{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PVGXZ3CLNIK3PUGF7YNRONQEZB","short_pith_number":"pith:PVGXZ3CL","canonical_record":{"source":{"id":"2509.04809","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-05T05:09:09Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"751300e67a276560dc693236de9f5c9cd9fd279b1911f12550f0ec14ab0505a0","abstract_canon_sha256":"f8096067fb9061929fdb867f9dfcaa2dcce430f2c8395288c3226debd92a5adc"},"schema_version":"1.0"},"canonical_sha256":"7d4d7cec4b6a15b7d0c5fe1b173604c86dfeb72f7e477011fad2ea9bbf91d820","source":{"kind":"arxiv","id":"2509.04809","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04809","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04809v2","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04809","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"pith_short_12","alias_value":"PVGXZ3CLNIK3","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"pith_short_16","alias_value":"PVGXZ3CLNIK3PUGF","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"pith_short_8","alias_value":"PVGXZ3CL","created_at":"2026-07-05T12:06:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PVGXZ3CLNIK3PUGF7YNRONQEZB","target":"record","payload":{"canonical_record":{"source":{"id":"2509.04809","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-05T05:09:09Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"751300e67a276560dc693236de9f5c9cd9fd279b1911f12550f0ec14ab0505a0","abstract_canon_sha256":"f8096067fb9061929fdb867f9dfcaa2dcce430f2c8395288c3226debd92a5adc"},"schema_version":"1.0"},"canonical_sha256":"7d4d7cec4b6a15b7d0c5fe1b173604c86dfeb72f7e477011fad2ea9bbf91d820","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:20.688774Z","signature_b64":"fzsYs4ZnDte3QQVHVbtTsCVHD2bo6zVCS5xE6ZD3yvNRBYHCTFK6d0gSZtZ8n1cOzAjZRNKQlkcMRieO+x5rDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d4d7cec4b6a15b7d0c5fe1b173604c86dfeb72f7e477011fad2ea9bbf91d820","last_reissued_at":"2026-07-05T12:06:20.688224Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:20.688224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.04809","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:06:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JSzE9JTIeGDk0nLrPmdcYoqWT+APCPLhAqVUT0kiEhqOAXUNMCZrsyx0EeycSno5VaSvV6sJbZtAn+eTqbUoBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:04:01.746232Z"},"content_sha256":"325628738d21e34fe5be091700564d1bc0ac7c6b2ed10229845f35d1c52a30e8","schema_version":"1.0","event_id":"sha256:325628738d21e34fe5be091700564d1bc0ac7c6b2ed10229845f35d1c52a30e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PVGXZ3CLNIK3PUGF7YNRONQEZB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TalkToAgent: A Human-centric Explanation of Reinforcement Learning Agents with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Can Li, Haechang Kim, Hao Chen, Jong Min Lee","submitted_at":"2025-09-05T05:09:09Z","abstract_excerpt":"Explainable Reinforcement Learning (XRL) has emerged as a promising approach in improving the transparency of Reinforcement Learning (RL) agents. However, there remains a gap between complex RL policies and domain experts, due to the limited comprehensibility of XRL results and isolated coverage of current XRL approaches that leave users uncertain about which tools to employ. To address these challenges, we introduce TalkToAgent, a multi-agent Large Language Models (LLM) framework that delivers interactive, natural language explanations for RL policies. The architecture with five specialized L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04809","kind":"arxiv","version":2},"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/2509.04809/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":"2026-07-05T12:06:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Cvji+3cL5dAKUlX5Cebj3TM79hgZizEoKdW+kC1QbNW//Vyxo2nmACCkXku4y1l1eRirXQULpatCou4DQJyCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:04:01.747410Z"},"content_sha256":"d38c0d7631cca73adb91eb0fb60476cb3bc899c418e95ba7a2170973fab1c8d6","schema_version":"1.0","event_id":"sha256:d38c0d7631cca73adb91eb0fb60476cb3bc899c418e95ba7a2170973fab1c8d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PVGXZ3CLNIK3PUGF7YNRONQEZB/bundle.json","state_url":"https://pith.science/pith/PVGXZ3CLNIK3PUGF7YNRONQEZB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PVGXZ3CLNIK3PUGF7YNRONQEZB/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":"2026-08-11T03:04:01Z","links":{"resolver":"https://pith.science/pith/PVGXZ3CLNIK3PUGF7YNRONQEZB","bundle":"https://pith.science/pith/PVGXZ3CLNIK3PUGF7YNRONQEZB/bundle.json","state":"https://pith.science/pith/PVGXZ3CLNIK3PUGF7YNRONQEZB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PVGXZ3CLNIK3PUGF7YNRONQEZB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PVGXZ3CLNIK3PUGF7YNRONQEZB","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":"f8096067fb9061929fdb867f9dfcaa2dcce430f2c8395288c3226debd92a5adc","cross_cats_sorted":["cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-05T05:09:09Z","title_canon_sha256":"751300e67a276560dc693236de9f5c9cd9fd279b1911f12550f0ec14ab0505a0"},"schema_version":"1.0","source":{"id":"2509.04809","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04809","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04809v2","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04809","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"pith_short_12","alias_value":"PVGXZ3CLNIK3","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"pith_short_16","alias_value":"PVGXZ3CLNIK3PUGF","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"pith_short_8","alias_value":"PVGXZ3CL","created_at":"2026-07-05T12:06:20Z"}],"graph_snapshots":[{"event_id":"sha256:d38c0d7631cca73adb91eb0fb60476cb3bc899c418e95ba7a2170973fab1c8d6","target":"graph","created_at":"2026-07-05T12:06:20Z","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/2509.04809/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Explainable Reinforcement Learning (XRL) has emerged as a promising approach in improving the transparency of Reinforcement Learning (RL) agents. However, there remains a gap between complex RL policies and domain experts, due to the limited comprehensibility of XRL results and isolated coverage of current XRL approaches that leave users uncertain about which tools to employ. To address these challenges, we introduce TalkToAgent, a multi-agent Large Language Models (LLM) framework that delivers interactive, natural language explanations for RL policies. The architecture with five specialized L","authors_text":"Can Li, Haechang Kim, Hao Chen, Jong Min Lee","cross_cats":["cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-05T05:09:09Z","title":"TalkToAgent: A Human-centric Explanation of Reinforcement Learning Agents with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04809","kind":"arxiv","version":2},"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":"sha256:325628738d21e34fe5be091700564d1bc0ac7c6b2ed10229845f35d1c52a30e8","target":"record","created_at":"2026-07-05T12:06:20Z","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":"f8096067fb9061929fdb867f9dfcaa2dcce430f2c8395288c3226debd92a5adc","cross_cats_sorted":["cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-05T05:09:09Z","title_canon_sha256":"751300e67a276560dc693236de9f5c9cd9fd279b1911f12550f0ec14ab0505a0"},"schema_version":"1.0","source":{"id":"2509.04809","kind":"arxiv","version":2}},"canonical_sha256":"7d4d7cec4b6a15b7d0c5fe1b173604c86dfeb72f7e477011fad2ea9bbf91d820","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d4d7cec4b6a15b7d0c5fe1b173604c86dfeb72f7e477011fad2ea9bbf91d820","first_computed_at":"2026-07-05T12:06:20.688224Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:20.688224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fzsYs4ZnDte3QQVHVbtTsCVHD2bo6zVCS5xE6ZD3yvNRBYHCTFK6d0gSZtZ8n1cOzAjZRNKQlkcMRieO+x5rDw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:20.688774Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.04809","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:325628738d21e34fe5be091700564d1bc0ac7c6b2ed10229845f35d1c52a30e8","sha256:d38c0d7631cca73adb91eb0fb60476cb3bc899c418e95ba7a2170973fab1c8d6"],"state_sha256":"8ea164bf73053f73184262c905b40e41640ef22320dba784bc96350f64eea857"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6bagYYOO9XV3Trvv/wCuXQGvxnQI/pzBejNgd+vax2GzwjT3crCOLhgcZm77Xrbtju1ROIFCqhM2bukkHnBYDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T03:04:01.754329Z","bundle_sha256":"b1788821eb70f928d591fa4d82e5320f3abbd0252a76ef57e06cba2f65aa6d22"}}