{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EOLHNYZROGPKAYAZNYAAAPIBN6","short_pith_number":"pith:EOLHNYZR","canonical_record":{"source":{"id":"2602.01869","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-02T09:43:12Z","cross_cats_sorted":[],"title_canon_sha256":"9ce1cd3f78023a14abbe6a6e7c1681d1c7ddec483468097ab271327fdc2adcd2","abstract_canon_sha256":"090d34ac9a4679279642127a2cbb9daaa4c455584eeaf648ab6633dacac456bc"},"schema_version":"1.0"},"canonical_sha256":"239676e331719ea060196e00003d016f82e0522ee7e3604846dd9ff2c7445ab2","source":{"kind":"arxiv","id":"2602.01869","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.01869","created_at":"2026-05-29T02:05:40Z"},{"alias_kind":"arxiv_version","alias_value":"2602.01869v3","created_at":"2026-05-29T02:05:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.01869","created_at":"2026-05-29T02:05:40Z"},{"alias_kind":"pith_short_12","alias_value":"EOLHNYZROGPK","created_at":"2026-05-29T02:05:40Z"},{"alias_kind":"pith_short_16","alias_value":"EOLHNYZROGPKAYAZ","created_at":"2026-05-29T02:05:40Z"},{"alias_kind":"pith_short_8","alias_value":"EOLHNYZR","created_at":"2026-05-29T02:05:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EOLHNYZROGPKAYAZNYAAAPIBN6","target":"record","payload":{"canonical_record":{"source":{"id":"2602.01869","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-02T09:43:12Z","cross_cats_sorted":[],"title_canon_sha256":"9ce1cd3f78023a14abbe6a6e7c1681d1c7ddec483468097ab271327fdc2adcd2","abstract_canon_sha256":"090d34ac9a4679279642127a2cbb9daaa4c455584eeaf648ab6633dacac456bc"},"schema_version":"1.0"},"canonical_sha256":"239676e331719ea060196e00003d016f82e0522ee7e3604846dd9ff2c7445ab2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:40.216743Z","signature_b64":"N5CLOyQBqnqyE1lAKbgURtc6m9A//R2E+KYwVRzKNgg5Z2sDOq43VgB7H7dBM9YJceqVSoGN97ZHUo42FsqqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"239676e331719ea060196e00003d016f82e0522ee7e3604846dd9ff2c7445ab2","last_reissued_at":"2026-05-29T02:05:40.216021Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:40.216021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.01869","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T02:05:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1BxVwDKOAg7NdbWwvPnoZ06hP9f4YWKYbawcpSOd1qtnABNRhJP8pahYrjfc0AtjjdUuQztMqpKaGPDd12ViDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:11:12.018886Z"},"content_sha256":"336ea54cf15e16e6b413bcd1df3a79f2032d2c19ed9f075b15b1a0e080e0a829","schema_version":"1.0","event_id":"sha256:336ea54cf15e16e6b413bcd1df3a79f2032d2c19ed9f075b15b1a0e080e0a829"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EOLHNYZROGPKAYAZNYAAAPIBN6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Skill-Pro lets LLM agents learn reusable procedural skills from past experiences without updating any parameters.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haifeng Zhang, Haoxuan Li, Jun Wang, Mengyue Yang, Qirui Mi, Yisen Wang, Zhijian Ma","submitted_at":"2026-02-02T09:43:12Z","abstract_excerpt":"LLM-driven agents excel at sequential decision-making but often rely on on-the-fly reasoning, re-deriving solutions even in recurring scenarios. This insufficient experience reuse leads to computational redundancy and instability. To bridge this gap, we propose Skill-Pro, a framework enabling agents to autonomously learn reusable procedural skills from interaction experiences without parameter updates. By formalizing a Skill-MDP, Skill-Pro transforms passive episodic narratives into executable Skills defined by activation, execution, and termination conditions to ensure executability. To achie"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Skill-Pro achieves superior reuse rates and significant performance gains with extreme memory compression by autonomously learning reusable procedural skills from interaction experiences without parameter updates, using Skill-MDP formalization and Non-Parametric PPO for reliable verification.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That semantic gradients combined with a PPO Gate can generate and verify high-quality skills that remain executable and non-degrading across recurring scenarios without any post-hoc exclusions or capability loss.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Skill-Pro enables LLM agents to autonomously learn, verify, and reuse compact procedural skills from experience via a Skill-MDP formalization and Non-Parametric PPO, yielding higher reuse rates, performance gains, and extreme memory compression across in-domain, cross-task, and cross-agent settings.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Skill-Pro lets LLM agents learn reusable procedural skills from past experiences without updating any parameters.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cfdb92aac6ed8d7fea254fb87fc5088033ab64844870fb551b448d279863cb37"},"source":{"id":"2602.01869","kind":"arxiv","version":3},"verdict":{"id":"de1adf4e-d978-4769-bb94-7f76d07fb912","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T08:31:09.441739Z","strongest_claim":"Skill-Pro achieves superior reuse rates and significant performance gains with extreme memory compression by autonomously learning reusable procedural skills from interaction experiences without parameter updates, using Skill-MDP formalization and Non-Parametric PPO for reliable verification.","one_line_summary":"Skill-Pro enables LLM agents to autonomously learn, verify, and reuse compact procedural skills from experience via a Skill-MDP formalization and Non-Parametric PPO, yielding higher reuse rates, performance gains, and extreme memory compression across in-domain, cross-task, and cross-agent settings.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That semantic gradients combined with a PPO Gate can generate and verify high-quality skills that remain executable and non-degrading across recurring scenarios without any post-hoc exclusions or capability loss.","pith_extraction_headline":"Skill-Pro lets LLM agents learn reusable procedural skills from past experiences without updating any parameters."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.01869/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":"de1adf4e-d978-4769-bb94-7f76d07fb912"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T02:05:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AA1jbcjBQtPUQCyfe22poje81Cg3qDUFKLEjqVUVcelhpEMKt0+Saf/t5r19HbGHlzbH505ZaGzH0Fm0GokZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:11:12.019537Z"},"content_sha256":"ee3b25f0d7bdcb2e9a751eeb92f2dab19a2339d64d2b438c34762b6ec099dde0","schema_version":"1.0","event_id":"sha256:ee3b25f0d7bdcb2e9a751eeb92f2dab19a2339d64d2b438c34762b6ec099dde0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EOLHNYZROGPKAYAZNYAAAPIBN6/bundle.json","state_url":"https://pith.science/pith/EOLHNYZROGPKAYAZNYAAAPIBN6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EOLHNYZROGPKAYAZNYAAAPIBN6/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":"2026-08-04T15:11:12Z","links":{"resolver":"https://pith.science/pith/EOLHNYZROGPKAYAZNYAAAPIBN6","bundle":"https://pith.science/pith/EOLHNYZROGPKAYAZNYAAAPIBN6/bundle.json","state":"https://pith.science/pith/EOLHNYZROGPKAYAZNYAAAPIBN6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EOLHNYZROGPKAYAZNYAAAPIBN6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EOLHNYZROGPKAYAZNYAAAPIBN6","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":"090d34ac9a4679279642127a2cbb9daaa4c455584eeaf648ab6633dacac456bc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-02T09:43:12Z","title_canon_sha256":"9ce1cd3f78023a14abbe6a6e7c1681d1c7ddec483468097ab271327fdc2adcd2"},"schema_version":"1.0","source":{"id":"2602.01869","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.01869","created_at":"2026-05-29T02:05:40Z"},{"alias_kind":"arxiv_version","alias_value":"2602.01869v3","created_at":"2026-05-29T02:05:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.01869","created_at":"2026-05-29T02:05:40Z"},{"alias_kind":"pith_short_12","alias_value":"EOLHNYZROGPK","created_at":"2026-05-29T02:05:40Z"},{"alias_kind":"pith_short_16","alias_value":"EOLHNYZROGPKAYAZ","created_at":"2026-05-29T02:05:40Z"},{"alias_kind":"pith_short_8","alias_value":"EOLHNYZR","created_at":"2026-05-29T02:05:40Z"}],"graph_snapshots":[{"event_id":"sha256:ee3b25f0d7bdcb2e9a751eeb92f2dab19a2339d64d2b438c34762b6ec099dde0","target":"graph","created_at":"2026-05-29T02:05:40Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Skill-Pro achieves superior reuse rates and significant performance gains with extreme memory compression by autonomously learning reusable procedural skills from interaction experiences without parameter updates, using Skill-MDP formalization and Non-Parametric PPO for reliable verification."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That semantic gradients combined with a PPO Gate can generate and verify high-quality skills that remain executable and non-degrading across recurring scenarios without any post-hoc exclusions or capability loss."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Skill-Pro enables LLM agents to autonomously learn, verify, and reuse compact procedural skills from experience via a Skill-MDP formalization and Non-Parametric PPO, yielding higher reuse rates, performance gains, and extreme memory compression across in-domain, cross-task, and cross-agent settings."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Skill-Pro lets LLM agents learn reusable procedural skills from past experiences without updating any parameters."}],"snapshot_sha256":"cfdb92aac6ed8d7fea254fb87fc5088033ab64844870fb551b448d279863cb37"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.01869/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM-driven agents excel at sequential decision-making but often rely on on-the-fly reasoning, re-deriving solutions even in recurring scenarios. This insufficient experience reuse leads to computational redundancy and instability. To bridge this gap, we propose Skill-Pro, a framework enabling agents to autonomously learn reusable procedural skills from interaction experiences without parameter updates. By formalizing a Skill-MDP, Skill-Pro transforms passive episodic narratives into executable Skills defined by activation, execution, and termination conditions to ensure executability. To achie","authors_text":"Haifeng Zhang, Haoxuan Li, Jun Wang, Mengyue Yang, Qirui Mi, Yisen Wang, Zhijian Ma","cross_cats":[],"headline":"Skill-Pro lets LLM agents learn reusable procedural skills from past experiences without updating any parameters.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-02T09:43:12Z","title":"Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.01869","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T08:31:09.441739Z","id":"de1adf4e-d978-4769-bb94-7f76d07fb912","model_set":{"reader":"grok-4.3"},"one_line_summary":"Skill-Pro enables LLM agents to autonomously learn, verify, and reuse compact procedural skills from experience via a Skill-MDP formalization and Non-Parametric PPO, yielding higher reuse rates, performance gains, and extreme memory compression across in-domain, cross-task, and cross-agent settings.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Skill-Pro lets LLM agents learn reusable procedural skills from past experiences without updating any parameters.","strongest_claim":"Skill-Pro achieves superior reuse rates and significant performance gains with extreme memory compression by autonomously learning reusable procedural skills from interaction experiences without parameter updates, using Skill-MDP formalization and Non-Parametric PPO for reliable verification.","weakest_assumption":"That semantic gradients combined with a PPO Gate can generate and verify high-quality skills that remain executable and non-degrading across recurring scenarios without any post-hoc exclusions or capability loss."}},"verdict_id":"de1adf4e-d978-4769-bb94-7f76d07fb912"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:336ea54cf15e16e6b413bcd1df3a79f2032d2c19ed9f075b15b1a0e080e0a829","target":"record","created_at":"2026-05-29T02:05:40Z","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":"090d34ac9a4679279642127a2cbb9daaa4c455584eeaf648ab6633dacac456bc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-02T09:43:12Z","title_canon_sha256":"9ce1cd3f78023a14abbe6a6e7c1681d1c7ddec483468097ab271327fdc2adcd2"},"schema_version":"1.0","source":{"id":"2602.01869","kind":"arxiv","version":3}},"canonical_sha256":"239676e331719ea060196e00003d016f82e0522ee7e3604846dd9ff2c7445ab2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"239676e331719ea060196e00003d016f82e0522ee7e3604846dd9ff2c7445ab2","first_computed_at":"2026-05-29T02:05:40.216021Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:05:40.216021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N5CLOyQBqnqyE1lAKbgURtc6m9A//R2E+KYwVRzKNgg5Z2sDOq43VgB7H7dBM9YJceqVSoGN97ZHUo42FsqqDg==","signature_status":"signed_v1","signed_at":"2026-05-29T02:05:40.216743Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.01869","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:336ea54cf15e16e6b413bcd1df3a79f2032d2c19ed9f075b15b1a0e080e0a829","sha256:ee3b25f0d7bdcb2e9a751eeb92f2dab19a2339d64d2b438c34762b6ec099dde0"],"state_sha256":"3f96a3af1ffe6e68bea3d794ba819c577082302980641ea71162277bf8ee1d43"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cQUuZ70WqgW7zZuBgBEqRhZkIyTImTvCofHeg77PaINlw9UZ/RHcNdQZLjDW6P49drjGM401rjKnKy0XwUjbAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T15:11:12.023721Z","bundle_sha256":"1f9e84db1db4eea3c0a5ac699a2e95918cea346457b45ec94d33523a73dc8639"}}