{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3UMECFYBCEQSVQLLY5N2U6OPKZ","short_pith_number":"pith:3UMECFYB","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"},"canonical_sha256":"dd1841170111212ac16bc75baa79cf565fd3694940ff1b6aba21b99eb48d3887","source":{"kind":"arxiv","id":"2604.15097","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.15097","created_at":"2026-06-03T01:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2604.15097v2","created_at":"2026-06-03T01:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.15097","created_at":"2026-06-03T01:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"3UMECFYBCEQS","created_at":"2026-06-03T01:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"3UMECFYBCEQSVQLL","created_at":"2026-06-03T01:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"3UMECFYB","created_at":"2026-06-03T01:05:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3UMECFYBCEQSVQLLY5N2U6OPKZ","target":"record","payload":{"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"},"canonical_sha256":"dd1841170111212ac16bc75baa79cf565fd3694940ff1b6aba21b99eb48d3887","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"},"source_kind":"arxiv","source_id":"2604.15097","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":"2026-06-03T01:05:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1iz7Z/JGDX6ynz3UnmqVARyF75mJBsP36rc3uSsy3WvZJ44Guf379mIVnN1PS5nkXwSAZ8o0g9ZhrP7t4WsLBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T16:34:19.805146Z"},"content_sha256":"f2caba7a04205193e95a9cf7df7d636318ea6df16b67a0f7baaead89fb0b03de","schema_version":"1.0","event_id":"sha256:f2caba7a04205193e95a9cf7df7d636318ea6df16b67a0f7baaead89fb0b03de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3UMECFYBCEQSVQLLY5N2U6OPKZ","target":"graph","payload":{"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"},"verdict_id":"cf4b4b39-01ed-4fe5-a58b-9e8389c13310"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-03T01:05:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KkBwpOsb58dTO3KqRosQ4kVYkdk0AWh/SFnRxnGcdqhZ80bvZXaNZsd5qv+Dg+j7kvanFDjzVecQ2BDbgCALAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T16:34:19.806033Z"},"content_sha256":"ed356632f3390f1066cf691daaa8c61688ec0a2c24cf933df52b8abf3f3c0537","schema_version":"1.0","event_id":"sha256:ed356632f3390f1066cf691daaa8c61688ec0a2c24cf933df52b8abf3f3c0537"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3UMECFYBCEQSVQLLY5N2U6OPKZ/bundle.json","state_url":"https://pith.science/pith/3UMECFYBCEQSVQLLY5N2U6OPKZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3UMECFYBCEQSVQLLY5N2U6OPKZ/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":"2026-06-06T16:34:19Z","links":{"resolver":"https://pith.science/pith/3UMECFYBCEQSVQLLY5N2U6OPKZ","bundle":"https://pith.science/pith/3UMECFYBCEQSVQLLY5N2U6OPKZ/bundle.json","state":"https://pith.science/pith/3UMECFYBCEQSVQLLY5N2U6OPKZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3UMECFYBCEQSVQLLY5N2U6OPKZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3UMECFYBCEQSVQLLY5N2U6OPKZ","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":"4fe322d1d1dc472935ac2ea79b5dc562d59175ddb08c3f52c528d2912f8cf4fe","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-04-16T14:55:49Z","title_canon_sha256":"0faa693fe5c0f6a488db0001f578294f48d91bbbe18141e2b917affeaaedfd92"},"schema_version":"1.0","source":{"id":"2604.15097","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.15097","created_at":"2026-06-03T01:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2604.15097v2","created_at":"2026-06-03T01:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.15097","created_at":"2026-06-03T01:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"3UMECFYBCEQS","created_at":"2026-06-03T01:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"3UMECFYBCEQSVQLL","created_at":"2026-06-03T01:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"3UMECFYB","created_at":"2026-06-03T01:05:13Z"}],"graph_snapshots":[{"event_id":"sha256:ed356632f3390f1066cf691daaa8c61688ec0a2c24cf933df52b8abf3f3c0537","target":"graph","created_at":"2026-06-03T01:05:13Z","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":"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%."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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%."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A compact Gene representation for reusable experience outperforms documentation-heavy Skill packages in guiding AI code solvers and enabling iterative evolution."}],"snapshot_sha256":"a1ce6020e16cae731ef4bd7fe0f790a3a2e6c14da5babf21186f3c05c0b595f9"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.15097/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haoyang Zhang, Junjie Wang, Yiming Ren","cross_cats":["cs.CL"],"headline":"A compact Gene representation for reusable experience outperforms documentation-heavy Skill packages in guiding AI code solvers and enabling iterative evolution.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-04-16T14:55:49Z","title":"From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.15097","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T10:50:00.857462Z","id":"cf4b4b39-01ed-4fe5-a58b-9e8389c13310","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"A compact Gene representation for reusable experience outperforms documentation-heavy Skill packages in guiding AI code solvers and enabling iterative evolution.","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%.","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."}},"verdict_id":"cf4b4b39-01ed-4fe5-a58b-9e8389c13310"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f2caba7a04205193e95a9cf7df7d636318ea6df16b67a0f7baaead89fb0b03de","target":"record","created_at":"2026-06-03T01:05:13Z","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":"4fe322d1d1dc472935ac2ea79b5dc562d59175ddb08c3f52c528d2912f8cf4fe","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-04-16T14:55:49Z","title_canon_sha256":"0faa693fe5c0f6a488db0001f578294f48d91bbbe18141e2b917affeaaedfd92"},"schema_version":"1.0","source":{"id":"2604.15097","kind":"arxiv","version":2}},"canonical_sha256":"dd1841170111212ac16bc75baa79cf565fd3694940ff1b6aba21b99eb48d3887","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd1841170111212ac16bc75baa79cf565fd3694940ff1b6aba21b99eb48d3887","first_computed_at":"2026-06-03T01:05:13.711959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:13.711959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qqtQ2Ch3HD4wlFAll4jnqI9nsclogivwWE+wsisyqftDiQ45clQNqcWGR5szq2UZt0rbxh27x5artzP8JmeCCA==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:13.712347Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.15097","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2caba7a04205193e95a9cf7df7d636318ea6df16b67a0f7baaead89fb0b03de","sha256:ed356632f3390f1066cf691daaa8c61688ec0a2c24cf933df52b8abf3f3c0537"],"state_sha256":"fed38f354a283dff14a4e303562ac360cd1edddc6b5f4aac460873c7300b5f28"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AXkFVthU0xSRHvvmc2qUk/+HhpphKuisJQ4SRQvn58Is/iCWgpfI9/APngtIdtgoHfoAYkrPtElnw/YgTIaJDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T16:34:19.809348Z","bundle_sha256":"a96487e1380cf09d637705aad29bc56d6cf03e5990eae8dff8b5d3304e42edc9"}}