{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EANVAIKUXKWK3EXD7QPY2TJMWV","short_pith_number":"pith:EANVAIKU","schema_version":"1.0","canonical_sha256":"201b502154baacad92e3fc1f8d4d2cb56596ccb2e2cc3e26be11e22702c5df99","source":{"kind":"arxiv","id":"2607.28990","version":1},"attestation_state":"computed","paper":{"title":"Scaling Scientific Discovery Environments for Turn-Level Agentic RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Keyi Zhang, Min Zhang, Pei Chu, Shiyuan Meng, Yucheng Xu, Yuyang Yu, Zhongying Tu","submitted_at":"2026-07-31T03:34:39Z","abstract_excerpt":"Large language model agents have shown promising capabilities in data-driven scientific discovery tasks, where an agent interacts with an execution environment and produces a statistical claim. Long-horizon scientific analysis remains constrained by the lack of process supervised environments over real-world scientific data. This paper introduces SciDisco, a scalable framework for training Scientific Discovery agents in process-verifiable environments. SciTh\\`eque compiles hypotheses, datasets, hidden evidence graphs, and verifiers into task environments where analytical progress can be checke"},"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":"2607.28990","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-31T03:34:39Z","cross_cats_sorted":[],"title_canon_sha256":"d8a195ec17ed95e448419cd022fafeb8a6ba6d2ed56f1e3d5167ac8c89a9336f","abstract_canon_sha256":"db825e4f7792204a4ca257ae0aafea8fd6efb473d54a1f246642ab26ab406ff6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:17:52.343226Z","signature_b64":"0pPM4yIc+1czHyJwfd8ngBGQNyH4KZCpkkkgY0QCigc4pwrVDEAaTigzNoMUfBg9Cl3+RpPH2T1wdPXgMEO0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"201b502154baacad92e3fc1f8d4d2cb56596ccb2e2cc3e26be11e22702c5df99","last_reissued_at":"2026-08-03T01:17:52.341595Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:17:52.341595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Scientific Discovery Environments for Turn-Level Agentic RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Keyi Zhang, Min Zhang, Pei Chu, Shiyuan Meng, Yucheng Xu, Yuyang Yu, Zhongying Tu","submitted_at":"2026-07-31T03:34:39Z","abstract_excerpt":"Large language model agents have shown promising capabilities in data-driven scientific discovery tasks, where an agent interacts with an execution environment and produces a statistical claim. Long-horizon scientific analysis remains constrained by the lack of process supervised environments over real-world scientific data. This paper introduces SciDisco, a scalable framework for training Scientific Discovery agents in process-verifiable environments. SciTh\\`eque compiles hypotheses, datasets, hidden evidence graphs, and verifiers into task environments where analytical progress can be checke"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28990","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/2607.28990/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":"2607.28990","created_at":"2026-08-03T01:17:52.342541+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28990v1","created_at":"2026-08-03T01:17:52.342541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28990","created_at":"2026-08-03T01:17:52.342541+00:00"},{"alias_kind":"pith_short_12","alias_value":"EANVAIKUXKWK","created_at":"2026-08-03T01:17:52.342541+00:00"},{"alias_kind":"pith_short_16","alias_value":"EANVAIKUXKWK3EXD","created_at":"2026-08-03T01:17:52.342541+00:00"},{"alias_kind":"pith_short_8","alias_value":"EANVAIKU","created_at":"2026-08-03T01:17:52.342541+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.10792","citing_title":"ChemWorld: Programmable Chemical Worlds for Controlled and Replayable Agent Experimentation","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EANVAIKUXKWK3EXD7QPY2TJMWV","json":"https://pith.science/pith/EANVAIKUXKWK3EXD7QPY2TJMWV.json","graph_json":"https://pith.science/api/pith-number/EANVAIKUXKWK3EXD7QPY2TJMWV/graph.json","events_json":"https://pith.science/api/pith-number/EANVAIKUXKWK3EXD7QPY2TJMWV/events.json","paper":"https://pith.science/paper/EANVAIKU"},"agent_actions":{"view_html":"https://pith.science/pith/EANVAIKUXKWK3EXD7QPY2TJMWV","download_json":"https://pith.science/pith/EANVAIKUXKWK3EXD7QPY2TJMWV.json","view_paper":"https://pith.science/paper/EANVAIKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28990&json=true","fetch_graph":"https://pith.science/api/pith-number/EANVAIKUXKWK3EXD7QPY2TJMWV/graph.json","fetch_events":"https://pith.science/api/pith-number/EANVAIKUXKWK3EXD7QPY2TJMWV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EANVAIKUXKWK3EXD7QPY2TJMWV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EANVAIKUXKWK3EXD7QPY2TJMWV/action/storage_attestation","attest_author":"https://pith.science/pith/EANVAIKUXKWK3EXD7QPY2TJMWV/action/author_attestation","sign_citation":"https://pith.science/pith/EANVAIKUXKWK3EXD7QPY2TJMWV/action/citation_signature","submit_replication":"https://pith.science/pith/EANVAIKUXKWK3EXD7QPY2TJMWV/action/replication_record"}},"created_at":"2026-08-03T01:17:52.342541+00:00","updated_at":"2026-08-03T01:17:52.342541+00:00"}