{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WZMKQDMDG7QLAFRCZWLQTYDFXW","short_pith_number":"pith:WZMKQDMD","canonical_record":{"source":{"id":"2607.22996","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-25T02:21:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6d2f6dc2999a16bdf0291bb4037bee1015d9b9d7f4fc2f1d15118492bd9e4bcb","abstract_canon_sha256":"b5534fa6abf579d1338121718ede8057621fef51724751cb7d2b6ddee5a20445"},"schema_version":"1.0"},"canonical_sha256":"b658a80d8337e0b01622cd9709e065bdb5c6f84826a580fe537e4839e23b6f7f","source":{"kind":"arxiv","id":"2607.22996","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22996","created_at":"2026-07-28T00:22:06Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22996v1","created_at":"2026-07-28T00:22:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22996","created_at":"2026-07-28T00:22:06Z"},{"alias_kind":"pith_short_12","alias_value":"WZMKQDMDG7QL","created_at":"2026-07-28T00:22:06Z"},{"alias_kind":"pith_short_16","alias_value":"WZMKQDMDG7QLAFRC","created_at":"2026-07-28T00:22:06Z"},{"alias_kind":"pith_short_8","alias_value":"WZMKQDMD","created_at":"2026-07-28T00:22:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WZMKQDMDG7QLAFRCZWLQTYDFXW","target":"record","payload":{"canonical_record":{"source":{"id":"2607.22996","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-25T02:21:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6d2f6dc2999a16bdf0291bb4037bee1015d9b9d7f4fc2f1d15118492bd9e4bcb","abstract_canon_sha256":"b5534fa6abf579d1338121718ede8057621fef51724751cb7d2b6ddee5a20445"},"schema_version":"1.0"},"canonical_sha256":"b658a80d8337e0b01622cd9709e065bdb5c6f84826a580fe537e4839e23b6f7f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:22:06.670984Z","signature_b64":"99+orQxePcrq7jYg7Rb551RhonSALjUNlwN5kxD0ZK1yQb6PFzrmHJ29Wl0BcpBzv8+6hrmw+8oHCrsmprLDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b658a80d8337e0b01622cd9709e065bdb5c6f84826a580fe537e4839e23b6f7f","last_reissued_at":"2026-07-28T00:22:06.670156Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:22:06.670156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.22996","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":"2026-07-28T00:22:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D5uKBueqrRHO/QC7tDBkxnRgBlv6oH5quBCceofBbQ99BFZGa26dBJ9WtG4XGfJc+LmZNRPQhjj94BAci48DAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:45:31.024871Z"},"content_sha256":"76cac5f645fc589520359abd35ef7463eb6810ec6ce3780b1be3bd961bf017c9","schema_version":"1.0","event_id":"sha256:76cac5f645fc589520359abd35ef7463eb6810ec6ce3780b1be3bd961bf017c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WZMKQDMDG7QLAFRCZWLQTYDFXW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Siyu Song, Wentao Liu, Xiaodong Zou, Xiaokun Wang","submitted_at":"2026-07-25T02:21:32Z","abstract_excerpt":"Large language models (LLMs) deployed in educational settings often behave as direct answerers: they disclose target concepts in the opening turn instead of guiding students through progressive inquiry, as Socratic pedagogy prescribes. We present HeuristicEdu, a two-phase pipeline that aligns Qwen2.5-7B toward Socratic tutoring via supervised warm-up and Group Relative Policy Optimization (GRPO). Training uses SocraticEdu, 797 multi-turn Chinese children's science dialogues reconstructed from a live platform, with a heuristic reward over cognitive depth (R_cog), curiosity engagement (R_eng), a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22996","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/2607.22996/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":"2026-07-28T00:22:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lesIh8EjApWjB7kl4HKsNj1DT2gxdNklTKlyHV9wCqxYQUClupwfOFgGtQy6yDw+jTZbosZj53iGRCDvPDl2CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:45:31.025382Z"},"content_sha256":"8bf2801071d3e4e8dd6aab7845bb6cfbe1aca849b58e8a752f6351cb521215f5","schema_version":"1.0","event_id":"sha256:8bf2801071d3e4e8dd6aab7845bb6cfbe1aca849b58e8a752f6351cb521215f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WZMKQDMDG7QLAFRCZWLQTYDFXW/bundle.json","state_url":"https://pith.science/pith/WZMKQDMDG7QLAFRCZWLQTYDFXW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WZMKQDMDG7QLAFRCZWLQTYDFXW/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":"2026-08-07T19:45:31Z","links":{"resolver":"https://pith.science/pith/WZMKQDMDG7QLAFRCZWLQTYDFXW","bundle":"https://pith.science/pith/WZMKQDMDG7QLAFRCZWLQTYDFXW/bundle.json","state":"https://pith.science/pith/WZMKQDMDG7QLAFRCZWLQTYDFXW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WZMKQDMDG7QLAFRCZWLQTYDFXW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WZMKQDMDG7QLAFRCZWLQTYDFXW","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":"b5534fa6abf579d1338121718ede8057621fef51724751cb7d2b6ddee5a20445","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-25T02:21:32Z","title_canon_sha256":"6d2f6dc2999a16bdf0291bb4037bee1015d9b9d7f4fc2f1d15118492bd9e4bcb"},"schema_version":"1.0","source":{"id":"2607.22996","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22996","created_at":"2026-07-28T00:22:06Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22996v1","created_at":"2026-07-28T00:22:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22996","created_at":"2026-07-28T00:22:06Z"},{"alias_kind":"pith_short_12","alias_value":"WZMKQDMDG7QL","created_at":"2026-07-28T00:22:06Z"},{"alias_kind":"pith_short_16","alias_value":"WZMKQDMDG7QLAFRC","created_at":"2026-07-28T00:22:06Z"},{"alias_kind":"pith_short_8","alias_value":"WZMKQDMD","created_at":"2026-07-28T00:22:06Z"}],"graph_snapshots":[{"event_id":"sha256:8bf2801071d3e4e8dd6aab7845bb6cfbe1aca849b58e8a752f6351cb521215f5","target":"graph","created_at":"2026-07-28T00:22:06Z","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/2607.22996/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) deployed in educational settings often behave as direct answerers: they disclose target concepts in the opening turn instead of guiding students through progressive inquiry, as Socratic pedagogy prescribes. We present HeuristicEdu, a two-phase pipeline that aligns Qwen2.5-7B toward Socratic tutoring via supervised warm-up and Group Relative Policy Optimization (GRPO). Training uses SocraticEdu, 797 multi-turn Chinese children's science dialogues reconstructed from a live platform, with a heuristic reward over cognitive depth (R_cog), curiosity engagement (R_eng), a","authors_text":"Siyu Song, Wentao Liu, Xiaodong Zou, Xiaokun Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-25T02:21:32Z","title":"Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22996","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":"sha256:76cac5f645fc589520359abd35ef7463eb6810ec6ce3780b1be3bd961bf017c9","target":"record","created_at":"2026-07-28T00:22:06Z","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":"b5534fa6abf579d1338121718ede8057621fef51724751cb7d2b6ddee5a20445","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-25T02:21:32Z","title_canon_sha256":"6d2f6dc2999a16bdf0291bb4037bee1015d9b9d7f4fc2f1d15118492bd9e4bcb"},"schema_version":"1.0","source":{"id":"2607.22996","kind":"arxiv","version":1}},"canonical_sha256":"b658a80d8337e0b01622cd9709e065bdb5c6f84826a580fe537e4839e23b6f7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b658a80d8337e0b01622cd9709e065bdb5c6f84826a580fe537e4839e23b6f7f","first_computed_at":"2026-07-28T00:22:06.670156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T00:22:06.670156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"99+orQxePcrq7jYg7Rb551RhonSALjUNlwN5kxD0ZK1yQb6PFzrmHJ29Wl0BcpBzv8+6hrmw+8oHCrsmprLDBw==","signature_status":"signed_v1","signed_at":"2026-07-28T00:22:06.670984Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22996","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76cac5f645fc589520359abd35ef7463eb6810ec6ce3780b1be3bd961bf017c9","sha256:8bf2801071d3e4e8dd6aab7845bb6cfbe1aca849b58e8a752f6351cb521215f5"],"state_sha256":"70f4011daca61acf6d253ddbedff3ce534b4af736c2ad017bdf43d9945e4bc04"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/xRDj0+t1RSQ5DqFcv5x/7ZgnxRDkJWLiBCiQGBRUPB5/iv4l9TT1ulTXgWVtYAy9dllkBuagk3x7xJqRgClBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:45:31.029119Z","bundle_sha256":"e7d84182b9227152645f77b8fc474003ccec3efd19f4789b99a4de0f6b6149d3"}}