{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IWBAFUTYAOVQLTIQXI45DUTKRI","short_pith_number":"pith:IWBAFUTY","canonical_record":{"source":{"id":"2605.29310","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T03:42:24Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b1478a3656237dcef7e2eebf02abc394599beb19f010550aab746df531e6c976","abstract_canon_sha256":"2ab02a9968cac80752d31ea01e90bed81fcf97b8fefd1e8f6441b04c260b0561"},"schema_version":"1.0"},"canonical_sha256":"458202d27803ab05cd10ba39d1d26a8a06f8d1abc470237e7d80f36011880cc0","source":{"kind":"arxiv","id":"2605.29310","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29310","created_at":"2026-05-29T01:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29310v1","created_at":"2026-05-29T01:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29310","created_at":"2026-05-29T01:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"IWBAFUTYAOVQ","created_at":"2026-05-29T01:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"IWBAFUTYAOVQLTIQ","created_at":"2026-05-29T01:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"IWBAFUTY","created_at":"2026-05-29T01:05:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IWBAFUTYAOVQLTIQXI45DUTKRI","target":"record","payload":{"canonical_record":{"source":{"id":"2605.29310","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T03:42:24Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b1478a3656237dcef7e2eebf02abc394599beb19f010550aab746df531e6c976","abstract_canon_sha256":"2ab02a9968cac80752d31ea01e90bed81fcf97b8fefd1e8f6441b04c260b0561"},"schema_version":"1.0"},"canonical_sha256":"458202d27803ab05cd10ba39d1d26a8a06f8d1abc470237e7d80f36011880cc0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:31.975290Z","signature_b64":"yLrcnRnt+ls1bMlTSWwsRrh7sLRa2AKkTmB66LyGXqWe612J7wzUENwVG325PGC+sA8Jc9Q396kiJEGQecz0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"458202d27803ab05cd10ba39d1d26a8a06f8d1abc470237e7d80f36011880cc0","last_reissued_at":"2026-05-29T01:05:31.974559Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:31.974559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.29310","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":"2026-05-29T01:05:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"83ayQchThVM86ZWGgU9kLrjxxL4YsekHQ26iVkiNHb7Z3Eou/eiD2wgz/NchzOvGwZEF7UGLSOfwxl3Z+DgoAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T00:03:52.643770Z"},"content_sha256":"1d7fd0dea980814ae39aa32f7f0a8d3cb72cef6e5619114032880950ed89ea30","schema_version":"1.0","event_id":"sha256:1d7fd0dea980814ae39aa32f7f0a8d3cb72cef6e5619114032880950ed89ea30"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IWBAFUTYAOVQLTIQXI45DUTKRI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rubric-Guided Process Reward for Stepwise Model Routing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jian Yang, Shenghao Ye, Shuangwu Chen, Yu Guo, Zhengheng Li","submitted_at":"2026-05-28T03:42:24Z","abstract_excerpt":"Stepwise model routing improves the efficiency of Large Reasoning Models (LRMs) by assigning each reasoning step to a suitable model. Recent methods formulate routing as a sequential decision process and train the router with reinforcement learning. However, although they model routing as a process, they still supervise the router with outcome rewards. Such rewards only reflect final answer correctness and fail to evaluate intermediate routing decisions, which can weaken performance and generalization. To address this gap, we propose RoRo, a rubric-guided process reward framework for stepwise "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29310","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/2605.29310/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":"2026-05-29T01:05:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TrZrlP4kp4CPZW7pcV8zh5hfbG/R/KtdzhBvIdW8ecGg2bXKEpjdW+qdPy9hF2czaFtdoBfn6HPh08CcAUbWDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T00:03:52.644149Z"},"content_sha256":"eba74b5f361e99f31e05ce372f18ded2ce18f720a41a886b2d8be4908246e3b7","schema_version":"1.0","event_id":"sha256:eba74b5f361e99f31e05ce372f18ded2ce18f720a41a886b2d8be4908246e3b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IWBAFUTYAOVQLTIQXI45DUTKRI/bundle.json","state_url":"https://pith.science/pith/IWBAFUTYAOVQLTIQXI45DUTKRI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IWBAFUTYAOVQLTIQXI45DUTKRI/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":"2026-06-02T00:03:52Z","links":{"resolver":"https://pith.science/pith/IWBAFUTYAOVQLTIQXI45DUTKRI","bundle":"https://pith.science/pith/IWBAFUTYAOVQLTIQXI45DUTKRI/bundle.json","state":"https://pith.science/pith/IWBAFUTYAOVQLTIQXI45DUTKRI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IWBAFUTYAOVQLTIQXI45DUTKRI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IWBAFUTYAOVQLTIQXI45DUTKRI","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":"2ab02a9968cac80752d31ea01e90bed81fcf97b8fefd1e8f6441b04c260b0561","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T03:42:24Z","title_canon_sha256":"b1478a3656237dcef7e2eebf02abc394599beb19f010550aab746df531e6c976"},"schema_version":"1.0","source":{"id":"2605.29310","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29310","created_at":"2026-05-29T01:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29310v1","created_at":"2026-05-29T01:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29310","created_at":"2026-05-29T01:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"IWBAFUTYAOVQ","created_at":"2026-05-29T01:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"IWBAFUTYAOVQLTIQ","created_at":"2026-05-29T01:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"IWBAFUTY","created_at":"2026-05-29T01:05:31Z"}],"graph_snapshots":[{"event_id":"sha256:eba74b5f361e99f31e05ce372f18ded2ce18f720a41a886b2d8be4908246e3b7","target":"graph","created_at":"2026-05-29T01:05:31Z","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/2605.29310/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stepwise model routing improves the efficiency of Large Reasoning Models (LRMs) by assigning each reasoning step to a suitable model. Recent methods formulate routing as a sequential decision process and train the router with reinforcement learning. However, although they model routing as a process, they still supervise the router with outcome rewards. Such rewards only reflect final answer correctness and fail to evaluate intermediate routing decisions, which can weaken performance and generalization. To address this gap, we propose RoRo, a rubric-guided process reward framework for stepwise ","authors_text":"Jian Yang, Shenghao Ye, Shuangwu Chen, Yu Guo, Zhengheng Li","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T03:42:24Z","title":"Rubric-Guided Process Reward for Stepwise Model Routing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29310","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":"sha256:1d7fd0dea980814ae39aa32f7f0a8d3cb72cef6e5619114032880950ed89ea30","target":"record","created_at":"2026-05-29T01:05:31Z","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":"2ab02a9968cac80752d31ea01e90bed81fcf97b8fefd1e8f6441b04c260b0561","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T03:42:24Z","title_canon_sha256":"b1478a3656237dcef7e2eebf02abc394599beb19f010550aab746df531e6c976"},"schema_version":"1.0","source":{"id":"2605.29310","kind":"arxiv","version":1}},"canonical_sha256":"458202d27803ab05cd10ba39d1d26a8a06f8d1abc470237e7d80f36011880cc0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"458202d27803ab05cd10ba39d1d26a8a06f8d1abc470237e7d80f36011880cc0","first_computed_at":"2026-05-29T01:05:31.974559Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:31.974559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yLrcnRnt+ls1bMlTSWwsRrh7sLRa2AKkTmB66LyGXqWe612J7wzUENwVG325PGC+sA8Jc9Q396kiJEGQecz0Bw==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:31.975290Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29310","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d7fd0dea980814ae39aa32f7f0a8d3cb72cef6e5619114032880950ed89ea30","sha256:eba74b5f361e99f31e05ce372f18ded2ce18f720a41a886b2d8be4908246e3b7"],"state_sha256":"7e5a7e94a8aaeb2d1d1e3e572f3ecc49e49438caae480583521371d5795ee743"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EgmVgIv/moO6h6qKX2B7uC8ZJ6xuMLfpd1p7g9XgJ/8QrKPuaW6wnJL6LCCU+OfQ1bNYJSFoNnCPtmHyyKT7Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T00:03:52.646307Z","bundle_sha256":"4c06978c4559a429768a99885fcadc159ab7a8282cabd94a870c0391e8c446ce"}}