{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BTKCVRI3GH6LATC6JGBWJHETC5","short_pith_number":"pith:BTKCVRI3","canonical_record":{"source":{"id":"2608.09555","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T12:53:06Z","cross_cats_sorted":[],"title_canon_sha256":"6e04e203ae5ce73e8fa26dbfa9f56089574bee47a8a1a3352b7f11cd74d843d3","abstract_canon_sha256":"ce0f20aaa5dbbfa8c5677bd4e7b0f8eea2018709dcb198acdcb383f36edd644a"},"schema_version":"1.0"},"canonical_sha256":"0cd42ac51b31fcb04c5e4983649c93175ada6297af19de7be8ce1f875f37976f","source":{"kind":"arxiv","id":"2608.09555","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09555","created_at":"2026-08-11T02:24:29Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09555v1","created_at":"2026-08-11T02:24:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09555","created_at":"2026-08-11T02:24:29Z"},{"alias_kind":"pith_short_12","alias_value":"BTKCVRI3GH6L","created_at":"2026-08-11T02:24:29Z"},{"alias_kind":"pith_short_16","alias_value":"BTKCVRI3GH6LATC6","created_at":"2026-08-11T02:24:29Z"},{"alias_kind":"pith_short_8","alias_value":"BTKCVRI3","created_at":"2026-08-11T02:24:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BTKCVRI3GH6LATC6JGBWJHETC5","target":"record","payload":{"canonical_record":{"source":{"id":"2608.09555","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T12:53:06Z","cross_cats_sorted":[],"title_canon_sha256":"6e04e203ae5ce73e8fa26dbfa9f56089574bee47a8a1a3352b7f11cd74d843d3","abstract_canon_sha256":"ce0f20aaa5dbbfa8c5677bd4e7b0f8eea2018709dcb198acdcb383f36edd644a"},"schema_version":"1.0"},"canonical_sha256":"0cd42ac51b31fcb04c5e4983649c93175ada6297af19de7be8ce1f875f37976f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:24:29.910469Z","signature_b64":"MGdzYx4EeNJdWS6ZD1edVCOPUVGR83TruXkq2U3zMr00L6idLjLHaUEzzf7zOeQsXZb5Rp+BeJ6C1msQf/1FDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cd42ac51b31fcb04c5e4983649c93175ada6297af19de7be8ce1f875f37976f","last_reissued_at":"2026-08-11T02:24:29.908766Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:24:29.908766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.09555","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":"2026-08-11T02:24:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OX14xPeSrKx8zeb1Mtv3Ob3MK6DXhx6/iSqtup9OGaBILuDwtR5UBl/oNYT6yjg/paa2BVX36vUsDbXWod74Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T03:46:01.969296Z"},"content_sha256":"b4bcd4723a9a6fbf47b4338f02dbb865087c6428b876618bda24614f4f0212b1","schema_version":"1.0","event_id":"sha256:b4bcd4723a9a6fbf47b4338f02dbb865087c6428b876618bda24614f4f0212b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BTKCVRI3GH6LATC6JGBWJHETC5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bidirectional Context Self-Distillation for Reinforcement Learning of Skill-Based LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chengfu Huo, Chengyu Wang, Hongda Wang, Jiarong Zhao, Lei Gao, Linbo Jin, Mengfei Song, Qiming Shi, Shaokang Fu, Tianjun Pan, Yuan Li","submitted_at":"2026-08-10T12:53:06Z","abstract_excerpt":"External natural-language skills provide large language model (LLM) agents with reusable and editable guidance for solving complex tasks. Yet their effectiveness depends not only on skill quality, but also on whether the policy can translate the provided guidance into appropriate actions. However, methods specifically designed to improve this skill-utilization ability remain largely underexplored. In practice, skill-based agents are commonly trained with reinforcement learning objectives centered on task-level rewards, which offer limited supervision and struggle to capture subtle differences "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09555","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/2608.09555/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":"2026-08-11T02:24:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wYEdaFOw2NkXNMVzj0MF0HXeVpJkZDaPN2b1H6YEPJKr7pzdT8bMBW61ZFVLvZFjNS6WgLt/MdzJoiDmSSJnDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T03:46:01.969673Z"},"content_sha256":"2c0b9d3915b6c1d697b3f1b6d4b686bac07ba246ce086cb5da15e9291adb6a9c","schema_version":"1.0","event_id":"sha256:2c0b9d3915b6c1d697b3f1b6d4b686bac07ba246ce086cb5da15e9291adb6a9c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BTKCVRI3GH6LATC6JGBWJHETC5/bundle.json","state_url":"https://pith.science/pith/BTKCVRI3GH6LATC6JGBWJHETC5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BTKCVRI3GH6LATC6JGBWJHETC5/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":"2026-08-13T03:46:01Z","links":{"resolver":"https://pith.science/pith/BTKCVRI3GH6LATC6JGBWJHETC5","bundle":"https://pith.science/pith/BTKCVRI3GH6LATC6JGBWJHETC5/bundle.json","state":"https://pith.science/pith/BTKCVRI3GH6LATC6JGBWJHETC5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BTKCVRI3GH6LATC6JGBWJHETC5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BTKCVRI3GH6LATC6JGBWJHETC5","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":"ce0f20aaa5dbbfa8c5677bd4e7b0f8eea2018709dcb198acdcb383f36edd644a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T12:53:06Z","title_canon_sha256":"6e04e203ae5ce73e8fa26dbfa9f56089574bee47a8a1a3352b7f11cd74d843d3"},"schema_version":"1.0","source":{"id":"2608.09555","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09555","created_at":"2026-08-11T02:24:29Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09555v1","created_at":"2026-08-11T02:24:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09555","created_at":"2026-08-11T02:24:29Z"},{"alias_kind":"pith_short_12","alias_value":"BTKCVRI3GH6L","created_at":"2026-08-11T02:24:29Z"},{"alias_kind":"pith_short_16","alias_value":"BTKCVRI3GH6LATC6","created_at":"2026-08-11T02:24:29Z"},{"alias_kind":"pith_short_8","alias_value":"BTKCVRI3","created_at":"2026-08-11T02:24:29Z"}],"graph_snapshots":[{"event_id":"sha256:2c0b9d3915b6c1d697b3f1b6d4b686bac07ba246ce086cb5da15e9291adb6a9c","target":"graph","created_at":"2026-08-11T02:24:29Z","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/2608.09555/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"External natural-language skills provide large language model (LLM) agents with reusable and editable guidance for solving complex tasks. Yet their effectiveness depends not only on skill quality, but also on whether the policy can translate the provided guidance into appropriate actions. However, methods specifically designed to improve this skill-utilization ability remain largely underexplored. In practice, skill-based agents are commonly trained with reinforcement learning objectives centered on task-level rewards, which offer limited supervision and struggle to capture subtle differences ","authors_text":"Chengfu Huo, Chengyu Wang, Hongda Wang, Jiarong Zhao, Lei Gao, Linbo Jin, Mengfei Song, Qiming Shi, Shaokang Fu, Tianjun Pan, Yuan Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T12:53:06Z","title":"Bidirectional Context Self-Distillation for Reinforcement Learning of Skill-Based LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09555","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:b4bcd4723a9a6fbf47b4338f02dbb865087c6428b876618bda24614f4f0212b1","target":"record","created_at":"2026-08-11T02:24:29Z","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":"ce0f20aaa5dbbfa8c5677bd4e7b0f8eea2018709dcb198acdcb383f36edd644a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T12:53:06Z","title_canon_sha256":"6e04e203ae5ce73e8fa26dbfa9f56089574bee47a8a1a3352b7f11cd74d843d3"},"schema_version":"1.0","source":{"id":"2608.09555","kind":"arxiv","version":1}},"canonical_sha256":"0cd42ac51b31fcb04c5e4983649c93175ada6297af19de7be8ce1f875f37976f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cd42ac51b31fcb04c5e4983649c93175ada6297af19de7be8ce1f875f37976f","first_computed_at":"2026-08-11T02:24:29.908766Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:24:29.908766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MGdzYx4EeNJdWS6ZD1edVCOPUVGR83TruXkq2U3zMr00L6idLjLHaUEzzf7zOeQsXZb5Rp+BeJ6C1msQf/1FDQ==","signature_status":"signed_v1","signed_at":"2026-08-11T02:24:29.910469Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.09555","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4bcd4723a9a6fbf47b4338f02dbb865087c6428b876618bda24614f4f0212b1","sha256:2c0b9d3915b6c1d697b3f1b6d4b686bac07ba246ce086cb5da15e9291adb6a9c"],"state_sha256":"d5bb28bd6672c87e6dbad5a3b7e88fc3a82669ca409e8c676758b06de4cc663f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XusNWklXi3t+IyTvIM8EKsOvEoMm5wmfl/AyoQuIbwjYTQmzetAb5Q9oQHj47Xu92DAwOoA9xYfNYobiRPBXCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T03:46:01.972144Z","bundle_sha256":"f431a4d43a74eed1d725eb46aa5a222a02a7ebbe0086c3a35f1b46dcfd0c8859"}}