{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EMBLEMSTHDBROQJEQXZ3MJFJK5","short_pith_number":"pith:EMBLEMST","schema_version":"1.0","canonical_sha256":"2302b2325338c317412485f3b624a9577876ac9f9913df887b578238e0e0f2fd","source":{"kind":"arxiv","id":"2505.14925","version":1},"attestation_state":"computed","paper":{"title":"Too Long, Didn't Model: Decomposing LLM Long-Context Understanding With Novels","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"David Mimno, Matthew Wilkens, Rebecca M. M. Hicke, Sil Hamilton","submitted_at":"2025-05-20T21:21:09Z","abstract_excerpt":"Although the context length of large language models (LLMs) has increased to millions of tokens, evaluating their effectiveness beyond needle-in-a-haystack approaches has proven difficult. We argue that novels provide a case study of subtle, complicated structure and long-range semantic dependencies often over 128k tokens in length. Inspired by work on computational novel analysis, we release the Too Long, Didn't Model (TLDM) benchmark, which tests a model's ability to report plot summary, storyworld configuration, and elapsed narrative time. We find that none of seven tested frontier LLMs ret"},"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":"2505.14925","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T21:21:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"236b0cc5d5fdb8d2d82bec4da5d6a307a3066faa08848617973ea68eb074a908","abstract_canon_sha256":"6e85f8eb444e339a0c88ed66819dda7ff28273844f8aef9f2a178a46ede186da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:37.645249Z","signature_b64":"i/AtRTGY2688P9xfVPGLtjLDxM5ax82X92utK9NJSLEtMlA2+BLXeRr1sKW71fTWFcsXfzTrFH0Lf1eEXtx9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2302b2325338c317412485f3b624a9577876ac9f9913df887b578238e0e0f2fd","last_reissued_at":"2026-07-05T11:06:37.644744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:37.644744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Too Long, Didn't Model: Decomposing LLM Long-Context Understanding With Novels","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"David Mimno, Matthew Wilkens, Rebecca M. M. Hicke, Sil Hamilton","submitted_at":"2025-05-20T21:21:09Z","abstract_excerpt":"Although the context length of large language models (LLMs) has increased to millions of tokens, evaluating their effectiveness beyond needle-in-a-haystack approaches has proven difficult. We argue that novels provide a case study of subtle, complicated structure and long-range semantic dependencies often over 128k tokens in length. Inspired by work on computational novel analysis, we release the Too Long, Didn't Model (TLDM) benchmark, which tests a model's ability to report plot summary, storyworld configuration, and elapsed narrative time. We find that none of seven tested frontier LLMs ret"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14925","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/2505.14925/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":"2505.14925","created_at":"2026-07-05T11:06:37.644804+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14925v1","created_at":"2026-07-05T11:06:37.644804+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14925","created_at":"2026-07-05T11:06:37.644804+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMBLEMSTHDBR","created_at":"2026-07-05T11:06:37.644804+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMBLEMSTHDBROQJE","created_at":"2026-07-05T11:06:37.644804+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMBLEMST","created_at":"2026-07-05T11:06:37.644804+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.13841","citing_title":"The Challenge and Reward of Fair Play in Narrative: A Computational Approach","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27600","citing_title":"Purifying Multimodal Retrieval: Fragment-Level Evidence Selection for RAG","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMBLEMSTHDBROQJEQXZ3MJFJK5","json":"https://pith.science/pith/EMBLEMSTHDBROQJEQXZ3MJFJK5.json","graph_json":"https://pith.science/api/pith-number/EMBLEMSTHDBROQJEQXZ3MJFJK5/graph.json","events_json":"https://pith.science/api/pith-number/EMBLEMSTHDBROQJEQXZ3MJFJK5/events.json","paper":"https://pith.science/paper/EMBLEMST"},"agent_actions":{"view_html":"https://pith.science/pith/EMBLEMSTHDBROQJEQXZ3MJFJK5","download_json":"https://pith.science/pith/EMBLEMSTHDBROQJEQXZ3MJFJK5.json","view_paper":"https://pith.science/paper/EMBLEMST","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14925&json=true","fetch_graph":"https://pith.science/api/pith-number/EMBLEMSTHDBROQJEQXZ3MJFJK5/graph.json","fetch_events":"https://pith.science/api/pith-number/EMBLEMSTHDBROQJEQXZ3MJFJK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMBLEMSTHDBROQJEQXZ3MJFJK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMBLEMSTHDBROQJEQXZ3MJFJK5/action/storage_attestation","attest_author":"https://pith.science/pith/EMBLEMSTHDBROQJEQXZ3MJFJK5/action/author_attestation","sign_citation":"https://pith.science/pith/EMBLEMSTHDBROQJEQXZ3MJFJK5/action/citation_signature","submit_replication":"https://pith.science/pith/EMBLEMSTHDBROQJEQXZ3MJFJK5/action/replication_record"}},"created_at":"2026-07-05T11:06:37.644804+00:00","updated_at":"2026-07-05T11:06:37.644804+00:00"}