{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IN6YQY2MWWF73DS5LV6JNXUAFS","short_pith_number":"pith:IN6YQY2M","schema_version":"1.0","canonical_sha256":"437d88634cb58bfd8e5d5d7c96de802cb2d6065cdd7f25c0aa3440bcae535ca3","source":{"kind":"arxiv","id":"2606.01091","version":1},"attestation_state":"computed","paper":{"title":"Deep Research as Rubric for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Chen, Deqing Yang, Jiaqing Liang, Lefan Zhang, Wangyi Mei, Yan Gao, Yao Hu, Yin Cai, Yi Wu, Zhenhan Bai, Zhenxin Ding, Zhouhong Gu","submitted_at":"2026-05-31T08:25:04Z","abstract_excerpt":"Open-ended reasoning and long-form generation tasks lack reliable automatic verification signals for reward-based policy optimization. Rubrics offer a promising alternative, but existing approaches treat them as given artifacts -- either hand-crafted or prompt-generated -- and often miss the task-specific, knowledge-intensive dimensions that matter most, distorting the reward signal. Our key observation is that rubric construction is itself a research problem: identifying what makes a response correct or insightful requires discovering and synthesizing external knowledge. We propose Deep Resea"},"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":"2606.01091","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T08:25:04Z","cross_cats_sorted":[],"title_canon_sha256":"227bd14b9ceabb6c8c9322ada39eb8fbe95d0e00e2db5813fa987647d0766c8c","abstract_canon_sha256":"d0d8c035c286954b8351b0986d80693722d2a620462f2afd662e9336c18ab7f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:20.977135Z","signature_b64":"Ya2h7CFPekwQ4massIPKSybII3v8R39P4nND45oXY4PZOKme0cn3bp1EyCsk78AAAe6U+EWQtQTo4F8HJ7cNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"437d88634cb58bfd8e5d5d7c96de802cb2d6065cdd7f25c0aa3440bcae535ca3","last_reissued_at":"2026-06-02T01:04:20.976694Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:20.976694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Research as Rubric for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Chen, Deqing Yang, Jiaqing Liang, Lefan Zhang, Wangyi Mei, Yan Gao, Yao Hu, Yin Cai, Yi Wu, Zhenhan Bai, Zhenxin Ding, Zhouhong Gu","submitted_at":"2026-05-31T08:25:04Z","abstract_excerpt":"Open-ended reasoning and long-form generation tasks lack reliable automatic verification signals for reward-based policy optimization. Rubrics offer a promising alternative, but existing approaches treat them as given artifacts -- either hand-crafted or prompt-generated -- and often miss the task-specific, knowledge-intensive dimensions that matter most, distorting the reward signal. Our key observation is that rubric construction is itself a research problem: identifying what makes a response correct or insightful requires discovering and synthesizing external knowledge. We propose Deep Resea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01091","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/2606.01091/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":"2606.01091","created_at":"2026-06-02T01:04:20.976760+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01091v1","created_at":"2026-06-02T01:04:20.976760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01091","created_at":"2026-06-02T01:04:20.976760+00:00"},{"alias_kind":"pith_short_12","alias_value":"IN6YQY2MWWF7","created_at":"2026-06-02T01:04:20.976760+00:00"},{"alias_kind":"pith_short_16","alias_value":"IN6YQY2MWWF73DS5","created_at":"2026-06-02T01:04:20.976760+00:00"},{"alias_kind":"pith_short_8","alias_value":"IN6YQY2M","created_at":"2026-06-02T01:04:20.976760+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/IN6YQY2MWWF73DS5LV6JNXUAFS","json":"https://pith.science/pith/IN6YQY2MWWF73DS5LV6JNXUAFS.json","graph_json":"https://pith.science/api/pith-number/IN6YQY2MWWF73DS5LV6JNXUAFS/graph.json","events_json":"https://pith.science/api/pith-number/IN6YQY2MWWF73DS5LV6JNXUAFS/events.json","paper":"https://pith.science/paper/IN6YQY2M"},"agent_actions":{"view_html":"https://pith.science/pith/IN6YQY2MWWF73DS5LV6JNXUAFS","download_json":"https://pith.science/pith/IN6YQY2MWWF73DS5LV6JNXUAFS.json","view_paper":"https://pith.science/paper/IN6YQY2M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01091&json=true","fetch_graph":"https://pith.science/api/pith-number/IN6YQY2MWWF73DS5LV6JNXUAFS/graph.json","fetch_events":"https://pith.science/api/pith-number/IN6YQY2MWWF73DS5LV6JNXUAFS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IN6YQY2MWWF73DS5LV6JNXUAFS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IN6YQY2MWWF73DS5LV6JNXUAFS/action/storage_attestation","attest_author":"https://pith.science/pith/IN6YQY2MWWF73DS5LV6JNXUAFS/action/author_attestation","sign_citation":"https://pith.science/pith/IN6YQY2MWWF73DS5LV6JNXUAFS/action/citation_signature","submit_replication":"https://pith.science/pith/IN6YQY2MWWF73DS5LV6JNXUAFS/action/replication_record"}},"created_at":"2026-06-02T01:04:20.976760+00:00","updated_at":"2026-06-02T01:04:20.976760+00:00"}