{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FGZZDJJ2QR6R7U7BCBKGSXKCBG","short_pith_number":"pith:FGZZDJJ2","schema_version":"1.0","canonical_sha256":"29b391a53a847d1fd3e11054695d42098f483e954500535ecf7149c26583be15","source":{"kind":"arxiv","id":"2606.25198","version":1},"attestation_state":"computed","paper":{"title":"Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alfonso Amayuelas, Antonis Antoniades, Deepak Nathani, Ivan Bercovich, Kunal Bhatia, Ritam Saha, Vignesh Baskaran, William Yang Wang, Zhaotian Weng","submitted_at":"2026-06-23T21:44:08Z","abstract_excerpt":"Autonomous AI Research promises to accelerate the scientific progress of machine learning. To realise this goal, current Large Language Model (LLM)-based agents need to go beyond just writing code, to mastering the exploration of simultaneously performant, diverse and novel ideas. To this end, we introduce Heuresis, a framework that abstracts the research pipeline into a set of general and composable primitives, enabling open-ended scientific exploration in machine learning research. We implement six search strategies: a greedy baseline, two archive-based (MAP-Elites, Go-Explore), one evolutio"},"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":"2606.25198","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T21:44:08Z","cross_cats_sorted":[],"title_canon_sha256":"1366613f629031cbd3510eb02beb6c143381aa915247e4ef4c17c573699b6227","abstract_canon_sha256":"ce0d10fb458c958824dab42bcaa627dabdc0a99d32185ed7577da145410311b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T00:18:20.653969Z","signature_b64":"mhieWxBYiJ95G82l17IGm9m4nIPv1qPpazmnDfoBB3BNS8IF4w53Z2Ql7MbwbFDofMsoGmxxQhA3h16R3hJjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29b391a53a847d1fd3e11054695d42098f483e954500535ecf7149c26583be15","last_reissued_at":"2026-06-25T00:18:20.653565Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T00:18:20.653565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alfonso Amayuelas, Antonis Antoniades, Deepak Nathani, Ivan Bercovich, Kunal Bhatia, Ritam Saha, Vignesh Baskaran, William Yang Wang, Zhaotian Weng","submitted_at":"2026-06-23T21:44:08Z","abstract_excerpt":"Autonomous AI Research promises to accelerate the scientific progress of machine learning. To realise this goal, current Large Language Model (LLM)-based agents need to go beyond just writing code, to mastering the exploration of simultaneously performant, diverse and novel ideas. To this end, we introduce Heuresis, a framework that abstracts the research pipeline into a set of general and composable primitives, enabling open-ended scientific exploration in machine learning research. We implement six search strategies: a greedy baseline, two archive-based (MAP-Elites, Go-Explore), one evolutio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25198","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/2606.25198/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":"2606.25198","created_at":"2026-06-25T00:18:20.653629+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25198v1","created_at":"2026-06-25T00:18:20.653629+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25198","created_at":"2026-06-25T00:18:20.653629+00:00"},{"alias_kind":"pith_short_12","alias_value":"FGZZDJJ2QR6R","created_at":"2026-06-25T00:18:20.653629+00:00"},{"alias_kind":"pith_short_16","alias_value":"FGZZDJJ2QR6R7U7B","created_at":"2026-06-25T00:18:20.653629+00:00"},{"alias_kind":"pith_short_8","alias_value":"FGZZDJJ2","created_at":"2026-06-25T00:18:20.653629+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/FGZZDJJ2QR6R7U7BCBKGSXKCBG","json":"https://pith.science/pith/FGZZDJJ2QR6R7U7BCBKGSXKCBG.json","graph_json":"https://pith.science/api/pith-number/FGZZDJJ2QR6R7U7BCBKGSXKCBG/graph.json","events_json":"https://pith.science/api/pith-number/FGZZDJJ2QR6R7U7BCBKGSXKCBG/events.json","paper":"https://pith.science/paper/FGZZDJJ2"},"agent_actions":{"view_html":"https://pith.science/pith/FGZZDJJ2QR6R7U7BCBKGSXKCBG","download_json":"https://pith.science/pith/FGZZDJJ2QR6R7U7BCBKGSXKCBG.json","view_paper":"https://pith.science/paper/FGZZDJJ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25198&json=true","fetch_graph":"https://pith.science/api/pith-number/FGZZDJJ2QR6R7U7BCBKGSXKCBG/graph.json","fetch_events":"https://pith.science/api/pith-number/FGZZDJJ2QR6R7U7BCBKGSXKCBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FGZZDJJ2QR6R7U7BCBKGSXKCBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FGZZDJJ2QR6R7U7BCBKGSXKCBG/action/storage_attestation","attest_author":"https://pith.science/pith/FGZZDJJ2QR6R7U7BCBKGSXKCBG/action/author_attestation","sign_citation":"https://pith.science/pith/FGZZDJJ2QR6R7U7BCBKGSXKCBG/action/citation_signature","submit_replication":"https://pith.science/pith/FGZZDJJ2QR6R7U7BCBKGSXKCBG/action/replication_record"}},"created_at":"2026-06-25T00:18:20.653629+00:00","updated_at":"2026-06-25T00:18:20.653629+00:00"}