{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KDMIU4AROC7ML2AZBRZZMZYCAC","short_pith_number":"pith:KDMIU4AR","canonical_record":{"source":{"id":"2605.28918","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T17:57:43Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"f540683a55d2fd48830c428694a4fc56de7f9bf3beb4fab7eb5006681e2f3c25","abstract_canon_sha256":"8f9d091625e0debafd3b8bdc0003c8c4e725b67b48b299974331c2fd6cf2a1a0"},"schema_version":"1.0"},"canonical_sha256":"50d88a701170bec5e8190c7396670200856a5ae6a2df5dc15ab2b1e4f75baa82","source":{"kind":"arxiv","id":"2605.28918","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28918","created_at":"2026-05-29T00:04:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28918v1","created_at":"2026-05-29T00:04:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28918","created_at":"2026-05-29T00:04:16Z"},{"alias_kind":"pith_short_12","alias_value":"KDMIU4AROC7M","created_at":"2026-05-29T00:04:16Z"},{"alias_kind":"pith_short_16","alias_value":"KDMIU4AROC7ML2AZ","created_at":"2026-05-29T00:04:16Z"},{"alias_kind":"pith_short_8","alias_value":"KDMIU4AR","created_at":"2026-05-29T00:04:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KDMIU4AROC7ML2AZBRZZMZYCAC","target":"record","payload":{"canonical_record":{"source":{"id":"2605.28918","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T17:57:43Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"f540683a55d2fd48830c428694a4fc56de7f9bf3beb4fab7eb5006681e2f3c25","abstract_canon_sha256":"8f9d091625e0debafd3b8bdc0003c8c4e725b67b48b299974331c2fd6cf2a1a0"},"schema_version":"1.0"},"canonical_sha256":"50d88a701170bec5e8190c7396670200856a5ae6a2df5dc15ab2b1e4f75baa82","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T00:04:16.529002Z","signature_b64":"5gTQaIffv+ak0QF4xmKdaSzLRBIBMKtXci5rHS1+E7aZc6jJbRFssAN7dbIWuCkSSR8mHa0j3fEWE8vAplpYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50d88a701170bec5e8190c7396670200856a5ae6a2df5dc15ab2b1e4f75baa82","last_reissued_at":"2026-05-29T00:04:16.528510Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T00:04:16.528510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.28918","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":"2026-05-29T00:04:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pE2MPpE3Qt+KjLRXi+XZn9owBBeslGjpDC8aWOzGpnGJwoJQSVn0ek6k7SWr2fALoF2CHjk04Y4SvQJpBCriDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T19:43:06.449602Z"},"content_sha256":"a6b6700520148c5e089a50663e82148396d82a44e10fdbd247f09e090ea4f268","schema_version":"1.0","event_id":"sha256:a6b6700520148c5e089a50663e82148396d82a44e10fdbd247f09e090ea4f268"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KDMIU4AROC7ML2AZBRZZMZYCAC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Bowen Liu, Dingyan Shang, Xuan Liu, Youting Wang, Yuan Tang","submitted_at":"2026-05-27T17:57:43Z","abstract_excerpt":"For sparse, structured reinforcement-learning tasks with semantic reward-function interfaces, LLM-generated reward shaping is better framed as debugging than one-shot generation. We study PPO-trained agents using MiniGrid as core evaluation and MuJoCo as boundary stress test. Our audit finds two dominant one-shot failure modes -- reward flooding and semantic/API misunderstanding -- plus a rarer weak-shaping case. We propose diagnostic-driven iterative refinement, where training diagnostics and a failure-mode taxonomy guide targeted reward-function revision. Refinement improves DoorKey-8x8 from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28918","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/2605.28918/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":"2026-05-29T00:04:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ly9C80ObpYW21hLvOIIuG01ir++CBGPZyIknnZqRPOCjJmiPkBQEcsyqlIVrbWDK/Dw11Uv3noZ7aUKJej80AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T19:43:06.449979Z"},"content_sha256":"9119a4f9dda02005375ab1062c602f85b110266eb882757a5df63cc7f6046232","schema_version":"1.0","event_id":"sha256:9119a4f9dda02005375ab1062c602f85b110266eb882757a5df63cc7f6046232"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KDMIU4AROC7ML2AZBRZZMZYCAC/bundle.json","state_url":"https://pith.science/pith/KDMIU4AROC7ML2AZBRZZMZYCAC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KDMIU4AROC7ML2AZBRZZMZYCAC/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":"2026-06-29T19:43:06Z","links":{"resolver":"https://pith.science/pith/KDMIU4AROC7ML2AZBRZZMZYCAC","bundle":"https://pith.science/pith/KDMIU4AROC7ML2AZBRZZMZYCAC/bundle.json","state":"https://pith.science/pith/KDMIU4AROC7ML2AZBRZZMZYCAC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KDMIU4AROC7ML2AZBRZZMZYCAC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KDMIU4AROC7ML2AZBRZZMZYCAC","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":"8f9d091625e0debafd3b8bdc0003c8c4e725b67b48b299974331c2fd6cf2a1a0","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T17:57:43Z","title_canon_sha256":"f540683a55d2fd48830c428694a4fc56de7f9bf3beb4fab7eb5006681e2f3c25"},"schema_version":"1.0","source":{"id":"2605.28918","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28918","created_at":"2026-05-29T00:04:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28918v1","created_at":"2026-05-29T00:04:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28918","created_at":"2026-05-29T00:04:16Z"},{"alias_kind":"pith_short_12","alias_value":"KDMIU4AROC7M","created_at":"2026-05-29T00:04:16Z"},{"alias_kind":"pith_short_16","alias_value":"KDMIU4AROC7ML2AZ","created_at":"2026-05-29T00:04:16Z"},{"alias_kind":"pith_short_8","alias_value":"KDMIU4AR","created_at":"2026-05-29T00:04:16Z"}],"graph_snapshots":[{"event_id":"sha256:9119a4f9dda02005375ab1062c602f85b110266eb882757a5df63cc7f6046232","target":"graph","created_at":"2026-05-29T00:04:16Z","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/2605.28918/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For sparse, structured reinforcement-learning tasks with semantic reward-function interfaces, LLM-generated reward shaping is better framed as debugging than one-shot generation. We study PPO-trained agents using MiniGrid as core evaluation and MuJoCo as boundary stress test. Our audit finds two dominant one-shot failure modes -- reward flooding and semantic/API misunderstanding -- plus a rarer weak-shaping case. We propose diagnostic-driven iterative refinement, where training diagnostics and a failure-mode taxonomy guide targeted reward-function revision. Refinement improves DoorKey-8x8 from","authors_text":"Bowen Liu, Dingyan Shang, Xuan Liu, Youting Wang, Yuan Tang","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T17:57:43Z","title":"When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28918","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:a6b6700520148c5e089a50663e82148396d82a44e10fdbd247f09e090ea4f268","target":"record","created_at":"2026-05-29T00:04:16Z","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":"8f9d091625e0debafd3b8bdc0003c8c4e725b67b48b299974331c2fd6cf2a1a0","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T17:57:43Z","title_canon_sha256":"f540683a55d2fd48830c428694a4fc56de7f9bf3beb4fab7eb5006681e2f3c25"},"schema_version":"1.0","source":{"id":"2605.28918","kind":"arxiv","version":1}},"canonical_sha256":"50d88a701170bec5e8190c7396670200856a5ae6a2df5dc15ab2b1e4f75baa82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50d88a701170bec5e8190c7396670200856a5ae6a2df5dc15ab2b1e4f75baa82","first_computed_at":"2026-05-29T00:04:16.528510Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T00:04:16.528510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5gTQaIffv+ak0QF4xmKdaSzLRBIBMKtXci5rHS1+E7aZc6jJbRFssAN7dbIWuCkSSR8mHa0j3fEWE8vAplpYBg==","signature_status":"signed_v1","signed_at":"2026-05-29T00:04:16.529002Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28918","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6b6700520148c5e089a50663e82148396d82a44e10fdbd247f09e090ea4f268","sha256:9119a4f9dda02005375ab1062c602f85b110266eb882757a5df63cc7f6046232"],"state_sha256":"f62506bda196c7331aa1e820cc5546f581afbebc96624daf43222a3bf91a9e05"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jgFJYMsMJQZ+mK/kdLXfck+ZieqqjLho6tj8eoqKxll2u/EcnO01bgcT1zz/FQNlmSqWgXZNts/w47jS3Go+Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T19:43:06.451974Z","bundle_sha256":"38bf6ed74c71c2b497d50ef1fb62e627a2ab5a3a6de6177c5ac73fbd412991a3"}}