{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LJ364HT37EJD3IYQRCTXC74FBH","short_pith_number":"pith:LJ364HT3","canonical_record":{"source":{"id":"2607.01232","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T17:59:54Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"656c7a3fa4f5933a7514b6ddcc1593d61986ac28625f0597daa4a6e04a87a72a","abstract_canon_sha256":"b2aadc8c43827e2fc2818d0fe11578d488afaae187f37bcf944765c3d3e3fbee"},"schema_version":"1.0"},"canonical_sha256":"5a77ee1e7bf9123da31088a7717f8509f0ebbf44cd5acc79bc2dae7ed96b7292","source":{"kind":"arxiv","id":"2607.01232","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01232","created_at":"2026-07-02T01:18:33Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01232v1","created_at":"2026-07-02T01:18:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01232","created_at":"2026-07-02T01:18:33Z"},{"alias_kind":"pith_short_12","alias_value":"LJ364HT37EJD","created_at":"2026-07-02T01:18:33Z"},{"alias_kind":"pith_short_16","alias_value":"LJ364HT37EJD3IYQ","created_at":"2026-07-02T01:18:33Z"},{"alias_kind":"pith_short_8","alias_value":"LJ364HT3","created_at":"2026-07-02T01:18:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LJ364HT37EJD3IYQRCTXC74FBH","target":"record","payload":{"canonical_record":{"source":{"id":"2607.01232","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T17:59:54Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"656c7a3fa4f5933a7514b6ddcc1593d61986ac28625f0597daa4a6e04a87a72a","abstract_canon_sha256":"b2aadc8c43827e2fc2818d0fe11578d488afaae187f37bcf944765c3d3e3fbee"},"schema_version":"1.0"},"canonical_sha256":"5a77ee1e7bf9123da31088a7717f8509f0ebbf44cd5acc79bc2dae7ed96b7292","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:33.423680Z","signature_b64":"Aq5C9323cCOd8amTYEceYySy0AnEgTDnBtpvr1YD6XIuz4AK+KHWgYL9+8ZtJo97t/9ybWh55GiCY4Ejs0dyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a77ee1e7bf9123da31088a7717f8509f0ebbf44cd5acc79bc2dae7ed96b7292","last_reissued_at":"2026-07-02T01:18:33.423269Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:33.423269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.01232","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":"2026-07-02T01:18:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"53yQ9rCCYxEwhvMp26j/i+2NzMHfpfPQbQHboVrAg+RyFqiUGke9FmTZN27plToOZksbsbQaxzShlMKOaDguAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T08:22:47.515442Z"},"content_sha256":"d2c8be634dddcdcc8097b5aee03e3a26dc56cd6bfc7f3b4779f98b4afa0835a6","schema_version":"1.0","event_id":"sha256:d2c8be634dddcdcc8097b5aee03e3a26dc56cd6bfc7f3b4779f98b4afa0835a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LJ364HT37EJD3IYQRCTXC74FBH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Athanasios Glentis, Chung-Yiu Yau, Dawei Li, Hongzhou Lin, Mingyi Hong, Rizhen Hu, Zijian Zhang","submitted_at":"2026-07-01T17:59:54Z","abstract_excerpt":"Reinforcement learning (RL) has become a central component of post-training large language models (LLMs), yet little is understood about how RL adaptation is distributed across transformer layers. Existing approaches typically update all model parameters uniformly, implicitly assuming that every layer contributes similarly to the gains obtained during RL post-training. In this work, we challenge this assumption through a systematic layer-wise study of RL training. Surprisingly, we find that training a single transformer layer can recover most of the gains achieved by full-parameter RL training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01232","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/2607.01232/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":"2026-07-02T01:18:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t2pO6T21Ki64H1Yau56wmEHAUJnhA4nJZxBs+YaJpNOz9tKC5BaxqjWZ3vvumwc/n5AHjDoMrj/N3ApiWW/wBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T08:22:47.515818Z"},"content_sha256":"0229acbfb2ce678d3ad5203c1abb4e2017ae4d007c054f356ae424e399daf2e3","schema_version":"1.0","event_id":"sha256:0229acbfb2ce678d3ad5203c1abb4e2017ae4d007c054f356ae424e399daf2e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LJ364HT37EJD3IYQRCTXC74FBH/bundle.json","state_url":"https://pith.science/pith/LJ364HT37EJD3IYQRCTXC74FBH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LJ364HT37EJD3IYQRCTXC74FBH/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":"2026-07-03T08:22:47Z","links":{"resolver":"https://pith.science/pith/LJ364HT37EJD3IYQRCTXC74FBH","bundle":"https://pith.science/pith/LJ364HT37EJD3IYQRCTXC74FBH/bundle.json","state":"https://pith.science/pith/LJ364HT37EJD3IYQRCTXC74FBH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LJ364HT37EJD3IYQRCTXC74FBH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LJ364HT37EJD3IYQRCTXC74FBH","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":"b2aadc8c43827e2fc2818d0fe11578d488afaae187f37bcf944765c3d3e3fbee","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T17:59:54Z","title_canon_sha256":"656c7a3fa4f5933a7514b6ddcc1593d61986ac28625f0597daa4a6e04a87a72a"},"schema_version":"1.0","source":{"id":"2607.01232","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01232","created_at":"2026-07-02T01:18:33Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01232v1","created_at":"2026-07-02T01:18:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01232","created_at":"2026-07-02T01:18:33Z"},{"alias_kind":"pith_short_12","alias_value":"LJ364HT37EJD","created_at":"2026-07-02T01:18:33Z"},{"alias_kind":"pith_short_16","alias_value":"LJ364HT37EJD3IYQ","created_at":"2026-07-02T01:18:33Z"},{"alias_kind":"pith_short_8","alias_value":"LJ364HT3","created_at":"2026-07-02T01:18:33Z"}],"graph_snapshots":[{"event_id":"sha256:0229acbfb2ce678d3ad5203c1abb4e2017ae4d007c054f356ae424e399daf2e3","target":"graph","created_at":"2026-07-02T01:18:33Z","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/2607.01232/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has become a central component of post-training large language models (LLMs), yet little is understood about how RL adaptation is distributed across transformer layers. Existing approaches typically update all model parameters uniformly, implicitly assuming that every layer contributes similarly to the gains obtained during RL post-training. In this work, we challenge this assumption through a systematic layer-wise study of RL training. Surprisingly, we find that training a single transformer layer can recover most of the gains achieved by full-parameter RL training","authors_text":"Athanasios Glentis, Chung-Yiu Yau, Dawei Li, Hongzhou Lin, Mingyi Hong, Rizhen Hu, Zijian Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T17:59:54Z","title":"Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01232","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:d2c8be634dddcdcc8097b5aee03e3a26dc56cd6bfc7f3b4779f98b4afa0835a6","target":"record","created_at":"2026-07-02T01:18:33Z","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":"b2aadc8c43827e2fc2818d0fe11578d488afaae187f37bcf944765c3d3e3fbee","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T17:59:54Z","title_canon_sha256":"656c7a3fa4f5933a7514b6ddcc1593d61986ac28625f0597daa4a6e04a87a72a"},"schema_version":"1.0","source":{"id":"2607.01232","kind":"arxiv","version":1}},"canonical_sha256":"5a77ee1e7bf9123da31088a7717f8509f0ebbf44cd5acc79bc2dae7ed96b7292","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a77ee1e7bf9123da31088a7717f8509f0ebbf44cd5acc79bc2dae7ed96b7292","first_computed_at":"2026-07-02T01:18:33.423269Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:18:33.423269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Aq5C9323cCOd8amTYEceYySy0AnEgTDnBtpvr1YD6XIuz4AK+KHWgYL9+8ZtJo97t/9ybWh55GiCY4Ejs0dyDA==","signature_status":"signed_v1","signed_at":"2026-07-02T01:18:33.423680Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01232","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2c8be634dddcdcc8097b5aee03e3a26dc56cd6bfc7f3b4779f98b4afa0835a6","sha256:0229acbfb2ce678d3ad5203c1abb4e2017ae4d007c054f356ae424e399daf2e3"],"state_sha256":"2268278c56210eef8ef539f9bcfce5fa42983301f4b0d8af201f058d27bb423b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KtSKu9B3xuD6v8kYzxGKL8kAGcPL8xk365MR6eUTfWlHQpHUVbu1BGCdQNNUfaNmnNjeH9YNCy+5RfXQXVo2Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T08:22:47.517736Z","bundle_sha256":"c34c828dfe645e691cc7f6e46ba3755f0307fbe7573758b622810bc86705424c"}}