{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:G6TQ2TVPR2LVTJM342CWNC5PY7","short_pith_number":"pith:G6TQ2TVP","schema_version":"1.0","canonical_sha256":"37a70d4eaf8e9759a59be685668bafc7d4825f5bc00c6e716bb68dcf7703b982","source":{"kind":"arxiv","id":"2208.11646","version":4},"attestation_state":"computed","paper":{"title":"Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chlo\\'e Clavel, Cyril Chhun, Fabian M. Suchanek, Pierre Colombo","submitted_at":"2022-08-24T16:35:32Z","abstract_excerpt":"Research on Automatic Story Generation (ASG) relies heavily on human and automatic evaluation. However, there is no consensus on which human evaluation criteria to use, and no analysis of how well automatic criteria correlate with them. In this paper, we propose to re-evaluate ASG evaluation. We introduce a set of 6 orthogonal and comprehensive human criteria, carefully motivated by the social sciences literature. We also present HANNA, an annotated dataset of 1,056 stories produced by 10 different ASG systems. HANNA allows us to quantitatively evaluate the correlations of 72 automatic metrics"},"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":"2208.11646","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-08-24T16:35:32Z","cross_cats_sorted":[],"title_canon_sha256":"bf09b928b0000a711af6838855a390a71c2afc80166518a8c8130cf53ffa35d4","abstract_canon_sha256":"0c65ca5d39360f1346e02e3c3ae1d13f5652c7c053a182a78ae61a19b729cd56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:48.794539Z","signature_b64":"XY45Zi/kj3djcZYPegvfvxobpuRyBTPjRhZNidyzJk1No5eTqFUC0hPAMrRMhQQ9LoPBj/kLmKLuUd+mIiP4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37a70d4eaf8e9759a59be685668bafc7d4825f5bc00c6e716bb68dcf7703b982","last_reissued_at":"2026-07-05T04:57:48.794044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:48.794044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chlo\\'e Clavel, Cyril Chhun, Fabian M. Suchanek, Pierre Colombo","submitted_at":"2022-08-24T16:35:32Z","abstract_excerpt":"Research on Automatic Story Generation (ASG) relies heavily on human and automatic evaluation. However, there is no consensus on which human evaluation criteria to use, and no analysis of how well automatic criteria correlate with them. In this paper, we propose to re-evaluate ASG evaluation. We introduce a set of 6 orthogonal and comprehensive human criteria, carefully motivated by the social sciences literature. We also present HANNA, an annotated dataset of 1,056 stories produced by 10 different ASG systems. HANNA allows us to quantitatively evaluate the correlations of 72 automatic metrics"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.11646","kind":"arxiv","version":4},"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/2208.11646/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":"2208.11646","created_at":"2026-07-05T04:57:48.794113+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.11646v4","created_at":"2026-07-05T04:57:48.794113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.11646","created_at":"2026-07-05T04:57:48.794113+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6TQ2TVPR2LV","created_at":"2026-07-05T04:57:48.794113+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6TQ2TVPR2LVTJM3","created_at":"2026-07-05T04:57:48.794113+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6TQ2TVP","created_at":"2026-07-05T04:57:48.794113+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00918","citing_title":"From Personas to Plot: Character-Grounded Multi-Agent Story Generation for Long-Form Narratives","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07102","citing_title":"SAGE: Hierarchical LLM-Based Literary Evaluation through Ontology-Grounded Interpretive Dimensions","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G6TQ2TVPR2LVTJM342CWNC5PY7","json":"https://pith.science/pith/G6TQ2TVPR2LVTJM342CWNC5PY7.json","graph_json":"https://pith.science/api/pith-number/G6TQ2TVPR2LVTJM342CWNC5PY7/graph.json","events_json":"https://pith.science/api/pith-number/G6TQ2TVPR2LVTJM342CWNC5PY7/events.json","paper":"https://pith.science/paper/G6TQ2TVP"},"agent_actions":{"view_html":"https://pith.science/pith/G6TQ2TVPR2LVTJM342CWNC5PY7","download_json":"https://pith.science/pith/G6TQ2TVPR2LVTJM342CWNC5PY7.json","view_paper":"https://pith.science/paper/G6TQ2TVP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.11646&json=true","fetch_graph":"https://pith.science/api/pith-number/G6TQ2TVPR2LVTJM342CWNC5PY7/graph.json","fetch_events":"https://pith.science/api/pith-number/G6TQ2TVPR2LVTJM342CWNC5PY7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6TQ2TVPR2LVTJM342CWNC5PY7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6TQ2TVPR2LVTJM342CWNC5PY7/action/storage_attestation","attest_author":"https://pith.science/pith/G6TQ2TVPR2LVTJM342CWNC5PY7/action/author_attestation","sign_citation":"https://pith.science/pith/G6TQ2TVPR2LVTJM342CWNC5PY7/action/citation_signature","submit_replication":"https://pith.science/pith/G6TQ2TVPR2LVTJM342CWNC5PY7/action/replication_record"}},"created_at":"2026-07-05T04:57:48.794113+00:00","updated_at":"2026-07-05T04:57:48.794113+00:00"}