{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SMKNJNUIVN5VFEOQRUJODVV6F4","short_pith_number":"pith:SMKNJNUI","schema_version":"1.0","canonical_sha256":"9314d4b688ab7b5291d08d12e1d6be2f2eaeb3171cd7cb890c6f3148917e36d0","source":{"kind":"arxiv","id":"2606.17391","version":1},"attestation_state":"computed","paper":{"title":"NarrativeWorldBench: A Frontier-Saturated Benchmark and a Latent World Model for Long-Horizon Co-Creative Audio Drama","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abdur Rahman, Logan Mann, Mohammad Saifullah, Taaha Kazi, Vasu Sharma","submitted_at":"2026-06-16T01:04:55Z","abstract_excerpt":"Long-form serialized audio drama, with arcs that run for 200 to 800 episodes, is a major creative medium and a setting where frontier large language models (LLMs) fail. We benchmark 21 models, spanning classical, fine-tuned, open-frontier, closed-frontier, and reasoning tiers, on a uniform set of structural narrative metrics. All closed-frontier systems saturate at a plot-beat F1 in the band [0.78, 0.81] and collapse by about -0.20 F1 at horizon h=200. We introduce NarrativeWorldBench, an open benchmark of nine narrative-structure metrics evaluated across horizons h in {10, 20, 50, 100, 200}, "},"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":"2606.17391","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-16T01:04:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e8effc8569fe12719bbb1ea6decffb907dcab8f1a75e2b30f4f6fc2a19543ba8","abstract_canon_sha256":"0a558e07231155ca09107b1bc117364fb6e52a7da84c1e04bfc1e6d10459e178"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:11.026402Z","signature_b64":"3Figfx1+p+29jupTdDB07rlRxtlS9JapEQ4AlzgaoqSYcHvNThcUwh2sJzDx5z3ILTtxVbOEd1VjiK7TUXt8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9314d4b688ab7b5291d08d12e1d6be2f2eaeb3171cd7cb890c6f3148917e36d0","last_reissued_at":"2026-06-19T16:10:11.026033Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:11.026033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NarrativeWorldBench: A Frontier-Saturated Benchmark and a Latent World Model for Long-Horizon Co-Creative Audio Drama","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abdur Rahman, Logan Mann, Mohammad Saifullah, Taaha Kazi, Vasu Sharma","submitted_at":"2026-06-16T01:04:55Z","abstract_excerpt":"Long-form serialized audio drama, with arcs that run for 200 to 800 episodes, is a major creative medium and a setting where frontier large language models (LLMs) fail. We benchmark 21 models, spanning classical, fine-tuned, open-frontier, closed-frontier, and reasoning tiers, on a uniform set of structural narrative metrics. All closed-frontier systems saturate at a plot-beat F1 in the band [0.78, 0.81] and collapse by about -0.20 F1 at horizon h=200. We introduce NarrativeWorldBench, an open benchmark of nine narrative-structure metrics evaluated across horizons h in {10, 20, 50, 100, 200}, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17391","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/2606.17391/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":"2606.17391","created_at":"2026-06-19T16:10:11.026094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17391v1","created_at":"2026-06-19T16:10:11.026094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17391","created_at":"2026-06-19T16:10:11.026094+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMKNJNUIVN5V","created_at":"2026-06-19T16:10:11.026094+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMKNJNUIVN5VFEOQ","created_at":"2026-06-19T16:10:11.026094+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMKNJNUI","created_at":"2026-06-19T16:10:11.026094+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/SMKNJNUIVN5VFEOQRUJODVV6F4","json":"https://pith.science/pith/SMKNJNUIVN5VFEOQRUJODVV6F4.json","graph_json":"https://pith.science/api/pith-number/SMKNJNUIVN5VFEOQRUJODVV6F4/graph.json","events_json":"https://pith.science/api/pith-number/SMKNJNUIVN5VFEOQRUJODVV6F4/events.json","paper":"https://pith.science/paper/SMKNJNUI"},"agent_actions":{"view_html":"https://pith.science/pith/SMKNJNUIVN5VFEOQRUJODVV6F4","download_json":"https://pith.science/pith/SMKNJNUIVN5VFEOQRUJODVV6F4.json","view_paper":"https://pith.science/paper/SMKNJNUI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17391&json=true","fetch_graph":"https://pith.science/api/pith-number/SMKNJNUIVN5VFEOQRUJODVV6F4/graph.json","fetch_events":"https://pith.science/api/pith-number/SMKNJNUIVN5VFEOQRUJODVV6F4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMKNJNUIVN5VFEOQRUJODVV6F4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMKNJNUIVN5VFEOQRUJODVV6F4/action/storage_attestation","attest_author":"https://pith.science/pith/SMKNJNUIVN5VFEOQRUJODVV6F4/action/author_attestation","sign_citation":"https://pith.science/pith/SMKNJNUIVN5VFEOQRUJODVV6F4/action/citation_signature","submit_replication":"https://pith.science/pith/SMKNJNUIVN5VFEOQRUJODVV6F4/action/replication_record"}},"created_at":"2026-06-19T16:10:11.026094+00:00","updated_at":"2026-06-19T16:10:11.026094+00:00"}