{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LHIRNJFRSBMVYNBG4C2K4RMY43","short_pith_number":"pith:LHIRNJFR","schema_version":"1.0","canonical_sha256":"59d116a4b190595c3426e0b4ae4598e6c3d729b63531375ac85b89e753b4d47d","source":{"kind":"arxiv","id":"2605.17137","version":1},"attestation_state":"computed","paper":{"title":"Latent Heuristic Search: Continuous Optimization for Automated Algorithm Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheikh Ahmed, Mahdi Mostajabdaveh, Zirui Zhou","submitted_at":"2026-05-16T20:03:01Z","abstract_excerpt":"The integration of Large Language Models (LLMs) into evolutionary frameworks has established a new paradigm for automated heuristic discovery. Despite their promise, these methods typically search in the discrete space of program syntax, relying on stochastic sampling to navigate a highly non-convex optimization landscape. This work proposes a continuous heuristic discovery framework that shifts optimization to a learned latent manifold. We employ an encoder to map discrete programs into continuous embeddings and train a differentiable surrogate model to predict performance, enabling gradient-"},"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":"2605.17137","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T20:03:01Z","cross_cats_sorted":[],"title_canon_sha256":"ac53556abfcb9f5ba16deadf8b7678bdc134098c76d4ca1cf22edd4dce133f7b","abstract_canon_sha256":"b64444242a0e7053ce46084f46a000f45f0af9cf838425e8ab07d0d2967ec466"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:41.678622Z","signature_b64":"EqEdGL2XeIca3g0NWK/KmfzC6El3xyBYNDPfnP9/I0nmHYMFqN+9IutmMKNzw2JIwHBPYKqJYBWCLDWZPpBgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59d116a4b190595c3426e0b4ae4598e6c3d729b63531375ac85b89e753b4d47d","last_reissued_at":"2026-05-20T00:03:41.677783Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:41.677783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Heuristic Search: Continuous Optimization for Automated Algorithm Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheikh Ahmed, Mahdi Mostajabdaveh, Zirui Zhou","submitted_at":"2026-05-16T20:03:01Z","abstract_excerpt":"The integration of Large Language Models (LLMs) into evolutionary frameworks has established a new paradigm for automated heuristic discovery. Despite their promise, these methods typically search in the discrete space of program syntax, relying on stochastic sampling to navigate a highly non-convex optimization landscape. This work proposes a continuous heuristic discovery framework that shifts optimization to a learned latent manifold. We employ an encoder to map discrete programs into continuous embeddings and train a differentiable surrogate model to predict performance, enabling gradient-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17137","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/2605.17137/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T22:33:23.774051Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T22:01:58.014042Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"10f06f6353a306e4efb01f7a3e15cf4432ca167908f044d90598e351589eda28"},"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":"2605.17137","created_at":"2026-05-20T00:03:41.677922+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17137v1","created_at":"2026-05-20T00:03:41.677922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17137","created_at":"2026-05-20T00:03:41.677922+00:00"},{"alias_kind":"pith_short_12","alias_value":"LHIRNJFRSBMV","created_at":"2026-05-20T00:03:41.677922+00:00"},{"alias_kind":"pith_short_16","alias_value":"LHIRNJFRSBMVYNBG","created_at":"2026-05-20T00:03:41.677922+00:00"},{"alias_kind":"pith_short_8","alias_value":"LHIRNJFR","created_at":"2026-05-20T00:03:41.677922+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LHIRNJFRSBMVYNBG4C2K4RMY43","json":"https://pith.science/pith/LHIRNJFRSBMVYNBG4C2K4RMY43.json","graph_json":"https://pith.science/api/pith-number/LHIRNJFRSBMVYNBG4C2K4RMY43/graph.json","events_json":"https://pith.science/api/pith-number/LHIRNJFRSBMVYNBG4C2K4RMY43/events.json","paper":"https://pith.science/paper/LHIRNJFR"},"agent_actions":{"view_html":"https://pith.science/pith/LHIRNJFRSBMVYNBG4C2K4RMY43","download_json":"https://pith.science/pith/LHIRNJFRSBMVYNBG4C2K4RMY43.json","view_paper":"https://pith.science/paper/LHIRNJFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17137&json=true","fetch_graph":"https://pith.science/api/pith-number/LHIRNJFRSBMVYNBG4C2K4RMY43/graph.json","fetch_events":"https://pith.science/api/pith-number/LHIRNJFRSBMVYNBG4C2K4RMY43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LHIRNJFRSBMVYNBG4C2K4RMY43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LHIRNJFRSBMVYNBG4C2K4RMY43/action/storage_attestation","attest_author":"https://pith.science/pith/LHIRNJFRSBMVYNBG4C2K4RMY43/action/author_attestation","sign_citation":"https://pith.science/pith/LHIRNJFRSBMVYNBG4C2K4RMY43/action/citation_signature","submit_replication":"https://pith.science/pith/LHIRNJFRSBMVYNBG4C2K4RMY43/action/replication_record"}},"created_at":"2026-05-20T00:03:41.677922+00:00","updated_at":"2026-05-20T00:03:41.677922+00:00"}