{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JFWDTT5N2R3SLTIJFAQK3P2B5N","short_pith_number":"pith:JFWDTT5N","canonical_record":{"source":{"id":"2604.09297","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-10T13:08:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0c7d973d8b94b894e9974cd32ba69802a5ac556a1c9da46c3b5a0008ddf31929","abstract_canon_sha256":"df66d202ee7eccd7754b8baff06d93ca1d1cae75563c94b54ee7fe6bad54666f"},"schema_version":"1.0"},"canonical_sha256":"496c39cfadd47725cd092820adbf41eb60ce8c2a581eb8f2007cb94c2ba8751e","source":{"kind":"arxiv","id":"2604.09297","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.09297","created_at":"2026-05-20T00:03:10Z"},{"alias_kind":"arxiv_version","alias_value":"2604.09297v2","created_at":"2026-05-20T00:03:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.09297","created_at":"2026-05-20T00:03:10Z"},{"alias_kind":"pith_short_12","alias_value":"JFWDTT5N2R3S","created_at":"2026-05-20T00:03:10Z"},{"alias_kind":"pith_short_16","alias_value":"JFWDTT5N2R3SLTIJ","created_at":"2026-05-20T00:03:10Z"},{"alias_kind":"pith_short_8","alias_value":"JFWDTT5N","created_at":"2026-05-20T00:03:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JFWDTT5N2R3SLTIJFAQK3P2B5N","target":"record","payload":{"canonical_record":{"source":{"id":"2604.09297","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-10T13:08:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0c7d973d8b94b894e9974cd32ba69802a5ac556a1c9da46c3b5a0008ddf31929","abstract_canon_sha256":"df66d202ee7eccd7754b8baff06d93ca1d1cae75563c94b54ee7fe6bad54666f"},"schema_version":"1.0"},"canonical_sha256":"496c39cfadd47725cd092820adbf41eb60ce8c2a581eb8f2007cb94c2ba8751e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:10.908033Z","signature_b64":"aNRg51BKvPc17Z6GNnZZxQHjQVbAB4OngxWKEYs8e/Ah+76xPVozKu3Da7EsW3pO5BtTOdNoz0kqXuGI8XceBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"496c39cfadd47725cd092820adbf41eb60ce8c2a581eb8f2007cb94c2ba8751e","last_reissued_at":"2026-05-20T00:03:10.907210Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:10.907210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.09297","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":"2026-05-20T00:03:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3OpaQUIYqYbim6SnBcrNLqYj19yniEbJqlWwDO4vEUN5VtSC9SKLsfRGKTBuuNPgoI6v+Lju84rS2ViK6auGBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T07:05:49.885402Z"},"content_sha256":"55d622199cd50d906f488fffc1940aa48443d6534a4198887914c1d752f8247d","schema_version":"1.0","event_id":"sha256:55d622199cd50d906f488fffc1940aa48443d6534a4198887914c1d752f8247d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JFWDTT5N2R3SLTIJFAQK3P2B5N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"SkillMOO evolves skill bundles for LLM coding agents by combining LLM-proposed edits with NSGA-II selection to raise pass rates while lowering cost.","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Alina Geiger, Dominik Sobania, Federica Sarro, Jie M. Zhang, Jingzhi Gong, Lukas Twist, Ruizhen Gu, Shuo Han, Yazhuo Cao, Zhiwei Fei","submitted_at":"2026-04-10T13:08:01Z","abstract_excerpt":"Agent skills are increasingly used to configure coding agents for software engineering (SE) tasks, yet current practice treats them as static, hand-crafted assets, or evolved on pass rate alone. This is insufficient: a skill can improve task success while substantially raising token cost, or introducing misleading guidance. We argue that SE agent skill bundles can be treated as multi-objective search objects and present SkillMOO, a framework that evolves skill bundles through LLM-proposed edits and NSGA-II Pareto selection on pass rate and inference cost. Evaluated across all 16 SkillsBench SE"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On three SkillsBench software engineering tasks, SkillMOO improves pass rate by up to 131% while reducing cost up to 32% relative to the best baseline per task at low optimization overhead.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That LLM-proposed edits guided by failure analysis combined with NSGA-II survivor selection will reliably discover superior skill bundles without overfitting to the specific benchmark tasks or introducing hidden costs not captured in the reported metrics.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SkillMOO automatically evolves skill bundles for LLM coding agents via LLM-proposed edits and NSGA-II, achieving up to 131% higher pass rates and 32% lower costs on three SkillsBench tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SkillMOO evolves skill bundles for LLM coding agents by combining LLM-proposed edits with NSGA-II selection to raise pass rates while lowering cost.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cbcacd44beb112a8b4be55d46a21845dd6cf79d31e2ae3cfe8686f4c24a705b4"},"source":{"id":"2604.09297","kind":"arxiv","version":2},"verdict":{"id":"d8720abe-ad4d-44d5-9df5-d4da9c5e24a1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T17:21:55.619579Z","strongest_claim":"On three SkillsBench software engineering tasks, SkillMOO improves pass rate by up to 131% while reducing cost up to 32% relative to the best baseline per task at low optimization overhead.","one_line_summary":"SkillMOO automatically evolves skill bundles for LLM coding agents via LLM-proposed edits and NSGA-II, achieving up to 131% higher pass rates and 32% lower costs on three SkillsBench tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That LLM-proposed edits guided by failure analysis combined with NSGA-II survivor selection will reliably discover superior skill bundles without overfitting to the specific benchmark tasks or introducing hidden costs not captured in the reported metrics.","pith_extraction_headline":"SkillMOO evolves skill bundles for LLM coding agents by combining LLM-proposed edits with NSGA-II selection to raise pass rates while lowering cost."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.09297/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":"d8720abe-ad4d-44d5-9df5-d4da9c5e24a1"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OD4H2/X3E6I4/Vsfp1jxL9722uhbV6vxcUHSjwWr/SWP+r3IpU+NfvH4ruOMJwJARi3SeRtEpDvLvo0eMrKiBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T07:05:49.885866Z"},"content_sha256":"24a221b6a99f8382675e086881ecc93822a8c5a11e0f5e645ccb8a1e5d80cbf6","schema_version":"1.0","event_id":"sha256:24a221b6a99f8382675e086881ecc93822a8c5a11e0f5e645ccb8a1e5d80cbf6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JFWDTT5N2R3SLTIJFAQK3P2B5N/bundle.json","state_url":"https://pith.science/pith/JFWDTT5N2R3SLTIJFAQK3P2B5N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JFWDTT5N2R3SLTIJFAQK3P2B5N/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":"2026-05-21T07:05:49Z","links":{"resolver":"https://pith.science/pith/JFWDTT5N2R3SLTIJFAQK3P2B5N","bundle":"https://pith.science/pith/JFWDTT5N2R3SLTIJFAQK3P2B5N/bundle.json","state":"https://pith.science/pith/JFWDTT5N2R3SLTIJFAQK3P2B5N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JFWDTT5N2R3SLTIJFAQK3P2B5N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JFWDTT5N2R3SLTIJFAQK3P2B5N","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":"df66d202ee7eccd7754b8baff06d93ca1d1cae75563c94b54ee7fe6bad54666f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-10T13:08:01Z","title_canon_sha256":"0c7d973d8b94b894e9974cd32ba69802a5ac556a1c9da46c3b5a0008ddf31929"},"schema_version":"1.0","source":{"id":"2604.09297","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.09297","created_at":"2026-05-20T00:03:10Z"},{"alias_kind":"arxiv_version","alias_value":"2604.09297v2","created_at":"2026-05-20T00:03:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.09297","created_at":"2026-05-20T00:03:10Z"},{"alias_kind":"pith_short_12","alias_value":"JFWDTT5N2R3S","created_at":"2026-05-20T00:03:10Z"},{"alias_kind":"pith_short_16","alias_value":"JFWDTT5N2R3SLTIJ","created_at":"2026-05-20T00:03:10Z"},{"alias_kind":"pith_short_8","alias_value":"JFWDTT5N","created_at":"2026-05-20T00:03:10Z"}],"graph_snapshots":[{"event_id":"sha256:24a221b6a99f8382675e086881ecc93822a8c5a11e0f5e645ccb8a1e5d80cbf6","target":"graph","created_at":"2026-05-20T00:03:10Z","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":"On three SkillsBench software engineering tasks, SkillMOO improves pass rate by up to 131% while reducing cost up to 32% relative to the best baseline per task at low optimization overhead."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That LLM-proposed edits guided by failure analysis combined with NSGA-II survivor selection will reliably discover superior skill bundles without overfitting to the specific benchmark tasks or introducing hidden costs not captured in the reported metrics."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SkillMOO automatically evolves skill bundles for LLM coding agents via LLM-proposed edits and NSGA-II, achieving up to 131% higher pass rates and 32% lower costs on three SkillsBench tasks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"SkillMOO evolves skill bundles for LLM coding agents by combining LLM-proposed edits with NSGA-II selection to raise pass rates while lowering cost."}],"snapshot_sha256":"cbcacd44beb112a8b4be55d46a21845dd6cf79d31e2ae3cfe8686f4c24a705b4"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.09297/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agent skills are increasingly used to configure coding agents for software engineering (SE) tasks, yet current practice treats them as static, hand-crafted assets, or evolved on pass rate alone. This is insufficient: a skill can improve task success while substantially raising token cost, or introducing misleading guidance. We argue that SE agent skill bundles can be treated as multi-objective search objects and present SkillMOO, a framework that evolves skill bundles through LLM-proposed edits and NSGA-II Pareto selection on pass rate and inference cost. Evaluated across all 16 SkillsBench SE","authors_text":"Alina Geiger, Dominik Sobania, Federica Sarro, Jie M. Zhang, Jingzhi Gong, Lukas Twist, Ruizhen Gu, Shuo Han, Yazhuo Cao, Zhiwei Fei","cross_cats":["cs.AI"],"headline":"SkillMOO evolves skill bundles for LLM coding agents by combining LLM-proposed edits with NSGA-II selection to raise pass rates while lowering cost.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-10T13:08:01Z","title":"SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.09297","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T17:21:55.619579Z","id":"d8720abe-ad4d-44d5-9df5-d4da9c5e24a1","model_set":{"reader":"grok-4.3"},"one_line_summary":"SkillMOO automatically evolves skill bundles for LLM coding agents via LLM-proposed edits and NSGA-II, achieving up to 131% higher pass rates and 32% lower costs on three SkillsBench tasks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"SkillMOO evolves skill bundles for LLM coding agents by combining LLM-proposed edits with NSGA-II selection to raise pass rates while lowering cost.","strongest_claim":"On three SkillsBench software engineering tasks, SkillMOO improves pass rate by up to 131% while reducing cost up to 32% relative to the best baseline per task at low optimization overhead.","weakest_assumption":"That LLM-proposed edits guided by failure analysis combined with NSGA-II survivor selection will reliably discover superior skill bundles without overfitting to the specific benchmark tasks or introducing hidden costs not captured in the reported metrics."}},"verdict_id":"d8720abe-ad4d-44d5-9df5-d4da9c5e24a1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:55d622199cd50d906f488fffc1940aa48443d6534a4198887914c1d752f8247d","target":"record","created_at":"2026-05-20T00:03:10Z","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":"df66d202ee7eccd7754b8baff06d93ca1d1cae75563c94b54ee7fe6bad54666f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-10T13:08:01Z","title_canon_sha256":"0c7d973d8b94b894e9974cd32ba69802a5ac556a1c9da46c3b5a0008ddf31929"},"schema_version":"1.0","source":{"id":"2604.09297","kind":"arxiv","version":2}},"canonical_sha256":"496c39cfadd47725cd092820adbf41eb60ce8c2a581eb8f2007cb94c2ba8751e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"496c39cfadd47725cd092820adbf41eb60ce8c2a581eb8f2007cb94c2ba8751e","first_computed_at":"2026-05-20T00:03:10.907210Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:10.907210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aNRg51BKvPc17Z6GNnZZxQHjQVbAB4OngxWKEYs8e/Ah+76xPVozKu3Da7EsW3pO5BtTOdNoz0kqXuGI8XceBA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:10.908033Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.09297","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55d622199cd50d906f488fffc1940aa48443d6534a4198887914c1d752f8247d","sha256:24a221b6a99f8382675e086881ecc93822a8c5a11e0f5e645ccb8a1e5d80cbf6"],"state_sha256":"faa722de80cb0ce6700aeb15367958ec326be3c25c84441eb6d69c4ab161086e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cq27EsPePCacIm/fiLOwMPOe6ER2duM0+1PTCEe12cxeb6RdasjOLcjwFVszlG6OqWVyGHpIMnJpI8Dc9v9DCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T07:05:49.888093Z","bundle_sha256":"0fc68247b176eb90e0c431931a2f0016d0220bd110b876249d0b060bacca426f"}}