{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7N7EZVAKL4HVTTS3B53QG5ATGU","short_pith_number":"pith:7N7EZVAK","schema_version":"1.0","canonical_sha256":"fb7e4cd40a5f0f59ce5b0f7703741335389a0c8a242d5f5bc624f919bd4a2b5c","source":{"kind":"arxiv","id":"2504.20090","version":2},"attestation_state":"computed","paper":{"title":"Spark: A System for Scientifically Creative Idea Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.AI","authors_text":"Aishik Sanyal, Dilek Hakkani-Tur, Lav R. Varshney, Royce Moon, Samuel Schapiro, Sumuk Shashidhar","submitted_at":"2025-04-25T20:33:57Z","abstract_excerpt":"Recently, large language models (LLMs) have shown promising abilities to generate novel research ideas in science, a direction which coincides with many foundational principles in computational creativity (CC). In light of these developments, we present an idea generation system named Spark that couples retrieval-augmented idea generation using LLMs with a reviewer model named Judge trained on 600K scientific reviews from OpenReview. Our work is both a system demonstration and intended to inspire other CC researchers to explore grounding the generation and evaluation of scientific ideas within"},"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":"2504.20090","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-25T20:33:57Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"d58e33ee1a92cca7d98ca780ea7e697f74ab49e1c34126ef7cfafd9661ec1f10","abstract_canon_sha256":"f4f62f74e31e548b5dd9fbf9063124198d868ff908579bad2b49054ac6478a9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:24.082752Z","signature_b64":"djkXgSQhnIFHwRY2HlMhpXvP88f3woCNJmD9bDylzwjS4jdT3tVXBMlfae9ia6V1qfMWtKUK7q27bed/bnufDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb7e4cd40a5f0f59ce5b0f7703741335389a0c8a242d5f5bc624f919bd4a2b5c","last_reissued_at":"2026-07-05T11:07:24.082259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:24.082259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spark: A System for Scientifically Creative Idea Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.AI","authors_text":"Aishik Sanyal, Dilek Hakkani-Tur, Lav R. Varshney, Royce Moon, Samuel Schapiro, Sumuk Shashidhar","submitted_at":"2025-04-25T20:33:57Z","abstract_excerpt":"Recently, large language models (LLMs) have shown promising abilities to generate novel research ideas in science, a direction which coincides with many foundational principles in computational creativity (CC). In light of these developments, we present an idea generation system named Spark that couples retrieval-augmented idea generation using LLMs with a reviewer model named Judge trained on 600K scientific reviews from OpenReview. Our work is both a system demonstration and intended to inspire other CC researchers to explore grounding the generation and evaluation of scientific ideas within"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20090","kind":"arxiv","version":2},"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/2504.20090/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":"2504.20090","created_at":"2026-07-05T11:07:24.082322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.20090v2","created_at":"2026-07-05T11:07:24.082322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20090","created_at":"2026-07-05T11:07:24.082322+00:00"},{"alias_kind":"pith_short_12","alias_value":"7N7EZVAKL4HV","created_at":"2026-07-05T11:07:24.082322+00:00"},{"alias_kind":"pith_short_16","alias_value":"7N7EZVAKL4HVTTS3","created_at":"2026-07-05T11:07:24.082322+00:00"},{"alias_kind":"pith_short_8","alias_value":"7N7EZVAK","created_at":"2026-07-05T11:07:24.082322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.28158","citing_title":"Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05517","citing_title":"UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7N7EZVAKL4HVTTS3B53QG5ATGU","json":"https://pith.science/pith/7N7EZVAKL4HVTTS3B53QG5ATGU.json","graph_json":"https://pith.science/api/pith-number/7N7EZVAKL4HVTTS3B53QG5ATGU/graph.json","events_json":"https://pith.science/api/pith-number/7N7EZVAKL4HVTTS3B53QG5ATGU/events.json","paper":"https://pith.science/paper/7N7EZVAK"},"agent_actions":{"view_html":"https://pith.science/pith/7N7EZVAKL4HVTTS3B53QG5ATGU","download_json":"https://pith.science/pith/7N7EZVAKL4HVTTS3B53QG5ATGU.json","view_paper":"https://pith.science/paper/7N7EZVAK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.20090&json=true","fetch_graph":"https://pith.science/api/pith-number/7N7EZVAKL4HVTTS3B53QG5ATGU/graph.json","fetch_events":"https://pith.science/api/pith-number/7N7EZVAKL4HVTTS3B53QG5ATGU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7N7EZVAKL4HVTTS3B53QG5ATGU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7N7EZVAKL4HVTTS3B53QG5ATGU/action/storage_attestation","attest_author":"https://pith.science/pith/7N7EZVAKL4HVTTS3B53QG5ATGU/action/author_attestation","sign_citation":"https://pith.science/pith/7N7EZVAKL4HVTTS3B53QG5ATGU/action/citation_signature","submit_replication":"https://pith.science/pith/7N7EZVAKL4HVTTS3B53QG5ATGU/action/replication_record"}},"created_at":"2026-07-05T11:07:24.082322+00:00","updated_at":"2026-07-05T11:07:24.082322+00:00"}