{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KL6K6ZYIXGRPGSHAFQHSTP6ODS","short_pith_number":"pith:KL6K6ZYI","canonical_record":{"source":{"id":"2606.03963","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T17:50:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4ff8c787f4c0ded55f50f95c73ac2269624fb2f59a7cbb5005569ac02fa70c14","abstract_canon_sha256":"b853d4cf737e1594359a06b3d42f9d921f2b4bcdd5f904197001741908b3c536"},"schema_version":"1.0"},"canonical_sha256":"52fcaf6708b9a2f348e02c0f29bfce1c9dcdc095b4d3c2b61ee4f670dd88cbd1","source":{"kind":"arxiv","id":"2606.03963","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03963","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03963v1","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03963","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"pith_short_12","alias_value":"KL6K6ZYIXGRP","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"pith_short_16","alias_value":"KL6K6ZYIXGRPGSHA","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"pith_short_8","alias_value":"KL6K6ZYI","created_at":"2026-06-03T02:06:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KL6K6ZYIXGRPGSHAFQHSTP6ODS","target":"record","payload":{"canonical_record":{"source":{"id":"2606.03963","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T17:50:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4ff8c787f4c0ded55f50f95c73ac2269624fb2f59a7cbb5005569ac02fa70c14","abstract_canon_sha256":"b853d4cf737e1594359a06b3d42f9d921f2b4bcdd5f904197001741908b3c536"},"schema_version":"1.0"},"canonical_sha256":"52fcaf6708b9a2f348e02c0f29bfce1c9dcdc095b4d3c2b61ee4f670dd88cbd1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T02:06:08.100136Z","signature_b64":"I0Wa3HUxPvnJ3fdwVzQbdEbq3GwC9F9SHK5Eczs5E/s2zBrn83+nXAYSIvUhR2NJhmlwonuc3bqpTU1rs/qIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52fcaf6708b9a2f348e02c0f29bfce1c9dcdc095b4d3c2b61ee4f670dd88cbd1","last_reissued_at":"2026-06-03T02:06:08.099710Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T02:06:08.099710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.03963","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":"2026-06-03T02:06:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hRTjrkdxJNG+TopnkInDkJoCpPb10h67fEz6fWMMybcR4VdV/V9e8f+FLAO7enVkYHnFgck7IwS73v0yxiSKCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T12:39:23.140592Z"},"content_sha256":"71a74eb7053f78302a9974002a7c9b8eb93cc44e129585801ee8433e9025f9a6","schema_version":"1.0","event_id":"sha256:71a74eb7053f78302a9974002a7c9b8eb93cc44e129585801ee8433e9025f9a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KL6K6ZYIXGRPGSHAFQHSTP6ODS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Refining Agentic Reinforcement Learning for Vision-Conditioned UAV Navigation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Dzmitry Tsetserukou, Muhammad Ahsan Mustafa, Roohan Ahmed Khan, Yasheerah Yaqoot","submitted_at":"2026-06-02T17:50:15Z","abstract_excerpt":"Deep reinforcement learning has shown strong potential for enabling autonomous robots to learn complex navigational tasks. However, its practical use still depends heavily on human designed reward functions and repeated manual fine tuning, which is time consuming and does not guarantee high success in the desired task. This paper presents AgenticRL, agent guided reinforcement learning framework that increases autonomy in reward design, policy refinement, and real world deployment for unmanned aerial vehicles (UAV) navigation tasks. AgenticRL uses a multimodal generative pre-trained tansformer "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03963","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/2606.03963/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":"2026-06-03T02:06:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ibEK8jsm0U9gf4SfqfkH3hQEDEoUakj1bbNo7ZsOdGEm3vckbasNiUTulHBT79Xb+1VGut/NwauyJ8N+pnwiAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T12:39:23.141424Z"},"content_sha256":"d785373953c41fc9b13a0779a3b3610db1e4df0216224fc5615d4971176bbaa7","schema_version":"1.0","event_id":"sha256:d785373953c41fc9b13a0779a3b3610db1e4df0216224fc5615d4971176bbaa7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KL6K6ZYIXGRPGSHAFQHSTP6ODS/bundle.json","state_url":"https://pith.science/pith/KL6K6ZYIXGRPGSHAFQHSTP6ODS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KL6K6ZYIXGRPGSHAFQHSTP6ODS/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":"2026-06-10T12:39:23Z","links":{"resolver":"https://pith.science/pith/KL6K6ZYIXGRPGSHAFQHSTP6ODS","bundle":"https://pith.science/pith/KL6K6ZYIXGRPGSHAFQHSTP6ODS/bundle.json","state":"https://pith.science/pith/KL6K6ZYIXGRPGSHAFQHSTP6ODS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KL6K6ZYIXGRPGSHAFQHSTP6ODS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KL6K6ZYIXGRPGSHAFQHSTP6ODS","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":"b853d4cf737e1594359a06b3d42f9d921f2b4bcdd5f904197001741908b3c536","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T17:50:15Z","title_canon_sha256":"4ff8c787f4c0ded55f50f95c73ac2269624fb2f59a7cbb5005569ac02fa70c14"},"schema_version":"1.0","source":{"id":"2606.03963","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03963","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03963v1","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03963","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"pith_short_12","alias_value":"KL6K6ZYIXGRP","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"pith_short_16","alias_value":"KL6K6ZYIXGRPGSHA","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"pith_short_8","alias_value":"KL6K6ZYI","created_at":"2026-06-03T02:06:08Z"}],"graph_snapshots":[{"event_id":"sha256:d785373953c41fc9b13a0779a3b3610db1e4df0216224fc5615d4971176bbaa7","target":"graph","created_at":"2026-06-03T02:06:08Z","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/2606.03963/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning has shown strong potential for enabling autonomous robots to learn complex navigational tasks. However, its practical use still depends heavily on human designed reward functions and repeated manual fine tuning, which is time consuming and does not guarantee high success in the desired task. This paper presents AgenticRL, agent guided reinforcement learning framework that increases autonomy in reward design, policy refinement, and real world deployment for unmanned aerial vehicles (UAV) navigation tasks. AgenticRL uses a multimodal generative pre-trained tansformer ","authors_text":"Dzmitry Tsetserukou, Muhammad Ahsan Mustafa, Roohan Ahmed Khan, Yasheerah Yaqoot","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T17:50:15Z","title":"Self-Refining Agentic Reinforcement Learning for Vision-Conditioned UAV Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03963","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":"sha256:71a74eb7053f78302a9974002a7c9b8eb93cc44e129585801ee8433e9025f9a6","target":"record","created_at":"2026-06-03T02:06:08Z","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":"b853d4cf737e1594359a06b3d42f9d921f2b4bcdd5f904197001741908b3c536","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T17:50:15Z","title_canon_sha256":"4ff8c787f4c0ded55f50f95c73ac2269624fb2f59a7cbb5005569ac02fa70c14"},"schema_version":"1.0","source":{"id":"2606.03963","kind":"arxiv","version":1}},"canonical_sha256":"52fcaf6708b9a2f348e02c0f29bfce1c9dcdc095b4d3c2b61ee4f670dd88cbd1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52fcaf6708b9a2f348e02c0f29bfce1c9dcdc095b4d3c2b61ee4f670dd88cbd1","first_computed_at":"2026-06-03T02:06:08.099710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T02:06:08.099710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I0Wa3HUxPvnJ3fdwVzQbdEbq3GwC9F9SHK5Eczs5E/s2zBrn83+nXAYSIvUhR2NJhmlwonuc3bqpTU1rs/qIBg==","signature_status":"signed_v1","signed_at":"2026-06-03T02:06:08.100136Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03963","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71a74eb7053f78302a9974002a7c9b8eb93cc44e129585801ee8433e9025f9a6","sha256:d785373953c41fc9b13a0779a3b3610db1e4df0216224fc5615d4971176bbaa7"],"state_sha256":"a90846cd517acecc537b047c3295f3997f6813c6b11b7a04894047ce75cafc62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xOFe2OSXMu1eBgOPtTwhvjWkv+7iVpR1rgEgTH41Ecek+MiCb5k0WaGgcF8PX6iANA2Dprp3mpXJTzg8Ba8ABg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T12:39:23.145861Z","bundle_sha256":"3b79c59343722ea4b5253d5e7806888dcc5f2bdf33af4a20c77d687c54e8789e"}}