{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4B26NHNVNB25IUT3PKGJ7VRZRB","short_pith_number":"pith:4B26NHNV","canonical_record":{"source":{"id":"2508.01604","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-03T05:41:36Z","cross_cats_sorted":[],"title_canon_sha256":"1b9e10806f6eaa538c3a4390bf1078976d257dacdf5362a436c92a9c3f6c0599","abstract_canon_sha256":"49f84821cde76e3b9108c924e430f5d51d72246aa7eb3c3848df3b8f4f04311a"},"schema_version":"1.0"},"canonical_sha256":"e075e69db56875d4527b7a8c9fd639884403eb72197c41e4b6544f50e8b80480","source":{"kind":"arxiv","id":"2508.01604","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.01604","created_at":"2026-07-05T11:47:42Z"},{"alias_kind":"arxiv_version","alias_value":"2508.01604v1","created_at":"2026-07-05T11:47:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01604","created_at":"2026-07-05T11:47:42Z"},{"alias_kind":"pith_short_12","alias_value":"4B26NHNVNB25","created_at":"2026-07-05T11:47:42Z"},{"alias_kind":"pith_short_16","alias_value":"4B26NHNVNB25IUT3","created_at":"2026-07-05T11:47:42Z"},{"alias_kind":"pith_short_8","alias_value":"4B26NHNV","created_at":"2026-07-05T11:47:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4B26NHNVNB25IUT3PKGJ7VRZRB","target":"record","payload":{"canonical_record":{"source":{"id":"2508.01604","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-03T05:41:36Z","cross_cats_sorted":[],"title_canon_sha256":"1b9e10806f6eaa538c3a4390bf1078976d257dacdf5362a436c92a9c3f6c0599","abstract_canon_sha256":"49f84821cde76e3b9108c924e430f5d51d72246aa7eb3c3848df3b8f4f04311a"},"schema_version":"1.0"},"canonical_sha256":"e075e69db56875d4527b7a8c9fd639884403eb72197c41e4b6544f50e8b80480","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:42.081492Z","signature_b64":"RKdnk/SB2JIz9V8GMq3UaVLNzcoKBGrfhXbaCyJ5Sy+ng8ojhwG7W/06hgKbuV6M206Pn9UbwlYuquMdWF0dBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e075e69db56875d4527b7a8c9fd639884403eb72197c41e4b6544f50e8b80480","last_reissued_at":"2026-07-05T11:47:42.081000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:42.081000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.01604","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":"2026-07-05T11:47:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RObPvtEGzRKiGpe4YRSwHZSz7vPkcLdLYDpI+uRd1dvc85LEuDZN39nTRR5yxUOe56wPETS1jh1Xxt1G+DINDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T01:42:54.704275Z"},"content_sha256":"329df0b22ab18f03a26f65ac3bde8c759e1f0619f7d550b8929e9076b929a4cc","schema_version":"1.0","event_id":"sha256:329df0b22ab18f03a26f65ac3bde8c759e1f0619f7d550b8929e9076b929a4cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4B26NHNVNB25IUT3PKGJ7VRZRB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Math Reasoning in Small-sized LLMs via Preview Difficulty-Aware Intervention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"JoyJiaoW, Xinhan Di","submitted_at":"2025-08-03T05:41:36Z","abstract_excerpt":"Reinforcement learning scaling enhances the reasoning capabilities of large language models, with reinforcement learning serving as the key technique to draw out complex reasoning. However, key technical details of state-of-the-art reasoning LLMs, such as those in the OpenAI O series, Claude 3 series, DeepMind's Gemini 2.5 series, and Grok 3 series, remain undisclosed, making it difficult for the research community to replicate their reinforcement learning training results. Therefore, we start our study from an Early Preview Reinforcement Learning (EPRLI) algorithm built on the open-source GRP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01604","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/2508.01604/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":"2026-07-05T11:47:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bHzd5NdLZ38M8i2nwxCzoLViahvl3nfrWTN1qPVrt+nfTwmMvqXzuVBXykkHASySygPoVnEQHQ1vxe1WpuTZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T01:42:54.704812Z"},"content_sha256":"99d7ccce374671c8a6d58cb8645524d32d2e61f581401df2af1a1f741c3c24e4","schema_version":"1.0","event_id":"sha256:99d7ccce374671c8a6d58cb8645524d32d2e61f581401df2af1a1f741c3c24e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4B26NHNVNB25IUT3PKGJ7VRZRB/bundle.json","state_url":"https://pith.science/pith/4B26NHNVNB25IUT3PKGJ7VRZRB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4B26NHNVNB25IUT3PKGJ7VRZRB/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":"2026-08-21T01:42:54Z","links":{"resolver":"https://pith.science/pith/4B26NHNVNB25IUT3PKGJ7VRZRB","bundle":"https://pith.science/pith/4B26NHNVNB25IUT3PKGJ7VRZRB/bundle.json","state":"https://pith.science/pith/4B26NHNVNB25IUT3PKGJ7VRZRB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4B26NHNVNB25IUT3PKGJ7VRZRB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4B26NHNVNB25IUT3PKGJ7VRZRB","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":"49f84821cde76e3b9108c924e430f5d51d72246aa7eb3c3848df3b8f4f04311a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-03T05:41:36Z","title_canon_sha256":"1b9e10806f6eaa538c3a4390bf1078976d257dacdf5362a436c92a9c3f6c0599"},"schema_version":"1.0","source":{"id":"2508.01604","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.01604","created_at":"2026-07-05T11:47:42Z"},{"alias_kind":"arxiv_version","alias_value":"2508.01604v1","created_at":"2026-07-05T11:47:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01604","created_at":"2026-07-05T11:47:42Z"},{"alias_kind":"pith_short_12","alias_value":"4B26NHNVNB25","created_at":"2026-07-05T11:47:42Z"},{"alias_kind":"pith_short_16","alias_value":"4B26NHNVNB25IUT3","created_at":"2026-07-05T11:47:42Z"},{"alias_kind":"pith_short_8","alias_value":"4B26NHNV","created_at":"2026-07-05T11:47:42Z"}],"graph_snapshots":[{"event_id":"sha256:99d7ccce374671c8a6d58cb8645524d32d2e61f581401df2af1a1f741c3c24e4","target":"graph","created_at":"2026-07-05T11:47:42Z","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/2508.01604/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning scaling enhances the reasoning capabilities of large language models, with reinforcement learning serving as the key technique to draw out complex reasoning. However, key technical details of state-of-the-art reasoning LLMs, such as those in the OpenAI O series, Claude 3 series, DeepMind's Gemini 2.5 series, and Grok 3 series, remain undisclosed, making it difficult for the research community to replicate their reinforcement learning training results. Therefore, we start our study from an Early Preview Reinforcement Learning (EPRLI) algorithm built on the open-source GRP","authors_text":"JoyJiaoW, Xinhan Di","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-03T05:41:36Z","title":"Enhancing Math Reasoning in Small-sized LLMs via Preview Difficulty-Aware Intervention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01604","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":"sha256:329df0b22ab18f03a26f65ac3bde8c759e1f0619f7d550b8929e9076b929a4cc","target":"record","created_at":"2026-07-05T11:47:42Z","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":"49f84821cde76e3b9108c924e430f5d51d72246aa7eb3c3848df3b8f4f04311a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-03T05:41:36Z","title_canon_sha256":"1b9e10806f6eaa538c3a4390bf1078976d257dacdf5362a436c92a9c3f6c0599"},"schema_version":"1.0","source":{"id":"2508.01604","kind":"arxiv","version":1}},"canonical_sha256":"e075e69db56875d4527b7a8c9fd639884403eb72197c41e4b6544f50e8b80480","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e075e69db56875d4527b7a8c9fd639884403eb72197c41e4b6544f50e8b80480","first_computed_at":"2026-07-05T11:47:42.081000Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:42.081000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RKdnk/SB2JIz9V8GMq3UaVLNzcoKBGrfhXbaCyJ5Sy+ng8ojhwG7W/06hgKbuV6M206Pn9UbwlYuquMdWF0dBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:42.081492Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.01604","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:329df0b22ab18f03a26f65ac3bde8c759e1f0619f7d550b8929e9076b929a4cc","sha256:99d7ccce374671c8a6d58cb8645524d32d2e61f581401df2af1a1f741c3c24e4"],"state_sha256":"8be1edc474e711a53c59253a4209d861f4661b9ae1dbfc32d8617c3b04475f84"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dUdItXQqp8HchAsjPMq3GRC5PQ/AzK/L1Rw9VYAm38IiOdgUlcf/RSstI1/VO8xpjU0jFZq2tUIACeI9k2ZlAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T01:42:54.710290Z","bundle_sha256":"787113675b4e58c2a8ab94936d1dcef3a8e9f99aa1312d5064ce615f6a387b9f"}}