{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DQCKP33HSEHI325HPUTUX6FNXP","short_pith_number":"pith:DQCKP33H","schema_version":"1.0","canonical_sha256":"1c04a7ef67910e8deba77d274bf8adbbfb8294dd407391c27fdc63b519b5ecb5","source":{"kind":"arxiv","id":"2508.11779","version":1},"attestation_state":"computed","paper":{"title":"A Multi-Task Evaluation of LLMs' Processing of Academic Text Input","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["econ.GN","q-fin.EC"],"primary_cat":"cs.CL","authors_text":"Olivia R. Liu Sheng, Tianyi Li, Yu Qin","submitted_at":"2025-08-15T19:05:57Z","abstract_excerpt":"How much large language models (LLMs) can aid scientific discovery, notably in assisting academic peer review, is in heated debate. Between a literature digest and a human-comparable research assistant lies their practical application potential. We organize individual tasks that computer science studies employ in separate terms into a guided and robust workflow to evaluate LLMs' processing of academic text input. We employ four tasks in the assessment: content reproduction/comparison/scoring/reflection, each demanding a specific role of the LLM (oracle/judgmental arbiter/knowledgeable arbiter/"},"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":"2508.11779","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-15T19:05:57Z","cross_cats_sorted":["econ.GN","q-fin.EC"],"title_canon_sha256":"a4443aeac6a734c17560c06fe328e6801e1c74d4c5a42b41600ce8c3a9fb8723","abstract_canon_sha256":"64c42028d67a20f794e681a22d5a4c5228d606bf68cab9935e631be5ed72b045"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:54.291657Z","signature_b64":"3m1GAD5Z4N3hsj0CV8FCJhzcgfnFlI7c5gh3dpa5Rhptn8SuAZhVoYAmzuPpyTzLasEfrJt95BrxkVUVBcs6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c04a7ef67910e8deba77d274bf8adbbfb8294dd407391c27fdc63b519b5ecb5","last_reissued_at":"2026-07-05T11:54:54.291262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:54.291262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multi-Task Evaluation of LLMs' Processing of Academic Text Input","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["econ.GN","q-fin.EC"],"primary_cat":"cs.CL","authors_text":"Olivia R. Liu Sheng, Tianyi Li, Yu Qin","submitted_at":"2025-08-15T19:05:57Z","abstract_excerpt":"How much large language models (LLMs) can aid scientific discovery, notably in assisting academic peer review, is in heated debate. Between a literature digest and a human-comparable research assistant lies their practical application potential. We organize individual tasks that computer science studies employ in separate terms into a guided and robust workflow to evaluate LLMs' processing of academic text input. We employ four tasks in the assessment: content reproduction/comparison/scoring/reflection, each demanding a specific role of the LLM (oracle/judgmental arbiter/knowledgeable arbiter/"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11779","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/2508.11779/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":"2508.11779","created_at":"2026-07-05T11:54:54.291323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11779v1","created_at":"2026-07-05T11:54:54.291323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11779","created_at":"2026-07-05T11:54:54.291323+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQCKP33HSEHI","created_at":"2026-07-05T11:54:54.291323+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQCKP33HSEHI325H","created_at":"2026-07-05T11:54:54.291323+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQCKP33H","created_at":"2026-07-05T11:54:54.291323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05384","citing_title":"Stability vs. Manipulability: Evaluating Robustness Under Post-Decision Interaction in LLM Judges","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28187","citing_title":"Whose Name Comes Up? III: Persona Prompting Effects in LLM-Based Scholar Recommendation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06571","citing_title":"LLM-based Schema-Guided Extraction and Validation of Missing-Person Intelligence from Heterogeneous Data Sources","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DQCKP33HSEHI325HPUTUX6FNXP","json":"https://pith.science/pith/DQCKP33HSEHI325HPUTUX6FNXP.json","graph_json":"https://pith.science/api/pith-number/DQCKP33HSEHI325HPUTUX6FNXP/graph.json","events_json":"https://pith.science/api/pith-number/DQCKP33HSEHI325HPUTUX6FNXP/events.json","paper":"https://pith.science/paper/DQCKP33H"},"agent_actions":{"view_html":"https://pith.science/pith/DQCKP33HSEHI325HPUTUX6FNXP","download_json":"https://pith.science/pith/DQCKP33HSEHI325HPUTUX6FNXP.json","view_paper":"https://pith.science/paper/DQCKP33H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11779&json=true","fetch_graph":"https://pith.science/api/pith-number/DQCKP33HSEHI325HPUTUX6FNXP/graph.json","fetch_events":"https://pith.science/api/pith-number/DQCKP33HSEHI325HPUTUX6FNXP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQCKP33HSEHI325HPUTUX6FNXP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQCKP33HSEHI325HPUTUX6FNXP/action/storage_attestation","attest_author":"https://pith.science/pith/DQCKP33HSEHI325HPUTUX6FNXP/action/author_attestation","sign_citation":"https://pith.science/pith/DQCKP33HSEHI325HPUTUX6FNXP/action/citation_signature","submit_replication":"https://pith.science/pith/DQCKP33HSEHI325HPUTUX6FNXP/action/replication_record"}},"created_at":"2026-07-05T11:54:54.291323+00:00","updated_at":"2026-07-05T11:54:54.291323+00:00"}