{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3UMECFYBCEQSVQLLY5N2U6OPKZ","short_pith_number":"pith:3UMECFYB","schema_version":"1.0","canonical_sha256":"dd1841170111212ac16bc75baa79cf565fd3694940ff1b6aba21b99eb48d3887","source":{"kind":"arxiv","id":"2604.15097","version":2},"attestation_state":"computed","paper":{"title":"From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A compact Gene representation for reusable experience outperforms documentation-heavy Skill packages in guiding AI code solvers and enabling iterative evolution.","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Haoyang Zhang, Junjie Wang, Yiming Ren","submitted_at":"2026-04-16T14:55:49Z","abstract_excerpt":"This beta technical report asks how reusable experience should be represented so that it can function as effective test-time control and as a substrate for iterative evolution. We study this question in 4.590 controlled trials across 45 scientific code-solving scenarios. We find that documentation-oriented Skill packages provide unstable control: their useful signal is sparse, and expanding a compact experience object into a fuller documentation package often fails to help and can degrade the overall average. We further show that representation itself is a first-order factor. A compact Gene re"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2604.15097","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-04-16T14:55:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0faa693fe5c0f6a488db0001f578294f48d91bbbe18141e2b917affeaaedfd92","abstract_canon_sha256":"4fe322d1d1dc472935ac2ea79b5dc562d59175ddb08c3f52c528d2912f8cf4fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:13.712347Z","signature_b64":"qqtQ2Ch3HD4wlFAll4jnqI9nsclogivwWE+wsisyqftDiQ45clQNqcWGR5szq2UZt0rbxh27x5artzP8JmeCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd1841170111212ac16bc75baa79cf565fd3694940ff1b6aba21b99eb48d3887","last_reissued_at":"2026-06-03T01:05:13.711959Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:13.711959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A compact Gene representation for reusable experience outperforms documentation-heavy Skill packages in guiding AI code solvers and enabling iterative evolution.","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Haoyang Zhang, Junjie Wang, Yiming Ren","submitted_at":"2026-04-16T14:55:49Z","abstract_excerpt":"This beta technical report asks how reusable experience should be represented so that it can function as effective test-time control and as a substrate for iterative evolution. We study this question in 4.590 controlled trials across 45 scientific code-solving scenarios. We find that documentation-oriented Skill packages provide unstable control: their useful signal is sparse, and expanding a compact experience object into a fuller documentation package often fails to help and can degrade the overall average. We further show that representation itself is a first-order factor. A compact Gene re"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"A compact Gene representation yields the strongest overall average, remains competitive under substantial structural perturbations, and outperforms matched-budget Skill fragments, while reattaching documentation-oriented material usually weakens rather than improves it. On CritPt, gene-evolved systems improve over their paired base models from 9.1% to 18.57% and from 17.7% to 27.14%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the 45 scientific code-solving scenarios and the specific definition of Gene versus Skill fragments are representative of broader experience-reuse needs, and that observed gains stem primarily from representation format rather than unstated differences in prompt construction or model behavior.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Compact Gene representations of experience outperform documentation-oriented Skill packages for test-time control and iterative evolution in code-solving tasks, with measured gains on CritPt from 9.1% to 18.57% and 17.7% to 27.14%.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A compact Gene representation for reusable experience outperforms documentation-heavy Skill packages in guiding AI code solvers and enabling iterative evolution.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a1ce6020e16cae731ef4bd7fe0f790a3a2e6c14da5babf21186f3c05c0b595f9"},"source":{"id":"2604.15097","kind":"arxiv","version":2},"verdict":{"id":"cf4b4b39-01ed-4fe5-a58b-9e8389c13310","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T10:50:00.857462Z","strongest_claim":"A compact Gene representation yields the strongest overall average, remains competitive under substantial structural perturbations, and outperforms matched-budget Skill fragments, while reattaching documentation-oriented material usually weakens rather than improves it. On CritPt, gene-evolved systems improve over their paired base models from 9.1% to 18.57% and from 17.7% to 27.14%.","one_line_summary":"Compact Gene representations of experience outperform documentation-oriented Skill packages for test-time control and iterative evolution in code-solving tasks, with measured gains on CritPt from 9.1% to 18.57% and 17.7% to 27.14%.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the 45 scientific code-solving scenarios and the specific definition of Gene versus Skill fragments are representative of broader experience-reuse needs, and that observed gains stem primarily from representation format rather than unstated differences in prompt construction or model behavior.","pith_extraction_headline":"A compact Gene representation for reusable experience outperforms documentation-heavy Skill packages in guiding AI code solvers and enabling iterative evolution."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.15097/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2604.15097","created_at":"2026-06-03T01:05:13.712006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.15097v2","created_at":"2026-06-03T01:05:13.712006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.15097","created_at":"2026-06-03T01:05:13.712006+00:00"},{"alias_kind":"pith_short_12","alias_value":"3UMECFYBCEQS","created_at":"2026-06-03T01:05:13.712006+00:00"},{"alias_kind":"pith_short_16","alias_value":"3UMECFYBCEQSVQLL","created_at":"2026-06-03T01:05:13.712006+00:00"},{"alias_kind":"pith_short_8","alias_value":"3UMECFYB","created_at":"2026-06-03T01:05:13.712006+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2605.22148","citing_title":"Ratchet: A Minimal Hygiene Recipe for Self-Evolving LLM Agents","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22794","citing_title":"MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18401","citing_title":"SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19576","citing_title":"Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3UMECFYBCEQSVQLLY5N2U6OPKZ","json":"https://pith.science/pith/3UMECFYBCEQSVQLLY5N2U6OPKZ.json","graph_json":"https://pith.science/api/pith-number/3UMECFYBCEQSVQLLY5N2U6OPKZ/graph.json","events_json":"https://pith.science/api/pith-number/3UMECFYBCEQSVQLLY5N2U6OPKZ/events.json","paper":"https://pith.science/paper/3UMECFYB"},"agent_actions":{"view_html":"https://pith.science/pith/3UMECFYBCEQSVQLLY5N2U6OPKZ","download_json":"https://pith.science/pith/3UMECFYBCEQSVQLLY5N2U6OPKZ.json","view_paper":"https://pith.science/paper/3UMECFYB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.15097&json=true","fetch_graph":"https://pith.science/api/pith-number/3UMECFYBCEQSVQLLY5N2U6OPKZ/graph.json","fetch_events":"https://pith.science/api/pith-number/3UMECFYBCEQSVQLLY5N2U6OPKZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3UMECFYBCEQSVQLLY5N2U6OPKZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3UMECFYBCEQSVQLLY5N2U6OPKZ/action/storage_attestation","attest_author":"https://pith.science/pith/3UMECFYBCEQSVQLLY5N2U6OPKZ/action/author_attestation","sign_citation":"https://pith.science/pith/3UMECFYBCEQSVQLLY5N2U6OPKZ/action/citation_signature","submit_replication":"https://pith.science/pith/3UMECFYBCEQSVQLLY5N2U6OPKZ/action/replication_record"}},"created_at":"2026-06-03T01:05:13.712006+00:00","updated_at":"2026-06-03T01:05:13.712006+00:00"}