{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NDYJDIZINU37H7K3L2WYMAUIAW","short_pith_number":"pith:NDYJDIZI","schema_version":"1.0","canonical_sha256":"68f091a3286d37f3fd5b5ead86028805a9ccc585f480cbf5911b3f6b05259afe","source":{"kind":"arxiv","id":"2606.30556","version":1},"attestation_state":"computed","paper":{"title":"Poller: Are LLMs Suitable for Evaluating the Poetry Understanding Task?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Derek F. Wong, Jingming Yao, Lidia S. Chao, Shanshan Wang","submitted_at":"2026-06-29T16:51:31Z","abstract_excerpt":"Traditional automatic evaluation methods have been shown to be unsuitable for modern Chinese poetry because of the distinct nature of this literary genre. Human evaluation remains reliable, but is expensive and not applicable to large-scale data. In this paper, we propose Poller (Poetry LLM Evaluator), a novel method leveraging large language models (LLMs) to evaluate the poetry understanding task. Specifically, our method requires LLMs to play the role of a poem's author with detailed information, thereby emulating human evaluation and judgment by adopting the poet's perspective. We conducted"},"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":"2606.30556","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T16:51:31Z","cross_cats_sorted":[],"title_canon_sha256":"6bdf0de4dbeb56a9d82265f1472363c88d7dfa63d4da0eb1104a1ad14c48b038","abstract_canon_sha256":"a046c632355a6b9a906e2c66bfd259f9721b28c677eafdb10c35bba2f384e6f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:18:20.389197Z","signature_b64":"57U4Wzo2alW7F01+lZf0xfU/KkD6STQ4HU9MneCFW5cmo7zmlat3e9kkRHtLdl6uO9l8UItTeDitxydxhYQsAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68f091a3286d37f3fd5b5ead86028805a9ccc585f480cbf5911b3f6b05259afe","last_reissued_at":"2026-06-30T02:18:20.388592Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:18:20.388592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Poller: Are LLMs Suitable for Evaluating the Poetry Understanding Task?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Derek F. Wong, Jingming Yao, Lidia S. Chao, Shanshan Wang","submitted_at":"2026-06-29T16:51:31Z","abstract_excerpt":"Traditional automatic evaluation methods have been shown to be unsuitable for modern Chinese poetry because of the distinct nature of this literary genre. Human evaluation remains reliable, but is expensive and not applicable to large-scale data. In this paper, we propose Poller (Poetry LLM Evaluator), a novel method leveraging large language models (LLMs) to evaluate the poetry understanding task. Specifically, our method requires LLMs to play the role of a poem's author with detailed information, thereby emulating human evaluation and judgment by adopting the poet's perspective. We conducted"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30556","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/2606.30556/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":"2606.30556","created_at":"2026-06-30T02:18:20.388688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30556v1","created_at":"2026-06-30T02:18:20.388688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30556","created_at":"2026-06-30T02:18:20.388688+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDYJDIZINU37","created_at":"2026-06-30T02:18:20.388688+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDYJDIZINU37H7K3","created_at":"2026-06-30T02:18:20.388688+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDYJDIZI","created_at":"2026-06-30T02:18:20.388688+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/NDYJDIZINU37H7K3L2WYMAUIAW","json":"https://pith.science/pith/NDYJDIZINU37H7K3L2WYMAUIAW.json","graph_json":"https://pith.science/api/pith-number/NDYJDIZINU37H7K3L2WYMAUIAW/graph.json","events_json":"https://pith.science/api/pith-number/NDYJDIZINU37H7K3L2WYMAUIAW/events.json","paper":"https://pith.science/paper/NDYJDIZI"},"agent_actions":{"view_html":"https://pith.science/pith/NDYJDIZINU37H7K3L2WYMAUIAW","download_json":"https://pith.science/pith/NDYJDIZINU37H7K3L2WYMAUIAW.json","view_paper":"https://pith.science/paper/NDYJDIZI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30556&json=true","fetch_graph":"https://pith.science/api/pith-number/NDYJDIZINU37H7K3L2WYMAUIAW/graph.json","fetch_events":"https://pith.science/api/pith-number/NDYJDIZINU37H7K3L2WYMAUIAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDYJDIZINU37H7K3L2WYMAUIAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDYJDIZINU37H7K3L2WYMAUIAW/action/storage_attestation","attest_author":"https://pith.science/pith/NDYJDIZINU37H7K3L2WYMAUIAW/action/author_attestation","sign_citation":"https://pith.science/pith/NDYJDIZINU37H7K3L2WYMAUIAW/action/citation_signature","submit_replication":"https://pith.science/pith/NDYJDIZINU37H7K3L2WYMAUIAW/action/replication_record"}},"created_at":"2026-06-30T02:18:20.388688+00:00","updated_at":"2026-06-30T02:18:20.388688+00:00"}