898ae8599ef06c34c1f9f33fce728cbd7ba414795a4675e96e888ab35bb8de","schema_version":"1.0","event_id":"sha256:93898ae8599ef06c34c1f9f33fce728cbd7ba414795a4675e96e888ab35bb8de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YLCZUBGOX4ACDFSAT667BP36CG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tool-Aware Optimization with Entropy Guidance for Efficient Agentic Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haoyuan Deng, Hongye Cao, Jing Huo, Nuo Yan, Tianpei Yang, Yang Gao, Yuyao Zhang, Ziwei Wang","submitted_at":"2026-06-02T15:16:12Z","abstract_excerpt":"Agentic reinforcement learning (RL) equips large language models (LLMs) with tool-use capabilities that substantially improve reasoning on complex tasks. However, integrating external tools often destabilizes training: over-reliance on tools can induce input distribution shift, while overly conservative tool use limits effective exploration. To address this issue, we propose a unified framework TAO-RL that couples tool-aware trajectory filtering with entropy-guided exploration for efficient policy optimization. Specifically, at the data level, TAO-RL filters rollout trajectories along two crit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03762","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/2606.03762/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":"2026-06-03T02:06:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iZKm1qyl5OxVk4J/faItwQbM32+6MF0tL8TYWVz1WFw6/+lK2+kios5/DaKEq+kVUhPZ+1q1sklnMQec0aNTDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T20:34:25.427931Z"},"content_sha256":"c41c53f7728def45f74d2af2a2b063171fe4ff23c987ce4a0aa6b97d27001352","schema_version":"1.0","event_id":"sha256:c41c53f7728def45f74d2af2a2b063171fe4ff23c987ce4a0aa6b97d27001352"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YLCZUBGOX4ACDFSAT667BP36CG/bundle.json","state_url":"https://pith.science/pith/YLCZUBGOX4ACDFSAT667BP36CG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YLCZUBGOX4ACDFSAT667BP36CG/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":"2026-06-20T20:34:25Z","links":{"resolver":"https://pith.science/pith/YLCZUBGOX4ACDFSAT667BP36CG","bundle":"https://pith.science/pith/YLCZUBGOX4ACDFSAT667BP36CG/bundle.json","state":"https://pith.science/pith/YLCZUBGOX4ACDFSAT667BP36CG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YLCZUBGOX4ACDFSAT667BP36CG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YLCZUBGOX4ACDFSAT667BP36CG","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":"61f5c796d69717c52e54f15d5d0c305b55ebe5d717187db73eedb576d1142b65","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T15:16:12Z","title_canon_sha256":"ba18d1513462ea056ca4699cdb59b95bb7be60ead6b71d88f89545c2dae659bf"},"schema_version":"1.0","source":{"id":"2606.03762","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03762","created_at":"2026-06-03T02:06:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03762v1","created_at":"2026-06-03T02:06:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03762","created_at":"2026-06-03T02:06:01Z"},{"alias_kind":"pith_short_12","alias_value":"YLCZUBGOX4AC","created_at":"2026-06-03T02:06:01Z"},{"alias_kind":"pith_short_16","alias_value":"YLCZUBGOX4ACDFSA","created_at":"2026-06-03T02:06:01Z"},{"alias_kind":"pith_short_8","alias_value":"YLCZUBGO","created_at":"2026-06-03T02:06:01Z"}],"graph_snapshots":[{"event_id":"sha256:c41c53f7728def45f74d2af2a2b063171fe4ff23c987ce4a0aa6b97d27001352","target":"graph","created_at":"2026-06-03T02:06:01Z","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/2606.03762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agentic reinforcement learning (RL) equips large language models (LLMs) with tool-use capabilities that substantially improve reasoning on complex tasks. However, integrating external tools often destabilizes training: over-reliance on tools can induce input distribution shift, while overly conservative tool use limits effective exploration. To address this issue, we propose a unified framework TAO-RL that couples tool-aware trajectory filtering with entropy-guided exploration for efficient policy optimization. Specifically, at the data level, TAO-RL filters rollout trajectories along two crit","authors_text":"Haoyuan Deng, Hongye Cao, Jing Huo, Nuo Yan, Tianpei Yang, Yang Gao, Yuyao Zhang, Ziwei Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T15:16:12Z","title":"Tool-Aware Optimization with Entropy Guidance for Efficient Agentic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03762","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":"sha256:93898ae8599ef06c34c1f9f33fce728cbd7ba414795a4675e96e888ab35bb8de","target":"record","created_at":"2026-06-03T02:06:01Z","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":"61f5c796d69717c52e54f15d5d0c305b55ebe5d717187db73eedb576d1142b65","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T15:16:12Z","title_canon_sha256":"ba18d1513462ea056ca4699cdb59b95bb7be60ead6b71d88f89545c2dae659bf"},"schema_version":"1.0","source":{"id":"2606.03762","kind":"arxiv","version":1}},"canonical_sha256":"c2c59a04cebf002196409fbdf0bf7e118194f97e9575eaef8880d293ea7c9b1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2c59a04cebf002196409fbdf0bf7e118194f97e9575eaef8880d293ea7c9b1c","first_computed_at":"2026-06-03T02:06:01.764197Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T02:06:01.764197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0nmSEdjp7WVxckT3ic1gic2kTMVCEZUA12DbeeNpmV8qLiHoqiiA80BYWucIQjWtKGBmRdXDBvrVhe5dPqiEDw==","signature_status":"signed_v1","signed_at":"2026-06-03T02:06:01.764642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03762","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93898ae8599ef06c34c1f9f33fce728cbd7ba414795a4675e96e888ab35bb8de","sha256:c41c53f7728def45f74d2af2a2b063171fe4ff23c987ce4a0aa6b97d27001352"],"state_sha256":"fd295afa122bcc9436a5718c1cf4429e12cff7afd82cc12b25076d9528317137"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L76fxocrBaOuCgRJ84rVudaLrX2PR/xqfluLcX7Jfti4+F8ukFlpcAVkTYfWa1IQ+TJ0KmOezT2mbD3ofx4wDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T20:34:25.429951Z","bundle_sha256":"b6eef8684500adbca2c9cdddb67295a1cae56ae73920966809edaa7d6985a9c0"}}