{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B23UHDYWBRITON7TEAIRR63GGI","short_pith_number":"pith:B23UHDYW","schema_version":"1.0","canonical_sha256":"0eb7438f160c513737f3201118fb663213c51e1c7537bf1e48e5c947203f72cb","source":{"kind":"arxiv","id":"2607.10474","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning with Verifiable Physics: Post-training LLMs with Continuous Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CE"],"primary_cat":"cs.LG","authors_text":"Alan Edelman, Christopher Vincent Rackauckas, Pengfei Cai, Rafael Gomez-Bombarelli, Utkarsh Utkarsh","submitted_at":"2026-07-11T20:53:04Z","abstract_excerpt":"Partial differential equations (PDEs) are foundational to modeling in science and engineering, but constructing reliable numerical solvers remains labor-intensive, demanding expert knowledge of discretization schemes, stability conditions, and boundary treatments. Recent work has begun to frame PDE solving as a code-generation task for large language models (LLMs), yet existing approaches operate primarily at inference time: relying on prompting, debugging, self-refinement, and test-time scaling rather than adapting the model itself. In parallel, reinforcement learning with verifiable rewards "},"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":"2607.10474","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-11T20:53:04Z","cross_cats_sorted":["cs.AI","cs.CE"],"title_canon_sha256":"d08492810c40051c8c49bbb53ad45a9370bb6f390e20fa9faacd60ef3ba03959","abstract_canon_sha256":"e664fc78e1cffd2177d88e9aa47fe0f7ab97412207736554bee0fd7253b2311e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:21:17.553137Z","signature_b64":"UCcOs0dc9N7dt4f9wf1nbOBWM31ZEgrb3o9YV/3/Er+7gYs5UkSIOKGiQxFCcCIip4+r9+Pd7P5vfQ23A/LlAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0eb7438f160c513737f3201118fb663213c51e1c7537bf1e48e5c947203f72cb","last_reissued_at":"2026-07-14T01:21:17.552307Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:21:17.552307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Verifiable Physics: Post-training LLMs with Continuous Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CE"],"primary_cat":"cs.LG","authors_text":"Alan Edelman, Christopher Vincent Rackauckas, Pengfei Cai, Rafael Gomez-Bombarelli, Utkarsh Utkarsh","submitted_at":"2026-07-11T20:53:04Z","abstract_excerpt":"Partial differential equations (PDEs) are foundational to modeling in science and engineering, but constructing reliable numerical solvers remains labor-intensive, demanding expert knowledge of discretization schemes, stability conditions, and boundary treatments. Recent work has begun to frame PDE solving as a code-generation task for large language models (LLMs), yet existing approaches operate primarily at inference time: relying on prompting, debugging, self-refinement, and test-time scaling rather than adapting the model itself. In parallel, reinforcement learning with verifiable rewards "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10474","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/2607.10474/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":"2607.10474","created_at":"2026-07-14T01:21:17.552744+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.10474v1","created_at":"2026-07-14T01:21:17.552744+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10474","created_at":"2026-07-14T01:21:17.552744+00:00"},{"alias_kind":"pith_short_12","alias_value":"B23UHDYWBRIT","created_at":"2026-07-14T01:21:17.552744+00:00"},{"alias_kind":"pith_short_16","alias_value":"B23UHDYWBRITON7T","created_at":"2026-07-14T01:21:17.552744+00:00"},{"alias_kind":"pith_short_8","alias_value":"B23UHDYW","created_at":"2026-07-14T01:21:17.552744+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/B23UHDYWBRITON7TEAIRR63GGI","json":"https://pith.science/pith/B23UHDYWBRITON7TEAIRR63GGI.json","graph_json":"https://pith.science/api/pith-number/B23UHDYWBRITON7TEAIRR63GGI/graph.json","events_json":"https://pith.science/api/pith-number/B23UHDYWBRITON7TEAIRR63GGI/events.json","paper":"https://pith.science/paper/B23UHDYW"},"agent_actions":{"view_html":"https://pith.science/pith/B23UHDYWBRITON7TEAIRR63GGI","download_json":"https://pith.science/pith/B23UHDYWBRITON7TEAIRR63GGI.json","view_paper":"https://pith.science/paper/B23UHDYW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.10474&json=true","fetch_graph":"https://pith.science/api/pith-number/B23UHDYWBRITON7TEAIRR63GGI/graph.json","fetch_events":"https://pith.science/api/pith-number/B23UHDYWBRITON7TEAIRR63GGI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B23UHDYWBRITON7TEAIRR63GGI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B23UHDYWBRITON7TEAIRR63GGI/action/storage_attestation","attest_author":"https://pith.science/pith/B23UHDYWBRITON7TEAIRR63GGI/action/author_attestation","sign_citation":"https://pith.science/pith/B23UHDYWBRITON7TEAIRR63GGI/action/citation_signature","submit_replication":"https://pith.science/pith/B23UHDYWBRITON7TEAIRR63GGI/action/replication_record"}},"created_at":"2026-07-14T01:21:17.552744+00:00","updated_at":"2026-07-14T01:21:17.552744+00:00"}