{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7MEC6ORRAL3UPOOF6TXKV25O3A","short_pith_number":"pith:7MEC6ORR","canonical_record":{"source":{"id":"2505.12601","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T01:33:41Z","cross_cats_sorted":[],"title_canon_sha256":"6c047cb9b072a3a1efd4906025fc1b1239d8824ecceef99988e056c0cec4f147","abstract_canon_sha256":"44a556e2e7bed6f08641af9fa12b014001b1f187afd10ca52d05f15f475e718f"},"schema_version":"1.0"},"canonical_sha256":"fb082f3a3102f747b9c5f4eeaaebaed83fe3fb3b975cfdfe98ce8d0d723c2738","source":{"kind":"arxiv","id":"2505.12601","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12601","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12601v2","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12601","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"pith_short_12","alias_value":"7MEC6ORRAL3U","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"pith_short_16","alias_value":"7MEC6ORRAL3UPOOF","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"pith_short_8","alias_value":"7MEC6ORR","created_at":"2026-05-20T00:00:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7MEC6ORRAL3UPOOF6TXKV25O3A","target":"record","payload":{"canonical_record":{"source":{"id":"2505.12601","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T01:33:41Z","cross_cats_sorted":[],"title_canon_sha256":"6c047cb9b072a3a1efd4906025fc1b1239d8824ecceef99988e056c0cec4f147","abstract_canon_sha256":"44a556e2e7bed6f08641af9fa12b014001b1f187afd10ca52d05f15f475e718f"},"schema_version":"1.0"},"canonical_sha256":"fb082f3a3102f747b9c5f4eeaaebaed83fe3fb3b975cfdfe98ce8d0d723c2738","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:19.918602Z","signature_b64":"8Rt064not9E9c0YM3XzmvjD0IomS8geTQBaBwQeK02xCJRfb4TaMpABD7NS/mgTohlpA12b4KoMTKt150SGBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb082f3a3102f747b9c5f4eeaaebaed83fe3fb3b975cfdfe98ce8d0d723c2738","last_reissued_at":"2026-05-20T00:00:19.917989Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:19.917989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.12601","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qG+E1fhKnkLJhE8eL3RUU3fS8whm1+Clzj1hOOX6oNx2kO62yq111K0AVYR+O2WZtpYp5DRTFNDwnNbQ1nYqCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T11:42:04.016195Z"},"content_sha256":"75d0f011f0334f8f27b67760cfcc4095e736606772a5fd3cf4f8da33d6e94812","schema_version":"1.0","event_id":"sha256:75d0f011f0334f8f27b67760cfcc4095e736606772a5fd3cf4f8da33d6e94812"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7MEC6ORRAL3UPOOF6TXKV25O3A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yang Li","submitted_at":"2025-05-19T01:33:41Z","abstract_excerpt":"As large language models (LLMs) grow in scale and specialization, routing--selecting the best model for a given input--has become essential for efficient and effective deployment. While recent methods rely on complex learned routing strategies, their dependence on disparate training data and evaluation setups makes comparison and generalization difficult. In this work, we revisit LLM routing through the lens of simplicity. We show that a well-tuned k-Nearest Neighbors (kNN) approach not only matches but often outperforms state-of-the-art learned routers across diverse tasks. To support systema"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12601","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/2505.12601/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":"2026-05-20T00:00:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BrthCN8W1QPCxxfskfPKADlx5N161ZLpYUGbT16Uy+7fpqzxIAOZnInuPjJbdMw6EW4n0tUcGHHdz4aMTVWoBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T11:42:04.016896Z"},"content_sha256":"df33e106d29fd27a0bd9c7b56321e60a4a3bb89a2259782814c2dd8be785259c","schema_version":"1.0","event_id":"sha256:df33e106d29fd27a0bd9c7b56321e60a4a3bb89a2259782814c2dd8be785259c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7MEC6ORRAL3UPOOF6TXKV25O3A/bundle.json","state_url":"https://pith.science/pith/7MEC6ORRAL3UPOOF6TXKV25O3A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7MEC6ORRAL3UPOOF6TXKV25O3A/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":"2026-05-25T11:42:04Z","links":{"resolver":"https://pith.science/pith/7MEC6ORRAL3UPOOF6TXKV25O3A","bundle":"https://pith.science/pith/7MEC6ORRAL3UPOOF6TXKV25O3A/bundle.json","state":"https://pith.science/pith/7MEC6ORRAL3UPOOF6TXKV25O3A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7MEC6ORRAL3UPOOF6TXKV25O3A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7MEC6ORRAL3UPOOF6TXKV25O3A","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":"44a556e2e7bed6f08641af9fa12b014001b1f187afd10ca52d05f15f475e718f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T01:33:41Z","title_canon_sha256":"6c047cb9b072a3a1efd4906025fc1b1239d8824ecceef99988e056c0cec4f147"},"schema_version":"1.0","source":{"id":"2505.12601","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12601","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12601v2","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12601","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"pith_short_12","alias_value":"7MEC6ORRAL3U","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"pith_short_16","alias_value":"7MEC6ORRAL3UPOOF","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"pith_short_8","alias_value":"7MEC6ORR","created_at":"2026-05-20T00:00:19Z"}],"graph_snapshots":[{"event_id":"sha256:df33e106d29fd27a0bd9c7b56321e60a4a3bb89a2259782814c2dd8be785259c","target":"graph","created_at":"2026-05-20T00:00:19Z","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/2505.12601/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) grow in scale and specialization, routing--selecting the best model for a given input--has become essential for efficient and effective deployment. While recent methods rely on complex learned routing strategies, their dependence on disparate training data and evaluation setups makes comparison and generalization difficult. In this work, we revisit LLM routing through the lens of simplicity. We show that a well-tuned k-Nearest Neighbors (kNN) approach not only matches but often outperforms state-of-the-art learned routers across diverse tasks. To support systema","authors_text":"Yang Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T01:33:41Z","title":"Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12601","kind":"arxiv","version":2},"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":"sha256:75d0f011f0334f8f27b67760cfcc4095e736606772a5fd3cf4f8da33d6e94812","target":"record","created_at":"2026-05-20T00:00:19Z","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":"44a556e2e7bed6f08641af9fa12b014001b1f187afd10ca52d05f15f475e718f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T01:33:41Z","title_canon_sha256":"6c047cb9b072a3a1efd4906025fc1b1239d8824ecceef99988e056c0cec4f147"},"schema_version":"1.0","source":{"id":"2505.12601","kind":"arxiv","version":2}},"canonical_sha256":"fb082f3a3102f747b9c5f4eeaaebaed83fe3fb3b975cfdfe98ce8d0d723c2738","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb082f3a3102f747b9c5f4eeaaebaed83fe3fb3b975cfdfe98ce8d0d723c2738","first_computed_at":"2026-05-20T00:00:19.917989Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:19.917989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Rt064not9E9c0YM3XzmvjD0IomS8geTQBaBwQeK02xCJRfb4TaMpABD7NS/mgTohlpA12b4KoMTKt150SGBBQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:19.918602Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12601","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75d0f011f0334f8f27b67760cfcc4095e736606772a5fd3cf4f8da33d6e94812","sha256:df33e106d29fd27a0bd9c7b56321e60a4a3bb89a2259782814c2dd8be785259c"],"state_sha256":"6666f445285b7b9eda65db32247193d79afba12cb525db0ee9a1e695a72360e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n7ZMYZMTfCi//BRILrFoGsNH94t2xSxj3ly2k20nwnRn40hnFkkg/0wz6JGq3TizeAd7E77MOiJz/AAL1Pt2Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T11:42:04.020371Z","bundle_sha256":"23f348fa127994359e08e759948d468264e153a603484e346c4bfe79d227717c"}}