{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LOB7LANO7WPL6FWZWNTZM6XWFQ","short_pith_number":"pith:LOB7LANO","canonical_record":{"source":{"id":"2608.03223","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T06:56:47Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"921cbd13b831a249b27d11aa443fdeaf2025a2b18a7a68b371c054242f5c5a0c","abstract_canon_sha256":"ece4f74cefbc25e1d07ce25a093301d8322afa747386cd298827148169543d2c"},"schema_version":"1.0"},"canonical_sha256":"5b83f581aefd9ebf16d9b367967af62c2005965cb951e02ab7ae08278533a55c","source":{"kind":"arxiv","id":"2608.03223","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03223","created_at":"2026-08-05T00:46:19Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03223v1","created_at":"2026-08-05T00:46:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03223","created_at":"2026-08-05T00:46:19Z"},{"alias_kind":"pith_short_12","alias_value":"LOB7LANO7WPL","created_at":"2026-08-05T00:46:19Z"},{"alias_kind":"pith_short_16","alias_value":"LOB7LANO7WPL6FWZ","created_at":"2026-08-05T00:46:19Z"},{"alias_kind":"pith_short_8","alias_value":"LOB7LANO","created_at":"2026-08-05T00:46:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LOB7LANO7WPL6FWZWNTZM6XWFQ","target":"record","payload":{"canonical_record":{"source":{"id":"2608.03223","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T06:56:47Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"921cbd13b831a249b27d11aa443fdeaf2025a2b18a7a68b371c054242f5c5a0c","abstract_canon_sha256":"ece4f74cefbc25e1d07ce25a093301d8322afa747386cd298827148169543d2c"},"schema_version":"1.0"},"canonical_sha256":"5b83f581aefd9ebf16d9b367967af62c2005965cb951e02ab7ae08278533a55c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:46:19.196340Z","signature_b64":"fKOG6urzcACLI8KW/pE+jBq6mX/JpDKnM57+iUA88NV8Qr4kKNlbcmsmIzQPQMWG8eZxPUgS4Ek9PsYgK6xHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b83f581aefd9ebf16d9b367967af62c2005965cb951e02ab7ae08278533a55c","last_reissued_at":"2026-08-05T00:46:19.193946Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:46:19.193946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.03223","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":"2026-08-05T00:46:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fWC9WopHILdhRoixzQIVgCzvf8UU7gHCPrbLyJ8501CE5J/YI2mxon5oWknV4R5rqv+asUh6MoUuT41318vACw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T03:55:25.988167Z"},"content_sha256":"42ae4f054a00355172275b2f0d32b18cd609d744357aaf513387059e41ec8de3","schema_version":"1.0","event_id":"sha256:42ae4f054a00355172275b2f0d32b18cd609d744357aaf513387059e41ec8de3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LOB7LANO7WPL6FWZWNTZM6XWFQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Agentic Reinforcement Learning with Self-Distilled Reward Shaping","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Chao Wang, Chenshaodong, Guinan Chen, Jinghao Lin, Ranxu zhang, Sunzhe, Xiaozhou Xu, Yanyong Zhang","submitted_at":"2026-08-04T06:56:47Z","abstract_excerpt":"Agentic reinforcement learning enables LLM agents to learn through interaction, but sparse trajectory-level rewards reveal success without identifying which intermediate decisions deserve credit. Training-only privileged skills can provide denser supervision by allowing the same frozen policy snapshot to rescore fixed tokens from skill-free trajectories while conditioned on task-matched procedural skills. Existing methods, however, do not jointly calibrate teacher scores across interaction steps, relate teacher confidence to realized returns, and integrate the resulting signal into native rewa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03223","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/2608.03223/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":"2026-08-05T00:46:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tqHfMek1+iIVM1xZATocaM1GMGlvZytHDAF7z7J7Ls28ebCazqaDeOv7hJQhjmSjQiJIIUMoZibMPDOPCwhpBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T03:55:25.988640Z"},"content_sha256":"9c240e0c581140d075c16c489951ddab27e0aeef7bec044f744dc7513021a68a","schema_version":"1.0","event_id":"sha256:9c240e0c581140d075c16c489951ddab27e0aeef7bec044f744dc7513021a68a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LOB7LANO7WPL6FWZWNTZM6XWFQ/bundle.json","state_url":"https://pith.science/pith/LOB7LANO7WPL6FWZWNTZM6XWFQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LOB7LANO7WPL6FWZWNTZM6XWFQ/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":"2026-08-07T03:55:25Z","links":{"resolver":"https://pith.science/pith/LOB7LANO7WPL6FWZWNTZM6XWFQ","bundle":"https://pith.science/pith/LOB7LANO7WPL6FWZWNTZM6XWFQ/bundle.json","state":"https://pith.science/pith/LOB7LANO7WPL6FWZWNTZM6XWFQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LOB7LANO7WPL6FWZWNTZM6XWFQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LOB7LANO7WPL6FWZWNTZM6XWFQ","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":"ece4f74cefbc25e1d07ce25a093301d8322afa747386cd298827148169543d2c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T06:56:47Z","title_canon_sha256":"921cbd13b831a249b27d11aa443fdeaf2025a2b18a7a68b371c054242f5c5a0c"},"schema_version":"1.0","source":{"id":"2608.03223","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03223","created_at":"2026-08-05T00:46:19Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03223v1","created_at":"2026-08-05T00:46:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03223","created_at":"2026-08-05T00:46:19Z"},{"alias_kind":"pith_short_12","alias_value":"LOB7LANO7WPL","created_at":"2026-08-05T00:46:19Z"},{"alias_kind":"pith_short_16","alias_value":"LOB7LANO7WPL6FWZ","created_at":"2026-08-05T00:46:19Z"},{"alias_kind":"pith_short_8","alias_value":"LOB7LANO","created_at":"2026-08-05T00:46:19Z"}],"graph_snapshots":[{"event_id":"sha256:9c240e0c581140d075c16c489951ddab27e0aeef7bec044f744dc7513021a68a","target":"graph","created_at":"2026-08-05T00:46:19Z","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/2608.03223/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agentic reinforcement learning enables LLM agents to learn through interaction, but sparse trajectory-level rewards reveal success without identifying which intermediate decisions deserve credit. Training-only privileged skills can provide denser supervision by allowing the same frozen policy snapshot to rescore fixed tokens from skill-free trajectories while conditioned on task-matched procedural skills. Existing methods, however, do not jointly calibrate teacher scores across interaction steps, relate teacher confidence to realized returns, and integrate the resulting signal into native rewa","authors_text":"Chao Wang, Chenshaodong, Guinan Chen, Jinghao Lin, Ranxu zhang, Sunzhe, Xiaozhou Xu, Yanyong Zhang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T06:56:47Z","title":"Agentic Reinforcement Learning with Self-Distilled Reward Shaping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03223","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":"sha256:42ae4f054a00355172275b2f0d32b18cd609d744357aaf513387059e41ec8de3","target":"record","created_at":"2026-08-05T00:46:19Z","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":"ece4f74cefbc25e1d07ce25a093301d8322afa747386cd298827148169543d2c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T06:56:47Z","title_canon_sha256":"921cbd13b831a249b27d11aa443fdeaf2025a2b18a7a68b371c054242f5c5a0c"},"schema_version":"1.0","source":{"id":"2608.03223","kind":"arxiv","version":1}},"canonical_sha256":"5b83f581aefd9ebf16d9b367967af62c2005965cb951e02ab7ae08278533a55c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b83f581aefd9ebf16d9b367967af62c2005965cb951e02ab7ae08278533a55c","first_computed_at":"2026-08-05T00:46:19.193946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:46:19.193946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fKOG6urzcACLI8KW/pE+jBq6mX/JpDKnM57+iUA88NV8Qr4kKNlbcmsmIzQPQMWG8eZxPUgS4Ek9PsYgK6xHAg==","signature_status":"signed_v1","signed_at":"2026-08-05T00:46:19.196340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03223","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42ae4f054a00355172275b2f0d32b18cd609d744357aaf513387059e41ec8de3","sha256:9c240e0c581140d075c16c489951ddab27e0aeef7bec044f744dc7513021a68a"],"state_sha256":"8445496e706363e6facc3d12825d2bb3941657aa9c930341ae0d79e81c1797b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VVdObxAFRfr3J+I+tCKrkNsZEcep7RiixxBuPMSsK60U2lGn9panqAI7d2iiATqPBDFxa3d9tGT/3Eh16c8HAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T03:55:25.992681Z","bundle_sha256":"b3ea2a684c48573a1b6e6666082c0237c261308be64b3634ba9584e3d0328d74"}}