{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L5H73GYSWLTGV7XI7OSN3ZKUYV","short_pith_number":"pith:L5H73GYS","schema_version":"1.0","canonical_sha256":"5f4ffd9b12b2e66afee8fba4dde554c54f62deddbb3af17c272450f51b05e428","source":{"kind":"arxiv","id":"2606.04507","version":1},"attestation_state":"computed","paper":{"title":"Self-Evolving Deep Research via Joint Generation and Evaluation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengkun Cai, Han Zhu, Sirui Han, Xing Chen, Yike Guo, Yuanfeng Song","submitted_at":"2026-06-03T06:38:19Z","abstract_excerpt":"Large Language Models (LLMs) have become increasingly adopted in daily applications, with deep research standing out as a particularly important capability. Unlike traditional question-answering (QA) tasks, deep research report generation lacks definitive ground-truth, making reward design inherently unverifiable and limiting effective reinforcement learning. Existing approaches mitigate this challenge with LLM-as-a-judge and query-dependent evaluation rubrics, but they still rely on static evaluators that cannot adapt their standards as the solver improves, leading to insufficient and eventua"},"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":"2606.04507","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T06:38:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"411044713b587bd0039a2e1a514fc63176b153c1ab3e7600fa7c4bd1381db656","abstract_canon_sha256":"5eeb565ba03ef1c09eca51046279b44a41dd7745cfc9643eba650f7287ee595b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:15.032734Z","signature_b64":"hRUyWCBoNZuo0HAd/vze8EOMRhn+sTMdTL9H5Vz1yxfkvV0GuvmertULRScgb4bUtElOoFfFV7aqDNfdomV+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f4ffd9b12b2e66afee8fba4dde554c54f62deddbb3af17c272450f51b05e428","last_reissued_at":"2026-06-04T01:09:15.032060Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:15.032060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Evolving Deep Research via Joint Generation and Evaluation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengkun Cai, Han Zhu, Sirui Han, Xing Chen, Yike Guo, Yuanfeng Song","submitted_at":"2026-06-03T06:38:19Z","abstract_excerpt":"Large Language Models (LLMs) have become increasingly adopted in daily applications, with deep research standing out as a particularly important capability. Unlike traditional question-answering (QA) tasks, deep research report generation lacks definitive ground-truth, making reward design inherently unverifiable and limiting effective reinforcement learning. Existing approaches mitigate this challenge with LLM-as-a-judge and query-dependent evaluation rubrics, but they still rely on static evaluators that cannot adapt their standards as the solver improves, leading to insufficient and eventua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04507","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/2606.04507/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":"2606.04507","created_at":"2026-06-04T01:09:15.032158+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04507v1","created_at":"2026-06-04T01:09:15.032158+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04507","created_at":"2026-06-04T01:09:15.032158+00:00"},{"alias_kind":"pith_short_12","alias_value":"L5H73GYSWLTG","created_at":"2026-06-04T01:09:15.032158+00:00"},{"alias_kind":"pith_short_16","alias_value":"L5H73GYSWLTGV7XI","created_at":"2026-06-04T01:09:15.032158+00:00"},{"alias_kind":"pith_short_8","alias_value":"L5H73GYS","created_at":"2026-06-04T01:09:15.032158+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/L5H73GYSWLTGV7XI7OSN3ZKUYV","json":"https://pith.science/pith/L5H73GYSWLTGV7XI7OSN3ZKUYV.json","graph_json":"https://pith.science/api/pith-number/L5H73GYSWLTGV7XI7OSN3ZKUYV/graph.json","events_json":"https://pith.science/api/pith-number/L5H73GYSWLTGV7XI7OSN3ZKUYV/events.json","paper":"https://pith.science/paper/L5H73GYS"},"agent_actions":{"view_html":"https://pith.science/pith/L5H73GYSWLTGV7XI7OSN3ZKUYV","download_json":"https://pith.science/pith/L5H73GYSWLTGV7XI7OSN3ZKUYV.json","view_paper":"https://pith.science/paper/L5H73GYS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04507&json=true","fetch_graph":"https://pith.science/api/pith-number/L5H73GYSWLTGV7XI7OSN3ZKUYV/graph.json","fetch_events":"https://pith.science/api/pith-number/L5H73GYSWLTGV7XI7OSN3ZKUYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L5H73GYSWLTGV7XI7OSN3ZKUYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L5H73GYSWLTGV7XI7OSN3ZKUYV/action/storage_attestation","attest_author":"https://pith.science/pith/L5H73GYSWLTGV7XI7OSN3ZKUYV/action/author_attestation","sign_citation":"https://pith.science/pith/L5H73GYSWLTGV7XI7OSN3ZKUYV/action/citation_signature","submit_replication":"https://pith.science/pith/L5H73GYSWLTGV7XI7OSN3ZKUYV/action/replication_record"}},"created_at":"2026-06-04T01:09:15.032158+00:00","updated_at":"2026-06-04T01:09:15.032158+00:00"}