{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZS7EFEVSQHBTKPYJL7PKA4OERC","short_pith_number":"pith:ZS7EFEVS","schema_version":"1.0","canonical_sha256":"ccbe4292b281c3353f095fdea071c48892ae5f6d9c27cdf21ad5d818dc975432","source":{"kind":"arxiv","id":"2605.15721","version":1},"attestation_state":"computed","paper":{"title":"Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Congmin Zheng, Jiachen Zhu, Jianghao Lin, Lingyu Yang, Lionel Z. Wang, Rong Shan, Weinan Zhang, Weiwen Liu, Yong Yu, Yuxiang Chen, Zeyu Zheng, Zhuoying Ou","submitted_at":"2026-05-15T08:17:21Z","abstract_excerpt":"Large Language Models (LLMs) are highly sensitive to their input contexts, motivating the development of automated context engineering. However, existing methods predominantly treat this as a global search problem, seeking a single context strategy that maximizes average performance across a dataset. This restrictive assumption overlooks the fact that different inputs often require distinct guidance, leaving substantial instance-level performance gains untapped. In this paper, we propose a paradigm shift by formulating context engineering as a recommendation problem. We introduce \\textbf{Neura"},"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":"2605.15721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-15T08:17:21Z","cross_cats_sorted":[],"title_canon_sha256":"26ce36b7e4d72e039ce05c5fa91683ebf3365ced5e1ca9e5d1605ff8eaaf880f","abstract_canon_sha256":"f101ca9c28bbf1654c7ca2d57b9aa8e81838538182467197cce085fbbb9bf9d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:14.697133Z","signature_b64":"ZxIDEVBak8f+iHFstfpF4WeBD5YaBvSGuhuIqkxYBbCXRjnN/MgCrL48QZA5OmumaVAXuRxGsk5VKwtdchpgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccbe4292b281c3353f095fdea071c48892ae5f6d9c27cdf21ad5d818dc975432","last_reissued_at":"2026-05-20T00:01:14.696543Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:14.696543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Congmin Zheng, Jiachen Zhu, Jianghao Lin, Lingyu Yang, Lionel Z. Wang, Rong Shan, Weinan Zhang, Weiwen Liu, Yong Yu, Yuxiang Chen, Zeyu Zheng, Zhuoying Ou","submitted_at":"2026-05-15T08:17:21Z","abstract_excerpt":"Large Language Models (LLMs) are highly sensitive to their input contexts, motivating the development of automated context engineering. However, existing methods predominantly treat this as a global search problem, seeking a single context strategy that maximizes average performance across a dataset. This restrictive assumption overlooks the fact that different inputs often require distinct guidance, leaving substantial instance-level performance gains untapped. In this paper, we propose a paradigm shift by formulating context engineering as a recommendation problem. We introduce \\textbf{Neura"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15721","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/2605.15721/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:25.155209Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:21:56.006481Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"0809ccba1ef9c66d89b2623c8c4bb19972d3d55b1086a5863dd1a0a524cf6f81"},"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":"2605.15721","created_at":"2026-05-20T00:01:14.696647+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15721v1","created_at":"2026-05-20T00:01:14.696647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15721","created_at":"2026-05-20T00:01:14.696647+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZS7EFEVSQHBT","created_at":"2026-05-20T00:01:14.696647+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZS7EFEVSQHBTKPYJ","created_at":"2026-05-20T00:01:14.696647+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZS7EFEVS","created_at":"2026-05-20T00:01:14.696647+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/ZS7EFEVSQHBTKPYJL7PKA4OERC","json":"https://pith.science/pith/ZS7EFEVSQHBTKPYJL7PKA4OERC.json","graph_json":"https://pith.science/api/pith-number/ZS7EFEVSQHBTKPYJL7PKA4OERC/graph.json","events_json":"https://pith.science/api/pith-number/ZS7EFEVSQHBTKPYJL7PKA4OERC/events.json","paper":"https://pith.science/paper/ZS7EFEVS"},"agent_actions":{"view_html":"https://pith.science/pith/ZS7EFEVSQHBTKPYJL7PKA4OERC","download_json":"https://pith.science/pith/ZS7EFEVSQHBTKPYJL7PKA4OERC.json","view_paper":"https://pith.science/paper/ZS7EFEVS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15721&json=true","fetch_graph":"https://pith.science/api/pith-number/ZS7EFEVSQHBTKPYJL7PKA4OERC/graph.json","fetch_events":"https://pith.science/api/pith-number/ZS7EFEVSQHBTKPYJL7PKA4OERC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZS7EFEVSQHBTKPYJL7PKA4OERC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZS7EFEVSQHBTKPYJL7PKA4OERC/action/storage_attestation","attest_author":"https://pith.science/pith/ZS7EFEVSQHBTKPYJL7PKA4OERC/action/author_attestation","sign_citation":"https://pith.science/pith/ZS7EFEVSQHBTKPYJL7PKA4OERC/action/citation_signature","submit_replication":"https://pith.science/pith/ZS7EFEVSQHBTKPYJL7PKA4OERC/action/replication_record"}},"created_at":"2026-05-20T00:01:14.696647+00:00","updated_at":"2026-05-20T00:01:14.696647+00:00"}