{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2AIMFV52EYF2ZPEXJIFXOFBRG7","short_pith_number":"pith:2AIMFV52","schema_version":"1.0","canonical_sha256":"d010c2d7ba260bacbc974a0b77143137f504a0a2f34e660884fee8e9a8f8a196","source":{"kind":"arxiv","id":"2607.20470","version":1},"attestation_state":"computed","paper":{"title":"PlanE: Meta Planning of Data, Tuning, and Inference for Extractive-based LLMs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guangya Yu, Jiacheng Wang, Weiyan Zhang","submitted_at":"2026-05-22T13:37:33Z","abstract_excerpt":"Enhancing the task-specific capabilities of Large Language Models (LLMs) primarily requires substantial instruction-tuning datasets. However, the sheer volume of such data imposes a considerable annotation cost, and a lack of optimization methods for tailoring LLMs to specific tasks. To address the above issues, we propose a \\textbf{Plan}ning framework for constructing \\textbf{E}xtractive-based LLMs called \\textbf{PlanE}, which includes data decomposition, instruction tuning, and prompt inference. Additionally, we introduce a Data-Tuning-Inference (DTI) planner, aimed at selecting the optimal "},"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":"2607.20470","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-22T13:37:33Z","cross_cats_sorted":[],"title_canon_sha256":"35c9b2a42d584f070bf24f18159389d02db8a656921b9751309c439b5ffee0ed","abstract_canon_sha256":"9a595c1b97c6c03cd49f2b129bfde807a4b144a4c6c4a8240ded46c739811a63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T00:23:17.461683Z","signature_b64":"xtSdVeoPUy5E5I4QEfw2X0em4bNm5vD0Ia286pjzW59s7elUIlouTrt1LnAO+d2rj9zV+BISNTQP6E0UqNs3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d010c2d7ba260bacbc974a0b77143137f504a0a2f34e660884fee8e9a8f8a196","last_reissued_at":"2026-07-24T00:23:17.460773Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T00:23:17.460773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PlanE: Meta Planning of Data, Tuning, and Inference for Extractive-based LLMs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guangya Yu, Jiacheng Wang, Weiyan Zhang","submitted_at":"2026-05-22T13:37:33Z","abstract_excerpt":"Enhancing the task-specific capabilities of Large Language Models (LLMs) primarily requires substantial instruction-tuning datasets. However, the sheer volume of such data imposes a considerable annotation cost, and a lack of optimization methods for tailoring LLMs to specific tasks. To address the above issues, we propose a \\textbf{Plan}ning framework for constructing \\textbf{E}xtractive-based LLMs called \\textbf{PlanE}, which includes data decomposition, instruction tuning, and prompt inference. Additionally, we introduce a Data-Tuning-Inference (DTI) planner, aimed at selecting the optimal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20470","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/2607.20470/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":"2607.20470","created_at":"2026-07-24T00:23:17.461241+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.20470v1","created_at":"2026-07-24T00:23:17.461241+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20470","created_at":"2026-07-24T00:23:17.461241+00:00"},{"alias_kind":"pith_short_12","alias_value":"2AIMFV52EYF2","created_at":"2026-07-24T00:23:17.461241+00:00"},{"alias_kind":"pith_short_16","alias_value":"2AIMFV52EYF2ZPEX","created_at":"2026-07-24T00:23:17.461241+00:00"},{"alias_kind":"pith_short_8","alias_value":"2AIMFV52","created_at":"2026-07-24T00:23:17.461241+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/2AIMFV52EYF2ZPEXJIFXOFBRG7","json":"https://pith.science/pith/2AIMFV52EYF2ZPEXJIFXOFBRG7.json","graph_json":"https://pith.science/api/pith-number/2AIMFV52EYF2ZPEXJIFXOFBRG7/graph.json","events_json":"https://pith.science/api/pith-number/2AIMFV52EYF2ZPEXJIFXOFBRG7/events.json","paper":"https://pith.science/paper/2AIMFV52"},"agent_actions":{"view_html":"https://pith.science/pith/2AIMFV52EYF2ZPEXJIFXOFBRG7","download_json":"https://pith.science/pith/2AIMFV52EYF2ZPEXJIFXOFBRG7.json","view_paper":"https://pith.science/paper/2AIMFV52","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.20470&json=true","fetch_graph":"https://pith.science/api/pith-number/2AIMFV52EYF2ZPEXJIFXOFBRG7/graph.json","fetch_events":"https://pith.science/api/pith-number/2AIMFV52EYF2ZPEXJIFXOFBRG7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2AIMFV52EYF2ZPEXJIFXOFBRG7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2AIMFV52EYF2ZPEXJIFXOFBRG7/action/storage_attestation","attest_author":"https://pith.science/pith/2AIMFV52EYF2ZPEXJIFXOFBRG7/action/author_attestation","sign_citation":"https://pith.science/pith/2AIMFV52EYF2ZPEXJIFXOFBRG7/action/citation_signature","submit_replication":"https://pith.science/pith/2AIMFV52EYF2ZPEXJIFXOFBRG7/action/replication_record"}},"created_at":"2026-07-24T00:23:17.461241+00:00","updated_at":"2026-07-24T00:23:17.461241+00:00"}