{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:R6AYCIEBQKEYXQARLDP6LRL77L","short_pith_number":"pith:R6AYCIEB","schema_version":"1.0","canonical_sha256":"8f8181208182898bc01158dfe5c57ffad3c808b0ee6963fe5ab0d00dd181b776","source":{"kind":"arxiv","id":"2512.00986","version":3},"attestation_state":"computed","paper":{"title":"ADRA-Bank: A Modular Benchmark for Academic Deep Research Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Feiyang Xu, Han Shi, Haoli Bai, Ho-fung Leung, Irwin King, Jiele Wu, Muzhi Li, Shuai Zou, Yifan Li, Zhihan Guo","submitted_at":"2025-11-30T17:16:47Z","abstract_excerpt":"A surge in academic publications calls for automated deep research (DR) systems, but accurately evaluating them is still an open problem. First, existing benchmarks often focus narrowly on retrieval while neglecting high-level planning and reasoning. Second, existing benchmarks favor general domains over the academic domains that are the core application for DR agents. To address these gaps, we introduce ADRA-Bank, a modular benchmark for Academic DR Agents. Grounded in academic literature, our benchmark is a human-annotated dataset of 200 instances across 10 academic domains, including both r"},"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":"2512.00986","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-30T17:16:47Z","cross_cats_sorted":[],"title_canon_sha256":"bbba9e9a09251e2ea56d8ed9d7ecdc45c62319c2b5340ad5a291a13cea79386d","abstract_canon_sha256":"2decb693f85448ea5b6ff98d9b452f55961fb2b9188faa94da81fca15aa3059a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:11.777060Z","signature_b64":"EQWf6aDm2cJF2G6/OAz4dK8Pi5ESycOd3K8VwbxisdUWatFjRC6pJQlyT+nKfkvM4NEh8O0/S+ifLfmZcSgTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f8181208182898bc01158dfe5c57ffad3c808b0ee6963fe5ab0d00dd181b776","last_reissued_at":"2026-06-02T02:04:11.776528Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:11.776528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ADRA-Bank: A Modular Benchmark for Academic Deep Research Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Feiyang Xu, Han Shi, Haoli Bai, Ho-fung Leung, Irwin King, Jiele Wu, Muzhi Li, Shuai Zou, Yifan Li, Zhihan Guo","submitted_at":"2025-11-30T17:16:47Z","abstract_excerpt":"A surge in academic publications calls for automated deep research (DR) systems, but accurately evaluating them is still an open problem. First, existing benchmarks often focus narrowly on retrieval while neglecting high-level planning and reasoning. Second, existing benchmarks favor general domains over the academic domains that are the core application for DR agents. To address these gaps, we introduce ADRA-Bank, a modular benchmark for Academic DR Agents. Grounded in academic literature, our benchmark is a human-annotated dataset of 200 instances across 10 academic domains, including both r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.00986","kind":"arxiv","version":3},"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/2512.00986/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":"2512.00986","created_at":"2026-06-02T02:04:11.776588+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.00986v3","created_at":"2026-06-02T02:04:11.776588+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.00986","created_at":"2026-06-02T02:04:11.776588+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6AYCIEBQKEY","created_at":"2026-06-02T02:04:11.776588+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6AYCIEBQKEYXQAR","created_at":"2026-06-02T02:04:11.776588+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6AYCIEB","created_at":"2026-06-02T02:04:11.776588+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/R6AYCIEBQKEYXQARLDP6LRL77L","json":"https://pith.science/pith/R6AYCIEBQKEYXQARLDP6LRL77L.json","graph_json":"https://pith.science/api/pith-number/R6AYCIEBQKEYXQARLDP6LRL77L/graph.json","events_json":"https://pith.science/api/pith-number/R6AYCIEBQKEYXQARLDP6LRL77L/events.json","paper":"https://pith.science/paper/R6AYCIEB"},"agent_actions":{"view_html":"https://pith.science/pith/R6AYCIEBQKEYXQARLDP6LRL77L","download_json":"https://pith.science/pith/R6AYCIEBQKEYXQARLDP6LRL77L.json","view_paper":"https://pith.science/paper/R6AYCIEB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.00986&json=true","fetch_graph":"https://pith.science/api/pith-number/R6AYCIEBQKEYXQARLDP6LRL77L/graph.json","fetch_events":"https://pith.science/api/pith-number/R6AYCIEBQKEYXQARLDP6LRL77L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6AYCIEBQKEYXQARLDP6LRL77L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6AYCIEBQKEYXQARLDP6LRL77L/action/storage_attestation","attest_author":"https://pith.science/pith/R6AYCIEBQKEYXQARLDP6LRL77L/action/author_attestation","sign_citation":"https://pith.science/pith/R6AYCIEBQKEYXQARLDP6LRL77L/action/citation_signature","submit_replication":"https://pith.science/pith/R6AYCIEBQKEYXQARLDP6LRL77L/action/replication_record"}},"created_at":"2026-06-02T02:04:11.776588+00:00","updated_at":"2026-06-02T02:04:11.776588+00:00"}