{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LNNED3KWEHEWUIEOMVE7IK33O2","short_pith_number":"pith:LNNED3KW","schema_version":"1.0","canonical_sha256":"5b5a41ed5621c96a208e6549f42b7b7684c1ee30f30ea1c182e8c1d61487814e","source":{"kind":"arxiv","id":"2506.18036","version":1},"attestation_state":"computed","paper":{"title":"Markov-Enhanced Clustering for Long Document Summarization: Tackling the 'Lost in the Middle' Challenge with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aziz Amari (1), Mohamed Achref Ben Ammar (1) ((1) National Institute of Applied Science, Technology (INSAT), Tunis, Tunisia), University of Carthage","submitted_at":"2025-06-22T13:34:58Z","abstract_excerpt":"The rapid expansion of information from diverse sources has heightened the need for effective automatic text summarization, which condenses documents into shorter, coherent texts. Summarization methods generally fall into two categories: extractive, which selects key segments from the original text, and abstractive, which generates summaries by rephrasing the content coherently. Large language models have advanced the field of abstractive summarization, but they are resourceintensive and face significant challenges in retaining key information across lengthy documents, which we call being \"los"},"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":"2506.18036","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-22T13:34:58Z","cross_cats_sorted":[],"title_canon_sha256":"cfc1faba359906392a7c3859f30b0515f7b905d3c5a513d39d52275790ebbe8e","abstract_canon_sha256":"0c81aca43f6474fede852c7ba4e18cb661bf12e651e2babe93b4dcaf7cdfef4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:27.499645Z","signature_b64":"0f91kc/2fUYLyFwz5x1E8wSHcStBDbq6iSWE0h0xIT1329gaNWYPFJH/3PGZa6Ej3lTysXrGbpBP4417L9UVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b5a41ed5621c96a208e6549f42b7b7684c1ee30f30ea1c182e8c1d61487814e","last_reissued_at":"2026-07-05T11:25:27.499114Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:27.499114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Markov-Enhanced Clustering for Long Document Summarization: Tackling the 'Lost in the Middle' Challenge with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aziz Amari (1), Mohamed Achref Ben Ammar (1) ((1) National Institute of Applied Science, Technology (INSAT), Tunis, Tunisia), University of Carthage","submitted_at":"2025-06-22T13:34:58Z","abstract_excerpt":"The rapid expansion of information from diverse sources has heightened the need for effective automatic text summarization, which condenses documents into shorter, coherent texts. Summarization methods generally fall into two categories: extractive, which selects key segments from the original text, and abstractive, which generates summaries by rephrasing the content coherently. Large language models have advanced the field of abstractive summarization, but they are resourceintensive and face significant challenges in retaining key information across lengthy documents, which we call being \"los"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18036","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/2506.18036/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":"2506.18036","created_at":"2026-07-05T11:25:27.499175+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.18036v1","created_at":"2026-07-05T11:25:27.499175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18036","created_at":"2026-07-05T11:25:27.499175+00:00"},{"alias_kind":"pith_short_12","alias_value":"LNNED3KWEHEW","created_at":"2026-07-05T11:25:27.499175+00:00"},{"alias_kind":"pith_short_16","alias_value":"LNNED3KWEHEWUIEO","created_at":"2026-07-05T11:25:27.499175+00:00"},{"alias_kind":"pith_short_8","alias_value":"LNNED3KW","created_at":"2026-07-05T11:25:27.499175+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03166","citing_title":"Adversarial Stress Testing of Role-Playing Language Agents using Multi-Agent Evaluation","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LNNED3KWEHEWUIEOMVE7IK33O2","json":"https://pith.science/pith/LNNED3KWEHEWUIEOMVE7IK33O2.json","graph_json":"https://pith.science/api/pith-number/LNNED3KWEHEWUIEOMVE7IK33O2/graph.json","events_json":"https://pith.science/api/pith-number/LNNED3KWEHEWUIEOMVE7IK33O2/events.json","paper":"https://pith.science/paper/LNNED3KW"},"agent_actions":{"view_html":"https://pith.science/pith/LNNED3KWEHEWUIEOMVE7IK33O2","download_json":"https://pith.science/pith/LNNED3KWEHEWUIEOMVE7IK33O2.json","view_paper":"https://pith.science/paper/LNNED3KW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.18036&json=true","fetch_graph":"https://pith.science/api/pith-number/LNNED3KWEHEWUIEOMVE7IK33O2/graph.json","fetch_events":"https://pith.science/api/pith-number/LNNED3KWEHEWUIEOMVE7IK33O2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LNNED3KWEHEWUIEOMVE7IK33O2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LNNED3KWEHEWUIEOMVE7IK33O2/action/storage_attestation","attest_author":"https://pith.science/pith/LNNED3KWEHEWUIEOMVE7IK33O2/action/author_attestation","sign_citation":"https://pith.science/pith/LNNED3KWEHEWUIEOMVE7IK33O2/action/citation_signature","submit_replication":"https://pith.science/pith/LNNED3KWEHEWUIEOMVE7IK33O2/action/replication_record"}},"created_at":"2026-07-05T11:25:27.499175+00:00","updated_at":"2026-07-05T11:25:27.499175+00:00"}