{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CNMHZAEB6SVA7NIRYFYS75H6DH","short_pith_number":"pith:CNMHZAEB","canonical_record":{"source":{"id":"2607.05339","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T17:21:16Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"cc0f816ef0c53cb1958ae4f8b411ba4a948afbbf41bda99ac3ef539325416ff9","abstract_canon_sha256":"6d23e8118c83f8aef4988f4717a411deaaf5b554cb9faeefd375b1678ed4461c"},"schema_version":"1.0"},"canonical_sha256":"13587c8081f4aa0fb511c1712ff4fe19cf5b29655bdf3d487c2b7a4d0dea5fc6","source":{"kind":"arxiv","id":"2607.05339","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05339","created_at":"2026-07-07T03:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05339v1","created_at":"2026-07-07T03:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05339","created_at":"2026-07-07T03:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"CNMHZAEB6SVA","created_at":"2026-07-07T03:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"CNMHZAEB6SVA7NIR","created_at":"2026-07-07T03:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"CNMHZAEB","created_at":"2026-07-07T03:19:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CNMHZAEB6SVA7NIRYFYS75H6DH","target":"record","payload":{"canonical_record":{"source":{"id":"2607.05339","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T17:21:16Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"cc0f816ef0c53cb1958ae4f8b411ba4a948afbbf41bda99ac3ef539325416ff9","abstract_canon_sha256":"6d23e8118c83f8aef4988f4717a411deaaf5b554cb9faeefd375b1678ed4461c"},"schema_version":"1.0"},"canonical_sha256":"13587c8081f4aa0fb511c1712ff4fe19cf5b29655bdf3d487c2b7a4d0dea5fc6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T03:19:24.121728Z","signature_b64":"ZQtD7MG16oEL+adF5HAP3Dgxujhky5I2RLGGXjMDZGqY7eW/6cnUpu8+lBrq2M87Ik1BHa/fUDhqEsaP8LrBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13587c8081f4aa0fb511c1712ff4fe19cf5b29655bdf3d487c2b7a4d0dea5fc6","last_reissued_at":"2026-07-07T03:19:24.121301Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T03:19:24.121301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.05339","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":"2026-07-07T03:19:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dxV+k3yFm9eiueBqunbWcwj2oZ/TIJ6dArPsIiBU2KoCKo2Eh8ngSdDnBR2gbD9gsAY7vECjwXtEnipl95pTCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:25:56.522222Z"},"content_sha256":"1bed6bae03d25bdfa78ac5bf765a283ab1189b092645a67f964c23fe7791bac2","schema_version":"1.0","event_id":"sha256:1bed6bae03d25bdfa78ac5bf765a283ab1189b092645a67f964c23fe7791bac2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CNMHZAEB6SVA7NIRYFYS75H6DH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TREK: Distill to Explore, Reinforce to Refine","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aida Rahmattalabi, Alborz Geramifard, Hejian Sang, Jelena Markovic-Voronov, Kayhan Behdin, Ran He, Sen Na, Wenhui Zhu, Xiaomin Li, Xinchen Du, Yuanda Xu, Zhengze Zhou, Zhipeng Wang","submitted_at":"2026-07-06T17:21:16Z","abstract_excerpt":"Group Relative Policy Optimization (GRPO) is effective when the current policy already samples useful reasoning trajectories, but it stalls on hard prompts whose correct solution modes lie outside the student's on-policy support. We propose TREK (Teacher-Routed Exploration via Forward KL), a simple staged procedure that uses distillation not for imitation but for exploration support expansion. A key advantage of TREK is its generality: because it only consumes verified output trajectories, it can use an external black-box teacher, a white-box teacher, or the same model given additional inferen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05339","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/2607.05339/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":"2026-07-07T03:19:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2gORcK9CwpRBYgLmSWIiojfUanrZ+ysVu+b+g/hMesS3WZj2F17t3srzistvlIj/MFyqkd4qr2JFlvhB1uPBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:25:56.522723Z"},"content_sha256":"79139a690388fb739ce2ca3d15cb6caadf17e4ea182c0f926f40c58ae925669e","schema_version":"1.0","event_id":"sha256:79139a690388fb739ce2ca3d15cb6caadf17e4ea182c0f926f40c58ae925669e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CNMHZAEB6SVA7NIRYFYS75H6DH/bundle.json","state_url":"https://pith.science/pith/CNMHZAEB6SVA7NIRYFYS75H6DH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CNMHZAEB6SVA7NIRYFYS75H6DH/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":"2026-08-07T00:25:56Z","links":{"resolver":"https://pith.science/pith/CNMHZAEB6SVA7NIRYFYS75H6DH","bundle":"https://pith.science/pith/CNMHZAEB6SVA7NIRYFYS75H6DH/bundle.json","state":"https://pith.science/pith/CNMHZAEB6SVA7NIRYFYS75H6DH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CNMHZAEB6SVA7NIRYFYS75H6DH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CNMHZAEB6SVA7NIRYFYS75H6DH","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":"6d23e8118c83f8aef4988f4717a411deaaf5b554cb9faeefd375b1678ed4461c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T17:21:16Z","title_canon_sha256":"cc0f816ef0c53cb1958ae4f8b411ba4a948afbbf41bda99ac3ef539325416ff9"},"schema_version":"1.0","source":{"id":"2607.05339","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05339","created_at":"2026-07-07T03:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05339v1","created_at":"2026-07-07T03:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05339","created_at":"2026-07-07T03:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"CNMHZAEB6SVA","created_at":"2026-07-07T03:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"CNMHZAEB6SVA7NIR","created_at":"2026-07-07T03:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"CNMHZAEB","created_at":"2026-07-07T03:19:24Z"}],"graph_snapshots":[{"event_id":"sha256:79139a690388fb739ce2ca3d15cb6caadf17e4ea182c0f926f40c58ae925669e","target":"graph","created_at":"2026-07-07T03:19:24Z","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/2607.05339/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Group Relative Policy Optimization (GRPO) is effective when the current policy already samples useful reasoning trajectories, but it stalls on hard prompts whose correct solution modes lie outside the student's on-policy support. We propose TREK (Teacher-Routed Exploration via Forward KL), a simple staged procedure that uses distillation not for imitation but for exploration support expansion. A key advantage of TREK is its generality: because it only consumes verified output trajectories, it can use an external black-box teacher, a white-box teacher, or the same model given additional inferen","authors_text":"Aida Rahmattalabi, Alborz Geramifard, Hejian Sang, Jelena Markovic-Voronov, Kayhan Behdin, Ran He, Sen Na, Wenhui Zhu, Xiaomin Li, Xinchen Du, Yuanda Xu, Zhengze Zhou, Zhipeng Wang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T17:21:16Z","title":"TREK: Distill to Explore, Reinforce to Refine"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05339","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":"sha256:1bed6bae03d25bdfa78ac5bf765a283ab1189b092645a67f964c23fe7791bac2","target":"record","created_at":"2026-07-07T03:19:24Z","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":"6d23e8118c83f8aef4988f4717a411deaaf5b554cb9faeefd375b1678ed4461c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T17:21:16Z","title_canon_sha256":"cc0f816ef0c53cb1958ae4f8b411ba4a948afbbf41bda99ac3ef539325416ff9"},"schema_version":"1.0","source":{"id":"2607.05339","kind":"arxiv","version":1}},"canonical_sha256":"13587c8081f4aa0fb511c1712ff4fe19cf5b29655bdf3d487c2b7a4d0dea5fc6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13587c8081f4aa0fb511c1712ff4fe19cf5b29655bdf3d487c2b7a4d0dea5fc6","first_computed_at":"2026-07-07T03:19:24.121301Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T03:19:24.121301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZQtD7MG16oEL+adF5HAP3Dgxujhky5I2RLGGXjMDZGqY7eW/6cnUpu8+lBrq2M87Ik1BHa/fUDhqEsaP8LrBDg==","signature_status":"signed_v1","signed_at":"2026-07-07T03:19:24.121728Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.05339","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bed6bae03d25bdfa78ac5bf765a283ab1189b092645a67f964c23fe7791bac2","sha256:79139a690388fb739ce2ca3d15cb6caadf17e4ea182c0f926f40c58ae925669e"],"state_sha256":"6214f44ea39a28f342dce751ce8138205eeab7e285e056c8cfa5c3574f12b9fa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VHNuPwacsMz0YetBEicsbyYJPI6FXYtOm6RwDN0/6kuw3QKcYIMhXOGXcBMRkSN1dQYNq1SVNLsQAKJFz77/CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:25:56.527589Z","bundle_sha256":"de10cfa02e88a16df305327e9845f9fe9c3020ae4a7af2aba693b76766fee95e"}}