{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4K5Z7M56SU67IRBVQDGH265YC6","short_pith_number":"pith:4K5Z7M56","canonical_record":{"source":{"id":"2506.15710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T17:57:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4441e90ae07a9f1889f723c47aebcbda9502a677c1597c07f9f74f0137996f49","abstract_canon_sha256":"d57280a51961f0ebbab12d88ac2722ae50815c48b52103178f7bc3dfb39645dc"},"schema_version":"1.0"},"canonical_sha256":"e2bb9fb3be953df4443580cc7d7bb817893a16e54991f4567e9bff059f528c67","source":{"kind":"arxiv","id":"2506.15710","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.15710","created_at":"2026-07-05T11:23:50Z"},{"alias_kind":"arxiv_version","alias_value":"2506.15710v1","created_at":"2026-07-05T11:23:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15710","created_at":"2026-07-05T11:23:50Z"},{"alias_kind":"pith_short_12","alias_value":"4K5Z7M56SU67","created_at":"2026-07-05T11:23:50Z"},{"alias_kind":"pith_short_16","alias_value":"4K5Z7M56SU67IRBV","created_at":"2026-07-05T11:23:50Z"},{"alias_kind":"pith_short_8","alias_value":"4K5Z7M56","created_at":"2026-07-05T11:23:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4K5Z7M56SU67IRBVQDGH265YC6","target":"record","payload":{"canonical_record":{"source":{"id":"2506.15710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T17:57:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4441e90ae07a9f1889f723c47aebcbda9502a677c1597c07f9f74f0137996f49","abstract_canon_sha256":"d57280a51961f0ebbab12d88ac2722ae50815c48b52103178f7bc3dfb39645dc"},"schema_version":"1.0"},"canonical_sha256":"e2bb9fb3be953df4443580cc7d7bb817893a16e54991f4567e9bff059f528c67","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:50.840519Z","signature_b64":"xdMG/lioE9CXanXN3aZkSPb/5Lm5E+CCqo2qn2zvQ48IE+4sNiNVbTkfvQ4ktNCdK7+sNA3unrZuLZ0XaRAeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2bb9fb3be953df4443580cc7d7bb817893a16e54991f4567e9bff059f528c67","last_reissued_at":"2026-07-05T11:23:50.840004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:50.840004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.15710","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":"2026-07-05T11:23:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7F05PM3HSFuPpKStR7KvNfwVc7I6dfe9686iTl0prC/99kURSDc+9eDmBY81V8JTge1twMoLQhK7zASpmEifDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:28:38.445381Z"},"content_sha256":"647638a50b89daeb558b3e4138a9d6d7e5dc8d41be546e3195cf623474a3d8df","schema_version":"1.0","event_id":"sha256:647638a50b89daeb558b3e4138a9d6d7e5dc8d41be546e3195cf623474a3d8df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4K5Z7M56SU67IRBVQDGH265YC6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RAST: Reasoning Activation in LLMs via Small-model Transfer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiawei Han, Minhao Jiang, Siru Ouyang, Xinyu Zhu, Yu Meng, Zilin Xiao","submitted_at":"2025-05-30T17:57:08Z","abstract_excerpt":"Reinforcement learning (RL) has become a powerful approach for improving the reasoning capabilities of large language models (LLMs), as evidenced by recent successes such as OpenAI's o1 and Deepseek-R1. However, applying RL at scale remains intimidatingly resource-intensive, requiring multiple model copies and extensive GPU workloads. On the other hand, while being powerful, recent studies suggest that RL does not fundamentally endow models with new knowledge; rather, it primarily reshapes the model's output distribution to activate reasoning capabilities latent in the base model. Building on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15710","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/2506.15710/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":"2026-07-05T11:23:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EZ+8/ZbROnPF7X7YsQW2YInQjkLuwYKhpPPmueRmg0Dhte79y9N8pZ8anz4SpQUa+pUj0w3xU2KTZ35qqgKeAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:28:38.445955Z"},"content_sha256":"c1a612d1346192bf57a3cecfd3d1cd3e801d698d5676fc793aacd1b60d6db352","schema_version":"1.0","event_id":"sha256:c1a612d1346192bf57a3cecfd3d1cd3e801d698d5676fc793aacd1b60d6db352"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4K5Z7M56SU67IRBVQDGH265YC6/bundle.json","state_url":"https://pith.science/pith/4K5Z7M56SU67IRBVQDGH265YC6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4K5Z7M56SU67IRBVQDGH265YC6/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":"2026-08-09T07:28:38Z","links":{"resolver":"https://pith.science/pith/4K5Z7M56SU67IRBVQDGH265YC6","bundle":"https://pith.science/pith/4K5Z7M56SU67IRBVQDGH265YC6/bundle.json","state":"https://pith.science/pith/4K5Z7M56SU67IRBVQDGH265YC6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4K5Z7M56SU67IRBVQDGH265YC6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4K5Z7M56SU67IRBVQDGH265YC6","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":"d57280a51961f0ebbab12d88ac2722ae50815c48b52103178f7bc3dfb39645dc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T17:57:08Z","title_canon_sha256":"4441e90ae07a9f1889f723c47aebcbda9502a677c1597c07f9f74f0137996f49"},"schema_version":"1.0","source":{"id":"2506.15710","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.15710","created_at":"2026-07-05T11:23:50Z"},{"alias_kind":"arxiv_version","alias_value":"2506.15710v1","created_at":"2026-07-05T11:23:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15710","created_at":"2026-07-05T11:23:50Z"},{"alias_kind":"pith_short_12","alias_value":"4K5Z7M56SU67","created_at":"2026-07-05T11:23:50Z"},{"alias_kind":"pith_short_16","alias_value":"4K5Z7M56SU67IRBV","created_at":"2026-07-05T11:23:50Z"},{"alias_kind":"pith_short_8","alias_value":"4K5Z7M56","created_at":"2026-07-05T11:23:50Z"}],"graph_snapshots":[{"event_id":"sha256:c1a612d1346192bf57a3cecfd3d1cd3e801d698d5676fc793aacd1b60d6db352","target":"graph","created_at":"2026-07-05T11:23:50Z","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/2506.15710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has become a powerful approach for improving the reasoning capabilities of large language models (LLMs), as evidenced by recent successes such as OpenAI's o1 and Deepseek-R1. However, applying RL at scale remains intimidatingly resource-intensive, requiring multiple model copies and extensive GPU workloads. On the other hand, while being powerful, recent studies suggest that RL does not fundamentally endow models with new knowledge; rather, it primarily reshapes the model's output distribution to activate reasoning capabilities latent in the base model. Building on ","authors_text":"Jiawei Han, Minhao Jiang, Siru Ouyang, Xinyu Zhu, Yu Meng, Zilin Xiao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T17:57:08Z","title":"RAST: Reasoning Activation in LLMs via Small-model Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15710","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":"sha256:647638a50b89daeb558b3e4138a9d6d7e5dc8d41be546e3195cf623474a3d8df","target":"record","created_at":"2026-07-05T11:23:50Z","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":"d57280a51961f0ebbab12d88ac2722ae50815c48b52103178f7bc3dfb39645dc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T17:57:08Z","title_canon_sha256":"4441e90ae07a9f1889f723c47aebcbda9502a677c1597c07f9f74f0137996f49"},"schema_version":"1.0","source":{"id":"2506.15710","kind":"arxiv","version":1}},"canonical_sha256":"e2bb9fb3be953df4443580cc7d7bb817893a16e54991f4567e9bff059f528c67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2bb9fb3be953df4443580cc7d7bb817893a16e54991f4567e9bff059f528c67","first_computed_at":"2026-07-05T11:23:50.840004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:50.840004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xdMG/lioE9CXanXN3aZkSPb/5Lm5E+CCqo2qn2zvQ48IE+4sNiNVbTkfvQ4ktNCdK7+sNA3unrZuLZ0XaRAeCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:50.840519Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.15710","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:647638a50b89daeb558b3e4138a9d6d7e5dc8d41be546e3195cf623474a3d8df","sha256:c1a612d1346192bf57a3cecfd3d1cd3e801d698d5676fc793aacd1b60d6db352"],"state_sha256":"d861eac335df517fc57f6cb25426f4ebb93afbb007a4c9537136a4612f8fbba4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YO0HV3ynK1MvxrS+wixqQ64S5BB5cmoAnzmKiOlT69MgS9997dQrH9ktsbxMrDpcQ3EbVpZGfBAnqEstMt0oBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:28:38.451030Z","bundle_sha256":"22d17f29727788dab86e51b95d312dfa86379daabcc17ccd7394bee7ef48c8fb"}}