{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:S56JHCNMHDC74P7Q4CMETDQMHK","short_pith_number":"pith:S56JHCNM","canonical_record":{"source":{"id":"2605.25558","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-25T08:12:58Z","cross_cats_sorted":[],"title_canon_sha256":"be26a19a7bf096cd4c8339dee4c7f0c036ebf20257c0ec838ca40df0c9f7dd29","abstract_canon_sha256":"d4bb8fc2cc09aacf8a9b6b2fc79766933baf17ffee4a7834b18bb52313811b88"},"schema_version":"1.0"},"canonical_sha256":"977c9389ac38c5fe3ff0e098498e0c3abe1d7e1bd91b05590659b0ab19db3aab","source":{"kind":"arxiv","id":"2605.25558","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25558","created_at":"2026-05-26T02:04:42Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25558v1","created_at":"2026-05-26T02:04:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25558","created_at":"2026-05-26T02:04:42Z"},{"alias_kind":"pith_short_12","alias_value":"S56JHCNMHDC7","created_at":"2026-05-26T02:04:42Z"},{"alias_kind":"pith_short_16","alias_value":"S56JHCNMHDC74P7Q","created_at":"2026-05-26T02:04:42Z"},{"alias_kind":"pith_short_8","alias_value":"S56JHCNM","created_at":"2026-05-26T02:04:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:S56JHCNMHDC74P7Q4CMETDQMHK","target":"record","payload":{"canonical_record":{"source":{"id":"2605.25558","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-25T08:12:58Z","cross_cats_sorted":[],"title_canon_sha256":"be26a19a7bf096cd4c8339dee4c7f0c036ebf20257c0ec838ca40df0c9f7dd29","abstract_canon_sha256":"d4bb8fc2cc09aacf8a9b6b2fc79766933baf17ffee4a7834b18bb52313811b88"},"schema_version":"1.0"},"canonical_sha256":"977c9389ac38c5fe3ff0e098498e0c3abe1d7e1bd91b05590659b0ab19db3aab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:42.951219Z","signature_b64":"wfZiC8ee8kPUbIqKUfetBGQ+mVid24TJTgwpW6SkEQsxIE8cYri5aurxUkrRHDHXGCVtPWUpoTiuZdP8vgbwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"977c9389ac38c5fe3ff0e098498e0c3abe1d7e1bd91b05590659b0ab19db3aab","last_reissued_at":"2026-05-26T02:04:42.950584Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:42.950584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.25558","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:04:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hk98i7T4PCBiI1HC8kgJh9tnt5Uj7X0dhcvihicQHZQ35vwsPHP5f6E0jRoGupTTGf/UsZFu7uPlrsKnDG8LBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T05:08:36.109828Z"},"content_sha256":"ccc927374c11b90d721b716a4a97813574ef8630fa239474908b63feed3f906b","schema_version":"1.0","event_id":"sha256:ccc927374c11b90d721b716a4a97813574ef8630fa239474908b63feed3f906b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:S56JHCNMHDC74P7Q4CMETDQMHK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Query Memorization: Large Language Model Routing with Query Decomposition and Historical Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Lv, Jingbo Sun","submitted_at":"2026-05-25T08:12:58Z","abstract_excerpt":"Optimizing the trade-off among predictive performance and computational cost is a central focus in the deployment of Large Language Models (LLMs). Current routing methods primarily rely on direct mapping from queries to models based on surface-level features, making them susceptible to the memorization trap and leading to poor generalizability on out-of-distribution (OOD) data. In this paper, we propose DecoR, a novel routing framework that recasts the routing task as a matching process of sifting similar queries from historical logs, effectively mitigating the memorization trap. To enhance ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25558","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/2605.25558/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:04:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1OUb9zxhlCIcSEks+SLfbQdbZLVzlD5D1zxBTOXRPZ+R7EeNMTL3GSCYX5EX3Kn/zCqeflPlrzAPVoMY91z2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T05:08:36.110203Z"},"content_sha256":"be47ba2e0a26f60d5978935c20a375ca1113f23c5d79be0994570e56b79e0217","schema_version":"1.0","event_id":"sha256:be47ba2e0a26f60d5978935c20a375ca1113f23c5d79be0994570e56b79e0217"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S56JHCNMHDC74P7Q4CMETDQMHK/bundle.json","state_url":"https://pith.science/pith/S56JHCNMHDC74P7Q4CMETDQMHK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S56JHCNMHDC74P7Q4CMETDQMHK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-02T05:08:36Z","links":{"resolver":"https://pith.science/pith/S56JHCNMHDC74P7Q4CMETDQMHK","bundle":"https://pith.science/pith/S56JHCNMHDC74P7Q4CMETDQMHK/bundle.json","state":"https://pith.science/pith/S56JHCNMHDC74P7Q4CMETDQMHK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S56JHCNMHDC74P7Q4CMETDQMHK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:S56JHCNMHDC74P7Q4CMETDQMHK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d4bb8fc2cc09aacf8a9b6b2fc79766933baf17ffee4a7834b18bb52313811b88","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-25T08:12:58Z","title_canon_sha256":"be26a19a7bf096cd4c8339dee4c7f0c036ebf20257c0ec838ca40df0c9f7dd29"},"schema_version":"1.0","source":{"id":"2605.25558","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25558","created_at":"2026-05-26T02:04:42Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25558v1","created_at":"2026-05-26T02:04:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25558","created_at":"2026-05-26T02:04:42Z"},{"alias_kind":"pith_short_12","alias_value":"S56JHCNMHDC7","created_at":"2026-05-26T02:04:42Z"},{"alias_kind":"pith_short_16","alias_value":"S56JHCNMHDC74P7Q","created_at":"2026-05-26T02:04:42Z"},{"alias_kind":"pith_short_8","alias_value":"S56JHCNM","created_at":"2026-05-26T02:04:42Z"}],"graph_snapshots":[{"event_id":"sha256:be47ba2e0a26f60d5978935c20a375ca1113f23c5d79be0994570e56b79e0217","target":"graph","created_at":"2026-05-26T02:04:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.25558/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimizing the trade-off among predictive performance and computational cost is a central focus in the deployment of Large Language Models (LLMs). Current routing methods primarily rely on direct mapping from queries to models based on surface-level features, making them susceptible to the memorization trap and leading to poor generalizability on out-of-distribution (OOD) data. In this paper, we propose DecoR, a novel routing framework that recasts the routing task as a matching process of sifting similar queries from historical logs, effectively mitigating the memorization trap. To enhance ma","authors_text":"Bo Lv, Jingbo Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-25T08:12:58Z","title":"Beyond Query Memorization: Large Language Model Routing with Query Decomposition and Historical Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25558","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ccc927374c11b90d721b716a4a97813574ef8630fa239474908b63feed3f906b","target":"record","created_at":"2026-05-26T02:04:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d4bb8fc2cc09aacf8a9b6b2fc79766933baf17ffee4a7834b18bb52313811b88","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-25T08:12:58Z","title_canon_sha256":"be26a19a7bf096cd4c8339dee4c7f0c036ebf20257c0ec838ca40df0c9f7dd29"},"schema_version":"1.0","source":{"id":"2605.25558","kind":"arxiv","version":1}},"canonical_sha256":"977c9389ac38c5fe3ff0e098498e0c3abe1d7e1bd91b05590659b0ab19db3aab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"977c9389ac38c5fe3ff0e098498e0c3abe1d7e1bd91b05590659b0ab19db3aab","first_computed_at":"2026-05-26T02:04:42.950584Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:42.950584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wfZiC8ee8kPUbIqKUfetBGQ+mVid24TJTgwpW6SkEQsxIE8cYri5aurxUkrRHDHXGCVtPWUpoTiuZdP8vgbwAA==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:42.951219Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25558","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccc927374c11b90d721b716a4a97813574ef8630fa239474908b63feed3f906b","sha256:be47ba2e0a26f60d5978935c20a375ca1113f23c5d79be0994570e56b79e0217"],"state_sha256":"8ad73afc93f68bef323bef7f5fc354e3047d6e9e2b0b7d99c43ed1344d7a03f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"usMaF07ZpywocXVebyiCZHuEs6/R7pI3iUqv+lIwCui7lEnsWf395UQuavwKM2TB8GD6rNCMTTFoXSYDFoZ/Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T05:08:36.112226Z","bundle_sha256":"f6a697625e0e07cb3a4e528a0e980dccd8d28671fa18471d62df9a87dbef156f"}}