{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KV26OFPBNXJSPI7LX2OYAZP3LM","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":"23203d854083ceaebb3bef30538b7fdb59baf5f8c026ec9b4d6c47a3f476f9f8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-28T16:21:04Z","title_canon_sha256":"7d119e5bba3866e5d3125d304258e319a59afbbf656aa7979b2aaebbd955acbe"},"schema_version":"1.0","source":{"id":"2606.29481","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29481","created_at":"2026-06-30T01:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29481v1","created_at":"2026-06-30T01:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29481","created_at":"2026-06-30T01:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"KV26OFPBNXJS","created_at":"2026-06-30T01:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"KV26OFPBNXJSPI7L","created_at":"2026-06-30T01:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"KV26OFPB","created_at":"2026-06-30T01:18:08Z"}],"graph_snapshots":[{"event_id":"sha256:1f202f7ede9a04f26d57dbf64798f826ab81ab62d0f35ea99e4ffd7fe5c48e29","target":"graph","created_at":"2026-06-30T01:18:08Z","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/2606.29481/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While reinforcement learning (RL) significantly enhances LLM reasoning, its efficacy is severely undermined by Pre-RL data overlap, where RL datasets overlap with pretraining or SFT corpora, causing models to exploit shortcuts by memorizing correct answers and fabricating post-hoc reasoning. To address this, we introduce HIPPO, a novel RL framework that integrates hint-injected aggregation with a tailored pairwise reward model. By utilizing hint injection to deliberately trigger overlap-induced behaviors, the resulting traces naturally serve as explicit anchors for pairwise comparison. This pr","authors_text":"Chen Zhang, Jiuheng Lin, Yansong Feng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-28T16:21:04Z","title":"To Reason or to Fabricate: Reasoning Without Shortcuts via Hint-Anchored Pairwise Aggregation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29481","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":"sha256:8ce563ac2978089dade334f4074bed16718fc9580e48bd487583e950ad98e38d","target":"record","created_at":"2026-06-30T01:18:08Z","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":"23203d854083ceaebb3bef30538b7fdb59baf5f8c026ec9b4d6c47a3f476f9f8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-28T16:21:04Z","title_canon_sha256":"7d119e5bba3866e5d3125d304258e319a59afbbf656aa7979b2aaebbd955acbe"},"schema_version":"1.0","source":{"id":"2606.29481","kind":"arxiv","version":1}},"canonical_sha256":"5575e715e16dd327a3ebbe9d8065fb5b3e83026dda07dfe07c861250b8517623","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5575e715e16dd327a3ebbe9d8065fb5b3e83026dda07dfe07c861250b8517623","first_computed_at":"2026-06-30T01:18:08.305664Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:18:08.305664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1oEjqpZa49yxJLnqyXfSCfEVT6+DlJpqUAG+/jkQ8/qEeyYQeXYdkgbZBRu2chdjZvo8R+AEvCMVco2Nrui7Dw==","signature_status":"signed_v1","signed_at":"2026-06-30T01:18:08.306375Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29481","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ce563ac2978089dade334f4074bed16718fc9580e48bd487583e950ad98e38d","sha256:1f202f7ede9a04f26d57dbf64798f826ab81ab62d0f35ea99e4ffd7fe5c48e29"],"state_sha256":"a51547386175fd4f86ea7d2807e0d2adde8947eca5edcdf321f87c7a05058d3b"}