{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XPJIB7NK3RLTT7KKXC5I2EOIP7","short_pith_number":"pith:XPJIB7NK","canonical_record":{"source":{"id":"2606.24064","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T02:14:12Z","cross_cats_sorted":[],"title_canon_sha256":"67a56461b1c4bd6934784c4fcee04ffe89bebb06a2a97eefc172eff8ce19eadc","abstract_canon_sha256":"395a8e87e083bf72d44609f7b445d38fa5539d6ea36bfbae93114dd1dc7b6771"},"schema_version":"1.0"},"canonical_sha256":"bbd280fdaadc5739fd4ab8ba8d11c87fe082073bbf509866c18e3565dc510c34","source":{"kind":"arxiv","id":"2606.24064","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24064","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24064v1","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24064","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"pith_short_12","alias_value":"XPJIB7NK3RLT","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"pith_short_16","alias_value":"XPJIB7NK3RLTT7KK","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"pith_short_8","alias_value":"XPJIB7NK","created_at":"2026-06-24T01:14:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XPJIB7NK3RLTT7KKXC5I2EOIP7","target":"record","payload":{"canonical_record":{"source":{"id":"2606.24064","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T02:14:12Z","cross_cats_sorted":[],"title_canon_sha256":"67a56461b1c4bd6934784c4fcee04ffe89bebb06a2a97eefc172eff8ce19eadc","abstract_canon_sha256":"395a8e87e083bf72d44609f7b445d38fa5539d6ea36bfbae93114dd1dc7b6771"},"schema_version":"1.0"},"canonical_sha256":"bbd280fdaadc5739fd4ab8ba8d11c87fe082073bbf509866c18e3565dc510c34","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:39.427714Z","signature_b64":"ZKYb6MENVpopR7B9fycvg//cbyrQQTYj8zdqkOlSqNM19DnUViTz+fcmlEar4wvRJqZNYlBYg66rI2uwkNLPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbd280fdaadc5739fd4ab8ba8d11c87fe082073bbf509866c18e3565dc510c34","last_reissued_at":"2026-06-24T01:14:39.427302Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:39.427302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.24064","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":"2026-06-24T01:14:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m2xIHWimla3RZ+uQ42ebd+AOS48Bsjszf1XnNb9Oas0ura0ikN2Z8aocmPwVCm7M2XPWg6Wc8Y4A6D+TVdI7Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T11:04:26.882569Z"},"content_sha256":"9c5fb810899b36d81318c3df21a48f8ce0ab812922e0819aadc26aea1291cb9c","schema_version":"1.0","event_id":"sha256:9c5fb810899b36d81318c3df21a48f8ce0ab812922e0819aadc26aea1291cb9c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XPJIB7NK3RLTT7KKXC5I2EOIP7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bei Li, Canbin Huang, Jingang Wang, Qifan Wang, Tianyuan Shi, Xiaojun Quan, Xin Chen","submitted_at":"2026-06-23T02:14:12Z","abstract_excerpt":"Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories, effectively transferring what to answer rather than how to reason. This trajectory-level imitation encourages memorization of instance-specific steps rather than acquisition of transferable problem-solving skills, limiting generalization to novel problems. We propose Strategy-Guided Policy Optimization (SGPO), which replaces instance-level trajectory imitation with reusable strategy distillation. SGPO extracts structured strategy descriptions from strong-model resp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24064","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/2606.24064/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":"2026-06-24T01:14:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5fRW1nIftoXMO3VX8tVFrP37AXApmX8Tyhz3EDcozYAEOV3MaR89s6Z8wU2hSfV2OL6/1Q0KMzp82FR7zOPfCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T11:04:26.882947Z"},"content_sha256":"216e61c49e8fe3e46bfbb1ffefe34844afa3e2b9724d5f89edc77cec95ee0428","schema_version":"1.0","event_id":"sha256:216e61c49e8fe3e46bfbb1ffefe34844afa3e2b9724d5f89edc77cec95ee0428"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XPJIB7NK3RLTT7KKXC5I2EOIP7/bundle.json","state_url":"https://pith.science/pith/XPJIB7NK3RLTT7KKXC5I2EOIP7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XPJIB7NK3RLTT7KKXC5I2EOIP7/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":"2026-06-30T11:04:26Z","links":{"resolver":"https://pith.science/pith/XPJIB7NK3RLTT7KKXC5I2EOIP7","bundle":"https://pith.science/pith/XPJIB7NK3RLTT7KKXC5I2EOIP7/bundle.json","state":"https://pith.science/pith/XPJIB7NK3RLTT7KKXC5I2EOIP7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XPJIB7NK3RLTT7KKXC5I2EOIP7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XPJIB7NK3RLTT7KKXC5I2EOIP7","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":"395a8e87e083bf72d44609f7b445d38fa5539d6ea36bfbae93114dd1dc7b6771","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T02:14:12Z","title_canon_sha256":"67a56461b1c4bd6934784c4fcee04ffe89bebb06a2a97eefc172eff8ce19eadc"},"schema_version":"1.0","source":{"id":"2606.24064","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24064","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24064v1","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24064","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"pith_short_12","alias_value":"XPJIB7NK3RLT","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"pith_short_16","alias_value":"XPJIB7NK3RLTT7KK","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"pith_short_8","alias_value":"XPJIB7NK","created_at":"2026-06-24T01:14:39Z"}],"graph_snapshots":[{"event_id":"sha256:216e61c49e8fe3e46bfbb1ffefe34844afa3e2b9724d5f89edc77cec95ee0428","target":"graph","created_at":"2026-06-24T01:14:39Z","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/2606.24064/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories, effectively transferring what to answer rather than how to reason. This trajectory-level imitation encourages memorization of instance-specific steps rather than acquisition of transferable problem-solving skills, limiting generalization to novel problems. We propose Strategy-Guided Policy Optimization (SGPO), which replaces instance-level trajectory imitation with reusable strategy distillation. SGPO extracts structured strategy descriptions from strong-model resp","authors_text":"Bei Li, Canbin Huang, Jingang Wang, Qifan Wang, Tianyuan Shi, Xiaojun Quan, Xin Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T02:14:12Z","title":"Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24064","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":"sha256:9c5fb810899b36d81318c3df21a48f8ce0ab812922e0819aadc26aea1291cb9c","target":"record","created_at":"2026-06-24T01:14:39Z","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":"395a8e87e083bf72d44609f7b445d38fa5539d6ea36bfbae93114dd1dc7b6771","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T02:14:12Z","title_canon_sha256":"67a56461b1c4bd6934784c4fcee04ffe89bebb06a2a97eefc172eff8ce19eadc"},"schema_version":"1.0","source":{"id":"2606.24064","kind":"arxiv","version":1}},"canonical_sha256":"bbd280fdaadc5739fd4ab8ba8d11c87fe082073bbf509866c18e3565dc510c34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbd280fdaadc5739fd4ab8ba8d11c87fe082073bbf509866c18e3565dc510c34","first_computed_at":"2026-06-24T01:14:39.427302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:39.427302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZKYb6MENVpopR7B9fycvg//cbyrQQTYj8zdqkOlSqNM19DnUViTz+fcmlEar4wvRJqZNYlBYg66rI2uwkNLPAQ==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:39.427714Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24064","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c5fb810899b36d81318c3df21a48f8ce0ab812922e0819aadc26aea1291cb9c","sha256:216e61c49e8fe3e46bfbb1ffefe34844afa3e2b9724d5f89edc77cec95ee0428"],"state_sha256":"310320e16306c3a455815a6ef27cc54583957d65b1c7319f365cf291f06db2e0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vfEhZNX3TAgF81oY13aUabkh6kzMkhTCfNWJKZfeJBjFUxmO/9Ls8ldwGfp7pNhnIsuogLbDUSn7BZj2JXX8Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T11:04:26.884849Z","bundle_sha256":"ab4fd04801bff2f4f2b86582e093c535c08c4d6e10924a32848669208248ce88"}}