{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OW5TAHMU4457ZOFHR2EE4KBENO","short_pith_number":"pith:OW5TAHMU","schema_version":"1.0","canonical_sha256":"75bb301d94e73bfcb8a78e884e28246ba01101b5b94645d60fe4719cc8b3fff4","source":{"kind":"arxiv","id":"2505.12572","version":2},"attestation_state":"computed","paper":{"title":"Measuring Information Distortion in Hierarchical Ultra long Novel Reconstruction:The Optimal Expansion Ratio","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.CL","authors_text":"Hanwen Shen, Ting Ying","submitted_at":"2025-05-18T23:20:01Z","abstract_excerpt":"A two stage novel generation framework (outline -> section outline -> manuscript) is widely used in long novel generation,(e.g., \\textsc{DOME}, \\textsc{Plan\\&Write}, \\textsc{Long Writer}), but study of such framework in ultra long novel(>1M words) reconstruction is little. Building on recent text compression methods (\\textsc{LLMZip}, \\textsc{LLM2Vec}), we conduct an information-theoretic analysis to quantify semantic distortion under different compression-expansion ratios. We examine how outline length affects information preservation. Experiments on ultra-long novels show that the optimal com"},"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":"2505.12572","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T23:20:01Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"4ca8380aefd1c8c277fda2c79b4b739bf7062517a94a2ac05ab966a65c7dc273","abstract_canon_sha256":"953131b7eebfe34fbb38a7a08fccc5aa6ef6a42cc9df515fc2f86a0c7415257e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:05.810704Z","signature_b64":"ChutaKVRj8mCmfwWwOr4sbEct5vgmAwQPpOnW81zI8xafGhIM0CH2tgY9NNztDRoV3Zt4OP5fkTwdPxicWEiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75bb301d94e73bfcb8a78e884e28246ba01101b5b94645d60fe4719cc8b3fff4","last_reissued_at":"2026-07-05T11:44:05.810231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:05.810231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring Information Distortion in Hierarchical Ultra long Novel Reconstruction:The Optimal Expansion Ratio","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.CL","authors_text":"Hanwen Shen, Ting Ying","submitted_at":"2025-05-18T23:20:01Z","abstract_excerpt":"A two stage novel generation framework (outline -> section outline -> manuscript) is widely used in long novel generation,(e.g., \\textsc{DOME}, \\textsc{Plan\\&Write}, \\textsc{Long Writer}), but study of such framework in ultra long novel(>1M words) reconstruction is little. Building on recent text compression methods (\\textsc{LLMZip}, \\textsc{LLM2Vec}), we conduct an information-theoretic analysis to quantify semantic distortion under different compression-expansion ratios. We examine how outline length affects information preservation. Experiments on ultra-long novels show that the optimal com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12572","kind":"arxiv","version":2},"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/2505.12572/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":"2505.12572","created_at":"2026-07-05T11:44:05.810293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12572v2","created_at":"2026-07-05T11:44:05.810293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12572","created_at":"2026-07-05T11:44:05.810293+00:00"},{"alias_kind":"pith_short_12","alias_value":"OW5TAHMU4457","created_at":"2026-07-05T11:44:05.810293+00:00"},{"alias_kind":"pith_short_16","alias_value":"OW5TAHMU4457ZOFH","created_at":"2026-07-05T11:44:05.810293+00:00"},{"alias_kind":"pith_short_8","alias_value":"OW5TAHMU","created_at":"2026-07-05T11:44:05.810293+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22654","citing_title":"Seeing the Poem: Image-Semantic Detection of AI-Generated Modern Chinese Poetry with MLLMs","ref_index":123,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OW5TAHMU4457ZOFHR2EE4KBENO","json":"https://pith.science/pith/OW5TAHMU4457ZOFHR2EE4KBENO.json","graph_json":"https://pith.science/api/pith-number/OW5TAHMU4457ZOFHR2EE4KBENO/graph.json","events_json":"https://pith.science/api/pith-number/OW5TAHMU4457ZOFHR2EE4KBENO/events.json","paper":"https://pith.science/paper/OW5TAHMU"},"agent_actions":{"view_html":"https://pith.science/pith/OW5TAHMU4457ZOFHR2EE4KBENO","download_json":"https://pith.science/pith/OW5TAHMU4457ZOFHR2EE4KBENO.json","view_paper":"https://pith.science/paper/OW5TAHMU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12572&json=true","fetch_graph":"https://pith.science/api/pith-number/OW5TAHMU4457ZOFHR2EE4KBENO/graph.json","fetch_events":"https://pith.science/api/pith-number/OW5TAHMU4457ZOFHR2EE4KBENO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OW5TAHMU4457ZOFHR2EE4KBENO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OW5TAHMU4457ZOFHR2EE4KBENO/action/storage_attestation","attest_author":"https://pith.science/pith/OW5TAHMU4457ZOFHR2EE4KBENO/action/author_attestation","sign_citation":"https://pith.science/pith/OW5TAHMU4457ZOFHR2EE4KBENO/action/citation_signature","submit_replication":"https://pith.science/pith/OW5TAHMU4457ZOFHR2EE4KBENO/action/replication_record"}},"created_at":"2026-07-05T11:44:05.810293+00:00","updated_at":"2026-07-05T11:44:05.810293+00:00"}