{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WAUSLUAQQUZJFKKWGUD5PMUANU","short_pith_number":"pith:WAUSLUAQ","canonical_record":{"source":{"id":"2509.03990","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-04T08:18:39Z","cross_cats_sorted":[],"title_canon_sha256":"7a989144baec7f949bf8dad8fdaf2f47e4a915dd28d280d5d45c308571c843da","abstract_canon_sha256":"1b4899564f087c001c7ec88713c7b63ba9cf20534d5d2e41c4d1b90c0519f45c"},"schema_version":"1.0"},"canonical_sha256":"b02925d010853292a9563507d7b2806d388d6ffd23bce1d5749b64c294f97b27","source":{"kind":"arxiv","id":"2509.03990","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.03990","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"arxiv_version","alias_value":"2509.03990v2","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03990","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"pith_short_12","alias_value":"WAUSLUAQQUZJ","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"pith_short_16","alias_value":"WAUSLUAQQUZJFKKW","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"pith_short_8","alias_value":"WAUSLUAQ","created_at":"2026-07-05T12:06:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WAUSLUAQQUZJFKKWGUD5PMUANU","target":"record","payload":{"canonical_record":{"source":{"id":"2509.03990","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-04T08:18:39Z","cross_cats_sorted":[],"title_canon_sha256":"7a989144baec7f949bf8dad8fdaf2f47e4a915dd28d280d5d45c308571c843da","abstract_canon_sha256":"1b4899564f087c001c7ec88713c7b63ba9cf20534d5d2e41c4d1b90c0519f45c"},"schema_version":"1.0"},"canonical_sha256":"b02925d010853292a9563507d7b2806d388d6ffd23bce1d5749b64c294f97b27","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:20.325493Z","signature_b64":"CSzbaYl2bquUfAPsr2PSGYPCCLKyqp7JVXiyChX6+CI/64HlsLO/ESwwQG8WwaOTCWk85B03jdytFz7iuzHDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b02925d010853292a9563507d7b2806d388d6ffd23bce1d5749b64c294f97b27","last_reissued_at":"2026-07-05T12:06:20.324989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:20.324989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.03990","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":"PGV2gM7LiYeXqF8NiXfP5iEd7caBW6Iq00cukNUz8bdXU40ybkQimzkgqLMRmVLgt+uquBPvMdDLQgfZlZmpBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:26:57.060868Z"},"content_sha256":"ba6ec7c6cd5c3cbf31affcb091902fffd974d2874eb1849e5da4d52241621711","schema_version":"1.0","event_id":"sha256:ba6ec7c6cd5c3cbf31affcb091902fffd974d2874eb1849e5da4d52241621711"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WAUSLUAQQUZJFKKWGUD5PMUANU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chunlong Wu, Min Wang, Ye Luo, Zhibo Qu","submitted_at":"2025-09-04T08:18:39Z","abstract_excerpt":"Large language model (LLM) agents achieve impressive single-task performance but commonly exhibit repeated failures, inefficient exploration, and limited cross-task adaptability. Existing reflective strategies (e.g., Reflexion, ReAct) improve per-episode behavior but typically produce ephemeral, task-specific traces that are not reused across tasks. Reinforcement-learning based alternatives can produce transferable policies but require substantial parameter updates and compute. In this work we introduce Meta-Policy Reflexion (MPR): a hybrid framework that consolidates LLM-generated reflections"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03990","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/2509.03990/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":"n93v8IX9TNWYI5oh1W5LDOZzbyb24KDRjkn8NyCHRxsW69Kwklna8bsaI4GOaOHOZCzpeEIUWI4OeZJvmPjIAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:26:57.061392Z"},"content_sha256":"c092cce58f8321b35bff356ea3589d7e53ce5ff9a06d100afe9add868f01a54d","schema_version":"1.0","event_id":"sha256:c092cce58f8321b35bff356ea3589d7e53ce5ff9a06d100afe9add868f01a54d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WAUSLUAQQUZJFKKWGUD5PMUANU/bundle.json","state_url":"https://pith.science/pith/WAUSLUAQQUZJFKKWGUD5PMUANU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WAUSLUAQQUZJFKKWGUD5PMUANU/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":"2026-08-19T05:26:57Z","links":{"resolver":"https://pith.science/pith/WAUSLUAQQUZJFKKWGUD5PMUANU","bundle":"https://pith.science/pith/WAUSLUAQQUZJFKKWGUD5PMUANU/bundle.json","state":"https://pith.science/pith/WAUSLUAQQUZJFKKWGUD5PMUANU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WAUSLUAQQUZJFKKWGUD5PMUANU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WAUSLUAQQUZJFKKWGUD5PMUANU","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":"1b4899564f087c001c7ec88713c7b63ba9cf20534d5d2e41c4d1b90c0519f45c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-04T08:18:39Z","title_canon_sha256":"7a989144baec7f949bf8dad8fdaf2f47e4a915dd28d280d5d45c308571c843da"},"schema_version":"1.0","source":{"id":"2509.03990","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.03990","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"arxiv_version","alias_value":"2509.03990v2","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03990","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"pith_short_12","alias_value":"WAUSLUAQQUZJ","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"pith_short_16","alias_value":"WAUSLUAQQUZJFKKW","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"pith_short_8","alias_value":"WAUSLUAQ","created_at":"2026-07-05T12:06:20Z"}],"graph_snapshots":[{"event_id":"sha256:c092cce58f8321b35bff356ea3589d7e53ce5ff9a06d100afe9add868f01a54d","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/2509.03990/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM) agents achieve impressive single-task performance but commonly exhibit repeated failures, inefficient exploration, and limited cross-task adaptability. Existing reflective strategies (e.g., Reflexion, ReAct) improve per-episode behavior but typically produce ephemeral, task-specific traces that are not reused across tasks. Reinforcement-learning based alternatives can produce transferable policies but require substantial parameter updates and compute. In this work we introduce Meta-Policy Reflexion (MPR): a hybrid framework that consolidates LLM-generated reflections","authors_text":"Chunlong Wu, Min Wang, Ye Luo, Zhibo Qu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-04T08:18:39Z","title":"Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03990","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:ba6ec7c6cd5c3cbf31affcb091902fffd974d2874eb1849e5da4d52241621711","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":"1b4899564f087c001c7ec88713c7b63ba9cf20534d5d2e41c4d1b90c0519f45c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-04T08:18:39Z","title_canon_sha256":"7a989144baec7f949bf8dad8fdaf2f47e4a915dd28d280d5d45c308571c843da"},"schema_version":"1.0","source":{"id":"2509.03990","kind":"arxiv","version":2}},"canonical_sha256":"b02925d010853292a9563507d7b2806d388d6ffd23bce1d5749b64c294f97b27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b02925d010853292a9563507d7b2806d388d6ffd23bce1d5749b64c294f97b27","first_computed_at":"2026-07-05T12:06:20.324989Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:20.324989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CSzbaYl2bquUfAPsr2PSGYPCCLKyqp7JVXiyChX6+CI/64HlsLO/ESwwQG8WwaOTCWk85B03jdytFz7iuzHDDw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:20.325493Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.03990","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba6ec7c6cd5c3cbf31affcb091902fffd974d2874eb1849e5da4d52241621711","sha256:c092cce58f8321b35bff356ea3589d7e53ce5ff9a06d100afe9add868f01a54d"],"state_sha256":"b3fe942bc36185a3523338e5cfd661604c3fa99dea7c2d9159a86ffcd0c6500d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6/72APLt+LdrffXpG+foPsvrKmNYlY/K3GXGR2tZ7f4RrUwZYnapfZqoJDOE2ZJckZXVYEjFONVUjaZo/XzSBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T05:26:57.063812Z","bundle_sha256":"2d0ca633fd234dd2b69dc7a719cf6c2d043d148602734ac4e0280f55859f58a2"}}