{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DL6ZPSHZVPQ7OEZNTKPDAQ7PRP","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":"128fb98abdc797a795d1e257d3d6a5108fa02c8d26a07a0fba6363de3085e9c0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-10T17:15:53Z","title_canon_sha256":"684bdfc6b6b1c1e5c60246b2651a7a891449d5476f6f405cdfef109dab6296a4"},"schema_version":"1.0","source":{"id":"2504.07912","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07912","created_at":"2026-07-05T11:50:34Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07912v2","created_at":"2026-07-05T11:50:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07912","created_at":"2026-07-05T11:50:34Z"},{"alias_kind":"pith_short_12","alias_value":"DL6ZPSHZVPQ7","created_at":"2026-07-05T11:50:34Z"},{"alias_kind":"pith_short_16","alias_value":"DL6ZPSHZVPQ7OEZN","created_at":"2026-07-05T11:50:34Z"},{"alias_kind":"pith_short_8","alias_value":"DL6ZPSHZ","created_at":"2026-07-05T11:50:34Z"}],"graph_snapshots":[{"event_id":"sha256:afa91a41e193eb0920e0085d3e17702979e970002a416e0ed809b1093bff0a5b","target":"graph","created_at":"2026-07-05T11:50:34Z","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/2504.07912/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL)-based fine-tuning has become a crucial step in post-training language models for advanced mathematical reasoning and coding. Following the success of frontier reasoning models, recent work has demonstrated that RL fine-tuning consistently improves performance, even in smaller-scale models; however, the underlying mechanisms driving these improvements are not well-understood. Understanding the effects of RL fine-tuning requires disentangling its interaction with pretraining data composition, hyperparameters, and model scale, but such problems are exacerbated by the l","authors_text":"Alexandru Meterez, Cengiz Pehlevan, Eran Malach, Rosie Zhao, Samy Jelassi, Sham Kakade","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-10T17:15:53Z","title":"Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07912","kind":"arxiv","version":2},"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:f7863969ad5f8ab95e7478a516f37a25c8c8ba43febc6a2a0c1dc02290cb44c3","target":"record","created_at":"2026-07-05T11:50:34Z","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":"128fb98abdc797a795d1e257d3d6a5108fa02c8d26a07a0fba6363de3085e9c0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-10T17:15:53Z","title_canon_sha256":"684bdfc6b6b1c1e5c60246b2651a7a891449d5476f6f405cdfef109dab6296a4"},"schema_version":"1.0","source":{"id":"2504.07912","kind":"arxiv","version":2}},"canonical_sha256":"1afd97c8f9abe1f7132d9a9e3043ef8bd5bb338d8395e4c3b36e5b12e9e33bc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1afd97c8f9abe1f7132d9a9e3043ef8bd5bb338d8395e4c3b36e5b12e9e33bc7","first_computed_at":"2026-07-05T11:50:34.744929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:34.744929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M82j+jrIHnWB8c1oviP4SKthP4vY/rScF21TsWP591LrmBjcIG6bv4rwg6EsxbHjHbFIyAeVQNX2QYAmNBgBAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:34.745411Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07912","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7863969ad5f8ab95e7478a516f37a25c8c8ba43febc6a2a0c1dc02290cb44c3","sha256:afa91a41e193eb0920e0085d3e17702979e970002a416e0ed809b1093bff0a5b"],"state_sha256":"0f02e55a209e85b05ce3f6f3b7cf28ec09f82accfd04e15c0a20c9fb9746a950"}