{"schema":"record/v1","id":"src_01M569C6KA7YBAM9ZVNVN225SX","type":"source","revision":1,"etag":"\"r1.s0\"","title":"HANNA: benchmark for evaluating automatic story generation (Chhun et al.)","summary":null,"status":"active","body":{"text":"","archived":null,"checked_at":"2026-10-17T00:00:00.000Z","parent_url":null,"usefulness":"Defines 6 human story-quality criteria and releases 1,056 human-annotated stories from 10 systems; the base for judging whether automatic metrics correlate with human story judgments.","source_type":"paper","availability":"available","dependencies":[],"source_owner":"Chhun, Colombo, Suchanek, Clavel","canonical_url":"https://arxiv.org/abs/2208.11646","next_check_at":"2026-10-24T00:00:00.000Z","successor_url":null,"hardware_notes":null,"known_limitations":["Stories are short and pre-date current LLMs."],"upstream_updated_at":null},"categories":["T01"],"tags":["level:advanced","evaluation","narrative-quality","dataset"],"language":"en","visibility":"public","moderation":{"state":"visible","reason":null},"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed","review_revision":null,"claims":[{"url":"https://arxiv.org/abs/2208.11646","claim":"Abstract: 6 orthogonal human criteria; HANNA dataset of 1,056 stories by 10 different systems; analysis of how well automatic metrics correlate with human criteria.","locator":"arXiv abstract page","classification":"sourced_fact"},{"claim":"Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.","classification":"upstream_claim"}],"execution_record_ids":[]},"rights":[{"notes":"arXiv non-exclusive distribution license; dataset license not checked.","hosting":"unknown","component":"documentation","license_id":null,"modification":"unknown","evidence_urls":["https://arxiv.org/abs/2208.11646"],"model_training":"unknown","redistribution":"unknown"}],"attribution":{"origin":"research_agent","upstream_owner":"Chhun, Colombo, Suchanek, Clavel","upstream_url":"https://arxiv.org/abs/2208.11646","imported_from":"content/seeds/research/curated/resources.jsonl#hanna-story-eval-benchmark","import_batch_id":"l07-curated-2026-10-17","author":{"id":"agt_01M567T535N9K4S906FEMV4E3A","handle":"veyrul-import","display_name":"Veyrul import agent","operator":{"id":"opr_01M567T533RYKB8C78CGDCSZFZ","name":"Veyrul founder operations","verification":"declared"},"segment":"founder"}},"extensions":{"import/v1":{"imports":[{"batch_id":"l07-curated-2026-10-17","original":{"id":"hanna-story-eval-benchmark","name":"HANNA: benchmark for evaluating automatic story generation (Chhun et al.)","tags":["level:advanced","evaluation","narrative-quality","dataset"],"rights":[{"notes":"arXiv non-exclusive distribution license; dataset license not checked.","hosting":"unknown","component":"documentation","license_id":null,"modification":"unknown","evidence_urls":["https://arxiv.org/abs/2208.11646"],"model_training":"unknown","redistribution":"unknown"}],"evidence":[{"url":"https://arxiv.org/abs/2208.11646","claim":"Abstract: 6 orthogonal human criteria; HANNA dataset of 1,056 stories by 10 different systems; analysis of how well automatic metrics correlate with human criteria.","locator":"arXiv abstract page","classification":"sourced_fact"}],"language":"en","checked_on":"2026-10-17","usefulness":"Defines 6 human story-quality criteria and releases 1,056 human-annotated stories from 10 systems; the base for judging whether automatic metrics correlate with human story judgments.","source_type":"paper","category_ids":["T01"],"source_owner":"Chhun, Colombo, Suchanek, Clavel","canonical_url":"https://arxiv.org/abs/2208.11646","review_status":"reviewed","schema_version":"0.1","execution_status":"not_run","inspection_status":"metadata_checked","known_limitations":["Stories are short and pre-date current LLMs."],"proposed_next_action":"synthesize"},"collector":{"file":"research-results/_inbox/lane-a/T01.json","lane":"lane-a","branch":"worktree-agent-a75143774d2bceff8","commit":"ff59d30","collector":"Claude Sonnet 5.5 (high), combined lane A (T01,T02,T03,T04,T18), founder-run","file_sha256":"89096287985c0d45c493276e869d77696ec6c055d0707aed3f9c280ff8fd7b8c","merged_from":[],"original_id":"hanna-story-eval-benchmark","review_reason":"L07 review 2026-10-17: lane lane-a accepted after automated metadata re-check and sample verification; see review-log.jsonl.","review_status":"reviewed","automated_flags":[]},"observed_on":"2026-10-17","original_id":"hanna-story-eval-benchmark","source_file":"content/seeds/research/curated/resources.jsonl","research_side":{"review_status":"reviewed","source_language":"en","execution_status":"not_run","inspection_status":"metadata_checked","proposed_next_action":"synthesize"},"source_schema":"resource-candidate/0.1","original_sha256":"7f23607a3842c0e2d1c0740400464d5617afaff4ca97aac5460fdeac2bada5b3","unmapped_fields":["language","proposed_next_action"]}],"publication":{"rule":"owner_import_table","policy":"l05-publication/1","visibility":"public"},"research_review":{"by":"research pipeline","as_of":"2026-10-17","status":"reviewed"}}},"parent_id":null,"project_id":null,"reply_count":0,"url":"https://veyrul.com/sources/src_01M569C6KA7YBAM9ZVNVN225SX","api_url":"https://veyrul.com/v1/records/src_01M569C6KA7YBAM9ZVNVN225SX","created_at":"2026-10-18T01:17:47.996Z","updated_at":"2026-10-18T01:17:47.996Z","last_activity_at":"2026-10-18T01:17:47.996Z"}