{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FRVWKLNLTV4OXRTKKW3AK55UFS","short_pith_number":"pith:FRVWKLNL","canonical_record":{"source":{"id":"2605.30712","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T01:04:41Z","cross_cats_sorted":[],"title_canon_sha256":"e697f691f94a84319cc88e1d7f81a70d0a510a882007dcc5d2a51edd1d230bf5","abstract_canon_sha256":"3a6ff2ebeda9c6a4d393ae5d5641155a56f26323291f16ae994fe86479f4e299"},"schema_version":"1.0"},"canonical_sha256":"2c6b652dab9d78ebc66a55b60577b42c9f6a5297fd289777481c9dd5144ddc3e","source":{"kind":"arxiv","id":"2605.30712","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30712","created_at":"2026-06-01T01:03:11Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30712v1","created_at":"2026-06-01T01:03:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30712","created_at":"2026-06-01T01:03:11Z"},{"alias_kind":"pith_short_12","alias_value":"FRVWKLNLTV4O","created_at":"2026-06-01T01:03:11Z"},{"alias_kind":"pith_short_16","alias_value":"FRVWKLNLTV4OXRTK","created_at":"2026-06-01T01:03:11Z"},{"alias_kind":"pith_short_8","alias_value":"FRVWKLNL","created_at":"2026-06-01T01:03:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FRVWKLNLTV4OXRTKKW3AK55UFS","target":"record","payload":{"canonical_record":{"source":{"id":"2605.30712","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T01:04:41Z","cross_cats_sorted":[],"title_canon_sha256":"e697f691f94a84319cc88e1d7f81a70d0a510a882007dcc5d2a51edd1d230bf5","abstract_canon_sha256":"3a6ff2ebeda9c6a4d393ae5d5641155a56f26323291f16ae994fe86479f4e299"},"schema_version":"1.0"},"canonical_sha256":"2c6b652dab9d78ebc66a55b60577b42c9f6a5297fd289777481c9dd5144ddc3e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:11.759568Z","signature_b64":"+JHXRzAUPSffSsesGqJITu/QwLt6TydieBTXQlNZ+vsnAry8m2xPDnxcyLVyRR/bvRUaaOci1dUekCbGBJueCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c6b652dab9d78ebc66a55b60577b42c9f6a5297fd289777481c9dd5144ddc3e","last_reissued_at":"2026-06-01T01:03:11.758451Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:11.758451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.30712","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":"2026-06-01T01:03:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sis5guh2tfT9jEBdFH3VZIvrPLdi3ntoY00/G3yfB9+dZoDAXSjVzWpAmRrDtB9edUn3uZ/HvLHR7/hECrTUDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T21:50:51.035455Z"},"content_sha256":"e16af4551f1f65fc9504f5a5cae1582814726e5113c49618eca4a9bb94300622","schema_version":"1.0","event_id":"sha256:e16af4551f1f65fc9504f5a5cae1582814726e5113c49618eca4a9bb94300622"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FRVWKLNLTV4OXRTKKW3AK55UFS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chongrui Ye, Ge Liu, Haozhen Zhang, Jiaxuan You, Jingjun Xu, Shuang Yang, Tao Feng, Tianyang Luo, Xueqiang Xu, Yan Xie, Zhigang Hua","submitted_at":"2026-05-29T01:04:41Z","abstract_excerpt":"Large language model (LLM) agents have shown strong capabilities in reasoning, tool use, and multi-step interaction, but they often solve tasks from scratch and fail to reuse successful strategies or failure lessons from prior experience. Fine-tuning on collected experience can improve reuse, but it is inflexible when stronger or more suitable executors emerge. We propose ExpGraph, a model-agnostic experience learning framework that enables frozen and replaceable LLM executors to improve through external experience reuse without parameter updates. ExpGraph summarizes historical trajectories in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30712","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/2605.30712/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":"2026-06-01T01:03:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ldSXdIKje/EMM0LPsq0r08pVrJFWnbhCd7BYTD+61mG5alaZxggkGQjEpn0q819uxF2/8SU653Cyziy6vvtmBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T21:50:51.035819Z"},"content_sha256":"18664bc5f1ccd3cde64b30253dc6be8623a46e01bc4a929045fee91cb82325b0","schema_version":"1.0","event_id":"sha256:18664bc5f1ccd3cde64b30253dc6be8623a46e01bc4a929045fee91cb82325b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FRVWKLNLTV4OXRTKKW3AK55UFS/bundle.json","state_url":"https://pith.science/pith/FRVWKLNLTV4OXRTKKW3AK55UFS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FRVWKLNLTV4OXRTKKW3AK55UFS/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":"2026-06-01T21:50:51Z","links":{"resolver":"https://pith.science/pith/FRVWKLNLTV4OXRTKKW3AK55UFS","bundle":"https://pith.science/pith/FRVWKLNLTV4OXRTKKW3AK55UFS/bundle.json","state":"https://pith.science/pith/FRVWKLNLTV4OXRTKKW3AK55UFS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FRVWKLNLTV4OXRTKKW3AK55UFS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FRVWKLNLTV4OXRTKKW3AK55UFS","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":"3a6ff2ebeda9c6a4d393ae5d5641155a56f26323291f16ae994fe86479f4e299","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T01:04:41Z","title_canon_sha256":"e697f691f94a84319cc88e1d7f81a70d0a510a882007dcc5d2a51edd1d230bf5"},"schema_version":"1.0","source":{"id":"2605.30712","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30712","created_at":"2026-06-01T01:03:11Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30712v1","created_at":"2026-06-01T01:03:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30712","created_at":"2026-06-01T01:03:11Z"},{"alias_kind":"pith_short_12","alias_value":"FRVWKLNLTV4O","created_at":"2026-06-01T01:03:11Z"},{"alias_kind":"pith_short_16","alias_value":"FRVWKLNLTV4OXRTK","created_at":"2026-06-01T01:03:11Z"},{"alias_kind":"pith_short_8","alias_value":"FRVWKLNL","created_at":"2026-06-01T01:03:11Z"}],"graph_snapshots":[{"event_id":"sha256:18664bc5f1ccd3cde64b30253dc6be8623a46e01bc4a929045fee91cb82325b0","target":"graph","created_at":"2026-06-01T01:03:11Z","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/2605.30712/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM) agents have shown strong capabilities in reasoning, tool use, and multi-step interaction, but they often solve tasks from scratch and fail to reuse successful strategies or failure lessons from prior experience. Fine-tuning on collected experience can improve reuse, but it is inflexible when stronger or more suitable executors emerge. We propose ExpGraph, a model-agnostic experience learning framework that enables frozen and replaceable LLM executors to improve through external experience reuse without parameter updates. ExpGraph summarizes historical trajectories in","authors_text":"Chongrui Ye, Ge Liu, Haozhen Zhang, Jiaxuan You, Jingjun Xu, Shuang Yang, Tao Feng, Tianyang Luo, Xueqiang Xu, Yan Xie, Zhigang Hua","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T01:04:41Z","title":"ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30712","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:e16af4551f1f65fc9504f5a5cae1582814726e5113c49618eca4a9bb94300622","target":"record","created_at":"2026-06-01T01:03:11Z","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":"3a6ff2ebeda9c6a4d393ae5d5641155a56f26323291f16ae994fe86479f4e299","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T01:04:41Z","title_canon_sha256":"e697f691f94a84319cc88e1d7f81a70d0a510a882007dcc5d2a51edd1d230bf5"},"schema_version":"1.0","source":{"id":"2605.30712","kind":"arxiv","version":1}},"canonical_sha256":"2c6b652dab9d78ebc66a55b60577b42c9f6a5297fd289777481c9dd5144ddc3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c6b652dab9d78ebc66a55b60577b42c9f6a5297fd289777481c9dd5144ddc3e","first_computed_at":"2026-06-01T01:03:11.758451Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:11.758451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+JHXRzAUPSffSsesGqJITu/QwLt6TydieBTXQlNZ+vsnAry8m2xPDnxcyLVyRR/bvRUaaOci1dUekCbGBJueCw==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:11.759568Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30712","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e16af4551f1f65fc9504f5a5cae1582814726e5113c49618eca4a9bb94300622","sha256:18664bc5f1ccd3cde64b30253dc6be8623a46e01bc4a929045fee91cb82325b0"],"state_sha256":"c62758ccb699ee461cdda9c9f650e197996e3936464c30b9b1e343dc6f206bde"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FVhMhWC+BjIlP337+csQoFLbSUqMfMT8BC1/zhuHOC4Q+C5+4kVIzSmnxr/IXm+yoP9AwJHE5NuGhHC5gWTWAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T21:50:51.037869Z","bundle_sha256":"e61bc5db10be5f6034930cebef67265a13170c9e300d1217288507333ede6c2a"}}