{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KZWTEUEDHDIOS2JGJFLVZODNKN","short_pith_number":"pith:KZWTEUED","schema_version":"1.0","canonical_sha256":"566d32508338d0e9692649575cb86d53539cf1f7e5823f3edf2286a0019d5bd1","source":{"kind":"arxiv","id":"2505.24776","version":1},"attestation_state":"computed","paper":{"title":"Diffusion-Based Symbolic Regression","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jacob Hochhalter, Robert M. Kirby, Shandian Zhe, Zachary Bastiani","submitted_at":"2025-05-30T16:39:29Z","abstract_excerpt":"Diffusion has emerged as a powerful framework for generative modeling, achieving remarkable success in applications such as image and audio synthesis. Enlightened by this progress, we propose a novel diffusion-based approach for symbolic regression. We construct a random mask-based diffusion and denoising process to generate diverse and high-quality equations. We integrate this generative processes with a token-wise Group Relative Policy Optimization (GRPO) method to conduct efficient reinforcement learning on the given measurement dataset. In addition, we introduce a long short-term risk-seek"},"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":"2505.24776","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T16:39:29Z","cross_cats_sorted":[],"title_canon_sha256":"43299c600dc391961acd52d75743e47fd44239e1748b2ac786fc30f7baaaeb87","abstract_canon_sha256":"42e44dc77a420b8135940ad859b2641cf36d2bce9e4ee2bfa3d999eae51300de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:56.465391Z","signature_b64":"eXgxd3VOrh/wIBGha6qmjpwanL1dGI+hGnwCitBMObKGbk88bI5PWaTI+KpEdDDhYYw+xcCvotjCRd3UXL1mDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"566d32508338d0e9692649575cb86d53539cf1f7e5823f3edf2286a0019d5bd1","last_reissued_at":"2026-07-05T11:12:56.464824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:56.464824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion-Based Symbolic Regression","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jacob Hochhalter, Robert M. Kirby, Shandian Zhe, Zachary Bastiani","submitted_at":"2025-05-30T16:39:29Z","abstract_excerpt":"Diffusion has emerged as a powerful framework for generative modeling, achieving remarkable success in applications such as image and audio synthesis. Enlightened by this progress, we propose a novel diffusion-based approach for symbolic regression. We construct a random mask-based diffusion and denoising process to generate diverse and high-quality equations. We integrate this generative processes with a token-wise Group Relative Policy Optimization (GRPO) method to conduct efficient reinforcement learning on the given measurement dataset. In addition, we introduce a long short-term risk-seek"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24776","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/2505.24776/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":"2505.24776","created_at":"2026-07-05T11:12:56.464883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24776v1","created_at":"2026-07-05T11:12:56.464883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24776","created_at":"2026-07-05T11:12:56.464883+00:00"},{"alias_kind":"pith_short_12","alias_value":"KZWTEUEDHDIO","created_at":"2026-07-05T11:12:56.464883+00:00"},{"alias_kind":"pith_short_16","alias_value":"KZWTEUEDHDIOS2JG","created_at":"2026-07-05T11:12:56.464883+00:00"},{"alias_kind":"pith_short_8","alias_value":"KZWTEUED","created_at":"2026-07-05T11:12:56.464883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13260","citing_title":"Extracting Governing Equations from Latent Dynamics via Multi-View Contrastive Learning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07915","citing_title":"EditSR: Enhancing Neural Symbolic Regression via Edit-based Rectification","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KZWTEUEDHDIOS2JGJFLVZODNKN","json":"https://pith.science/pith/KZWTEUEDHDIOS2JGJFLVZODNKN.json","graph_json":"https://pith.science/api/pith-number/KZWTEUEDHDIOS2JGJFLVZODNKN/graph.json","events_json":"https://pith.science/api/pith-number/KZWTEUEDHDIOS2JGJFLVZODNKN/events.json","paper":"https://pith.science/paper/KZWTEUED"},"agent_actions":{"view_html":"https://pith.science/pith/KZWTEUEDHDIOS2JGJFLVZODNKN","download_json":"https://pith.science/pith/KZWTEUEDHDIOS2JGJFLVZODNKN.json","view_paper":"https://pith.science/paper/KZWTEUED","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24776&json=true","fetch_graph":"https://pith.science/api/pith-number/KZWTEUEDHDIOS2JGJFLVZODNKN/graph.json","fetch_events":"https://pith.science/api/pith-number/KZWTEUEDHDIOS2JGJFLVZODNKN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KZWTEUEDHDIOS2JGJFLVZODNKN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KZWTEUEDHDIOS2JGJFLVZODNKN/action/storage_attestation","attest_author":"https://pith.science/pith/KZWTEUEDHDIOS2JGJFLVZODNKN/action/author_attestation","sign_citation":"https://pith.science/pith/KZWTEUEDHDIOS2JGJFLVZODNKN/action/citation_signature","submit_replication":"https://pith.science/pith/KZWTEUEDHDIOS2JGJFLVZODNKN/action/replication_record"}},"created_at":"2026-07-05T11:12:56.464883+00:00","updated_at":"2026-07-05T11:12:56.464883+00:00"}