{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AETV3T3JX6ITSKDEDDJXC5UQBO","short_pith_number":"pith:AETV3T3J","canonical_record":{"source":{"id":"2607.27770","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T07:05:37Z","cross_cats_sorted":[],"title_canon_sha256":"047c8a7531b87dddb05226b30b241a0f30c0fde2a3ff8c906f8c87404af4afd7","abstract_canon_sha256":"d65125fa2d19a738a9ccd905e65ae1bccc97d9a69e0be934b6eafa201a72b25c"},"schema_version":"1.0"},"canonical_sha256":"01275dcf69bf9139286418d37176900ba0349abe0e78e9dbb05d3b19019e74e0","source":{"kind":"arxiv","id":"2607.27770","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27770","created_at":"2026-07-31T01:30:32Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27770v1","created_at":"2026-07-31T01:30:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27770","created_at":"2026-07-31T01:30:32Z"},{"alias_kind":"pith_short_12","alias_value":"AETV3T3JX6IT","created_at":"2026-07-31T01:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"AETV3T3JX6ITSKDE","created_at":"2026-07-31T01:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"AETV3T3J","created_at":"2026-07-31T01:30:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AETV3T3JX6ITSKDEDDJXC5UQBO","target":"record","payload":{"canonical_record":{"source":{"id":"2607.27770","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T07:05:37Z","cross_cats_sorted":[],"title_canon_sha256":"047c8a7531b87dddb05226b30b241a0f30c0fde2a3ff8c906f8c87404af4afd7","abstract_canon_sha256":"d65125fa2d19a738a9ccd905e65ae1bccc97d9a69e0be934b6eafa201a72b25c"},"schema_version":"1.0"},"canonical_sha256":"01275dcf69bf9139286418d37176900ba0349abe0e78e9dbb05d3b19019e74e0","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01275dcf69bf9139286418d37176900ba0349abe0e78e9dbb05d3b19019e74e0","last_reissued_at":"2026-07-31T01:30:32.259318Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:30:32.259318Z"},"source_kind":"arxiv","source_id":"2607.27770","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":"2026-07-31T01:30:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7aiqzgkgXdVU72aXtJ5yWDiHCKlubff/j/PAZzHoO9n7YD4aXJg+n8MzA6WmJneUJi5JksQHa7Oc7w0zGYyUBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T15:28:31.825619Z"},"content_sha256":"8044c64fc50509a52a29fa035f18e880f313d4835ffe2a448850196b1087ac77","schema_version":"1.0","event_id":"sha256:8044c64fc50509a52a29fa035f18e880f313d4835ffe2a448850196b1087ac77"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AETV3T3JX6ITSKDEDDJXC5UQBO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond the Best Teacher: Expanding and Compressing the Reasoning Solution Manifold","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Songshuo Lu, Yaohua Tang, Zhi Chen","submitted_at":"2026-07-30T07:05:37Z","abstract_excerpt":"A single reinforcement-learning run can produce a strong reasoner yet an incomplete teacher: it often amplifies only a subset of the valid solution modes. We argue that reinforcement learning (RL)-trained policies should therefore be viewed as local probes of a multi-basin reasoning solution manifold, rather than as globally reliable supervisors. Based on this view, we propose an expand-then-compress framework that couples teacher construction with multi-teacher policy distillation. In the expansion stage, Residual Group Relative Policy Optimization (RGRPO) trains a sequence of teachers from a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27770","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/2607.27770/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":"2026-07-31T01:30:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9gs9KybBPBJi0mIVG74Q48crFfxXF1I6XZ4rEHkz4Rf8TYFed5d/090r1dsNwUIojFCfp5MJX04jrpZe1E9TDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T15:28:31.825997Z"},"content_sha256":"b6d63a31d04e4f6bb355e3ebd75538276a8037c38a3fdc07f941f4bd104a90ce","schema_version":"1.0","event_id":"sha256:b6d63a31d04e4f6bb355e3ebd75538276a8037c38a3fdc07f941f4bd104a90ce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AETV3T3JX6ITSKDEDDJXC5UQBO/bundle.json","state_url":"https://pith.science/pith/AETV3T3JX6ITSKDEDDJXC5UQBO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AETV3T3JX6ITSKDEDDJXC5UQBO/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":"2026-08-23T15:28:31Z","links":{"resolver":"https://pith.science/pith/AETV3T3JX6ITSKDEDDJXC5UQBO","bundle":"https://pith.science/pith/AETV3T3JX6ITSKDEDDJXC5UQBO/bundle.json","state":"https://pith.science/pith/AETV3T3JX6ITSKDEDDJXC5UQBO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AETV3T3JX6ITSKDEDDJXC5UQBO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AETV3T3JX6ITSKDEDDJXC5UQBO","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":"d65125fa2d19a738a9ccd905e65ae1bccc97d9a69e0be934b6eafa201a72b25c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T07:05:37Z","title_canon_sha256":"047c8a7531b87dddb05226b30b241a0f30c0fde2a3ff8c906f8c87404af4afd7"},"schema_version":"1.0","source":{"id":"2607.27770","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27770","created_at":"2026-07-31T01:30:32Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27770v1","created_at":"2026-07-31T01:30:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27770","created_at":"2026-07-31T01:30:32Z"},{"alias_kind":"pith_short_12","alias_value":"AETV3T3JX6IT","created_at":"2026-07-31T01:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"AETV3T3JX6ITSKDE","created_at":"2026-07-31T01:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"AETV3T3J","created_at":"2026-07-31T01:30:32Z"}],"graph_snapshots":[{"event_id":"sha256:b6d63a31d04e4f6bb355e3ebd75538276a8037c38a3fdc07f941f4bd104a90ce","target":"graph","created_at":"2026-07-31T01:30:32Z","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/2607.27770/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A single reinforcement-learning run can produce a strong reasoner yet an incomplete teacher: it often amplifies only a subset of the valid solution modes. We argue that reinforcement learning (RL)-trained policies should therefore be viewed as local probes of a multi-basin reasoning solution manifold, rather than as globally reliable supervisors. Based on this view, we propose an expand-then-compress framework that couples teacher construction with multi-teacher policy distillation. In the expansion stage, Residual Group Relative Policy Optimization (RGRPO) trains a sequence of teachers from a","authors_text":"Songshuo Lu, Yaohua Tang, Zhi Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T07:05:37Z","title":"Beyond the Best Teacher: Expanding and Compressing the Reasoning Solution Manifold"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27770","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":"sha256:8044c64fc50509a52a29fa035f18e880f313d4835ffe2a448850196b1087ac77","target":"record","created_at":"2026-07-31T01:30:32Z","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":"d65125fa2d19a738a9ccd905e65ae1bccc97d9a69e0be934b6eafa201a72b25c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T07:05:37Z","title_canon_sha256":"047c8a7531b87dddb05226b30b241a0f30c0fde2a3ff8c906f8c87404af4afd7"},"schema_version":"1.0","source":{"id":"2607.27770","kind":"arxiv","version":1}},"canonical_sha256":"01275dcf69bf9139286418d37176900ba0349abe0e78e9dbb05d3b19019e74e0","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01275dcf69bf9139286418d37176900ba0349abe0e78e9dbb05d3b19019e74e0","first_computed_at":"2026-07-31T01:30:32.259318Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:30:32.259318Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.27770","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8044c64fc50509a52a29fa035f18e880f313d4835ffe2a448850196b1087ac77","sha256:b6d63a31d04e4f6bb355e3ebd75538276a8037c38a3fdc07f941f4bd104a90ce"],"state_sha256":"a2483b188b0b56ddef4927c28ee82114a193f4a3bdb08cf92d3e98d3767d84de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8GPxu3kp8tchKNHPlZhtH2lmil5Bl42XNOVyMDjadmVDOD2fwTi03aN/AjVi66BuJwK8NtZIXbu7ZIhN/D4FCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T15:28:31.828482Z","bundle_sha256":"b4c0514d5f2625af10bdc88c8616e72f129570a51f3cd1784ff1c640a1458635"}}