{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KKK6GEDMK7KL4SCRFFZLBAIQK3","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":"f87c17dbec146f48ab925260964d26365a8e76b9dd4deeb269fc9f2835c73b47","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T13:13:49Z","title_canon_sha256":"2e21f2045ce0ec770d8a252044d4ff7a8ad55eed53a6987b864945111fdf7cf9"},"schema_version":"1.0","source":{"id":"2605.29888","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29888","created_at":"2026-05-29T02:05:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29888v1","created_at":"2026-05-29T02:05:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29888","created_at":"2026-05-29T02:05:57Z"},{"alias_kind":"pith_short_12","alias_value":"KKK6GEDMK7KL","created_at":"2026-05-29T02:05:57Z"},{"alias_kind":"pith_short_16","alias_value":"KKK6GEDMK7KL4SCR","created_at":"2026-05-29T02:05:57Z"},{"alias_kind":"pith_short_8","alias_value":"KKK6GEDM","created_at":"2026-05-29T02:05:57Z"}],"graph_snapshots":[{"event_id":"sha256:20590f72d67db091a9072d6886a6ac5180c8655d7f0837ae9c7b61349b7b9288","target":"graph","created_at":"2026-05-29T02:05:57Z","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/2605.29888/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) post-training has shown to improve reasoning in large language models (LLMs). However, there has been little exploration on the problem of data contamination in RL post-training, potentially undermining generalization and evaluation reliability of the training process itself. Existing detection methods primarily rely on output-level signals such as likelihood or entropy, which become unreliable for RL-trained models since RL shapes behavior through trajectory-level rewards rather than token likelihoods. We propose LaRA, a layer-wise representation analysis framework","authors_text":"Alan Ritter, Dongseok Lee, Guijin Son, Jaehyung Kim, Minju Gwak, Minseo Kwak","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T13:13:49Z","title":"LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29888","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":"sha256:5c0c1605b8c7a48244755810abfdd8eb63293ce9ea75f4f9e22763e44bdd14ac","target":"record","created_at":"2026-05-29T02:05:57Z","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":"f87c17dbec146f48ab925260964d26365a8e76b9dd4deeb269fc9f2835c73b47","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T13:13:49Z","title_canon_sha256":"2e21f2045ce0ec770d8a252044d4ff7a8ad55eed53a6987b864945111fdf7cf9"},"schema_version":"1.0","source":{"id":"2605.29888","kind":"arxiv","version":1}},"canonical_sha256":"5295e3106c57d4be48512972b0811056ce21cb533129953a24245ffc3287cc27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5295e3106c57d4be48512972b0811056ce21cb533129953a24245ffc3287cc27","first_computed_at":"2026-05-29T02:05:57.884034Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:05:57.884034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8GWP3PZNb51JRcPEuzHnSYcMnsF6AE/GpB4HbVPWXbUuR6I5yqAWxKwdHXg5rs31OlRoNVBBEOuI0ttNarqICw==","signature_status":"signed_v1","signed_at":"2026-05-29T02:05:57.884798Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29888","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c0c1605b8c7a48244755810abfdd8eb63293ce9ea75f4f9e22763e44bdd14ac","sha256:20590f72d67db091a9072d6886a6ac5180c8655d7f0837ae9c7b61349b7b9288"],"state_sha256":"d0cb63aae936b0ea35f43274eb6efddc6ab770deef0db5a5f87835e134494565"}