{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AWFB5HYH2YYC2MQN3OEOFLGKHN","short_pith_number":"pith:AWFB5HYH","canonical_record":{"source":{"id":"2504.00829","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T14:18:38Z","cross_cats_sorted":[],"title_canon_sha256":"a9aae1db360d183cdd688272d390c6d9c132e90dce2d3ccc12315fc93fb13215","abstract_canon_sha256":"fedde771d39d5a3143962f6b4651b85c0349f15561b28cc4b1e231ea0e5fc55f"},"schema_version":"1.0"},"canonical_sha256":"058a1e9f07d6302d320ddb88e2acca3b61f74756d535d84cc0dbe7eab32029db","source":{"kind":"arxiv","id":"2504.00829","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.00829","created_at":"2026-07-05T10:42:51Z"},{"alias_kind":"arxiv_version","alias_value":"2504.00829v1","created_at":"2026-07-05T10:42:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00829","created_at":"2026-07-05T10:42:51Z"},{"alias_kind":"pith_short_12","alias_value":"AWFB5HYH2YYC","created_at":"2026-07-05T10:42:51Z"},{"alias_kind":"pith_short_16","alias_value":"AWFB5HYH2YYC2MQN","created_at":"2026-07-05T10:42:51Z"},{"alias_kind":"pith_short_8","alias_value":"AWFB5HYH","created_at":"2026-07-05T10:42:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AWFB5HYH2YYC2MQN3OEOFLGKHN","target":"record","payload":{"canonical_record":{"source":{"id":"2504.00829","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T14:18:38Z","cross_cats_sorted":[],"title_canon_sha256":"a9aae1db360d183cdd688272d390c6d9c132e90dce2d3ccc12315fc93fb13215","abstract_canon_sha256":"fedde771d39d5a3143962f6b4651b85c0349f15561b28cc4b1e231ea0e5fc55f"},"schema_version":"1.0"},"canonical_sha256":"058a1e9f07d6302d320ddb88e2acca3b61f74756d535d84cc0dbe7eab32029db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:51.051216Z","signature_b64":"qQh52DXAJWTzU6igLGlv4RgNYywDZquRqQQeXfpUB+E6njLa3y3xBo1arhQ+HNsoOkY/tlmjxCfzR7Pk4htkDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"058a1e9f07d6302d320ddb88e2acca3b61f74756d535d84cc0dbe7eab32029db","last_reissued_at":"2026-07-05T10:42:51.050650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:51.050650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.00829","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":"2026-07-05T10:42:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MCaJvK6H+2GX42dBcDHOBWwaE15Env+gVRNExEY8nuI/xt6+0odCi8T6jdQdLD/nSjIoYlSb8xrgn5AfMbzrCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:07:06.047750Z"},"content_sha256":"b9a14fc449efaee7bb253ba12350d6f3997067983affbff09233a5f1bad14b2b","schema_version":"1.0","event_id":"sha256:b9a14fc449efaee7bb253ba12350d6f3997067983affbff09233a5f1bad14b2b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AWFB5HYH2YYC2MQN3OEOFLGKHN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Han Zhao, Haotian Wang, Shuaiting Chen, Sitong Zhao, Xiangang Li, Xiaoyu Tian, Yiping Peng, Yunjie Ji","submitted_at":"2025-04-01T14:18:38Z","abstract_excerpt":"Enhancing the reasoning capabilities of Large Language Models (LLMs) with efficiency and scalability remains a fundamental challenge in artificial intelligence research. This paper presents a rigorous experimental investigation into how difficulty-aware staged reinforcement learning (RL) strategies can substantially improve LLM reasoning performance. Through systematic analysis, we demonstrate that strategically selecting training data according to well-defined difficulty levels markedly enhances RL optimization. Moreover, we introduce a staged training methodology, progressively exposing mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00829","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/2504.00829/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":"2026-07-05T10:42:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OYSpct2bgyc0dWMPl0udUcLacUYeWJ2vyBUlIHtzlOa/fSGNMyAGjJLTCMb9a1HBWvxIEiYzokf1fHnlICBZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:07:06.048114Z"},"content_sha256":"1c4292a68d159e0294e37cbef978548127f07d52762ca5ee9a6980230766a17b","schema_version":"1.0","event_id":"sha256:1c4292a68d159e0294e37cbef978548127f07d52762ca5ee9a6980230766a17b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AWFB5HYH2YYC2MQN3OEOFLGKHN/bundle.json","state_url":"https://pith.science/pith/AWFB5HYH2YYC2MQN3OEOFLGKHN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AWFB5HYH2YYC2MQN3OEOFLGKHN/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":"2026-07-07T10:07:06Z","links":{"resolver":"https://pith.science/pith/AWFB5HYH2YYC2MQN3OEOFLGKHN","bundle":"https://pith.science/pith/AWFB5HYH2YYC2MQN3OEOFLGKHN/bundle.json","state":"https://pith.science/pith/AWFB5HYH2YYC2MQN3OEOFLGKHN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AWFB5HYH2YYC2MQN3OEOFLGKHN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AWFB5HYH2YYC2MQN3OEOFLGKHN","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":"fedde771d39d5a3143962f6b4651b85c0349f15561b28cc4b1e231ea0e5fc55f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T14:18:38Z","title_canon_sha256":"a9aae1db360d183cdd688272d390c6d9c132e90dce2d3ccc12315fc93fb13215"},"schema_version":"1.0","source":{"id":"2504.00829","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.00829","created_at":"2026-07-05T10:42:51Z"},{"alias_kind":"arxiv_version","alias_value":"2504.00829v1","created_at":"2026-07-05T10:42:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00829","created_at":"2026-07-05T10:42:51Z"},{"alias_kind":"pith_short_12","alias_value":"AWFB5HYH2YYC","created_at":"2026-07-05T10:42:51Z"},{"alias_kind":"pith_short_16","alias_value":"AWFB5HYH2YYC2MQN","created_at":"2026-07-05T10:42:51Z"},{"alias_kind":"pith_short_8","alias_value":"AWFB5HYH","created_at":"2026-07-05T10:42:51Z"}],"graph_snapshots":[{"event_id":"sha256:1c4292a68d159e0294e37cbef978548127f07d52762ca5ee9a6980230766a17b","target":"graph","created_at":"2026-07-05T10:42:51Z","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/2504.00829/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Enhancing the reasoning capabilities of Large Language Models (LLMs) with efficiency and scalability remains a fundamental challenge in artificial intelligence research. This paper presents a rigorous experimental investigation into how difficulty-aware staged reinforcement learning (RL) strategies can substantially improve LLM reasoning performance. Through systematic analysis, we demonstrate that strategically selecting training data according to well-defined difficulty levels markedly enhances RL optimization. Moreover, we introduce a staged training methodology, progressively exposing mode","authors_text":"Han Zhao, Haotian Wang, Shuaiting Chen, Sitong Zhao, Xiangang Li, Xiaoyu Tian, Yiping Peng, Yunjie Ji","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T14:18:38Z","title":"How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00829","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:b9a14fc449efaee7bb253ba12350d6f3997067983affbff09233a5f1bad14b2b","target":"record","created_at":"2026-07-05T10:42:51Z","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":"fedde771d39d5a3143962f6b4651b85c0349f15561b28cc4b1e231ea0e5fc55f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T14:18:38Z","title_canon_sha256":"a9aae1db360d183cdd688272d390c6d9c132e90dce2d3ccc12315fc93fb13215"},"schema_version":"1.0","source":{"id":"2504.00829","kind":"arxiv","version":1}},"canonical_sha256":"058a1e9f07d6302d320ddb88e2acca3b61f74756d535d84cc0dbe7eab32029db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"058a1e9f07d6302d320ddb88e2acca3b61f74756d535d84cc0dbe7eab32029db","first_computed_at":"2026-07-05T10:42:51.050650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:42:51.050650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qQh52DXAJWTzU6igLGlv4RgNYywDZquRqQQeXfpUB+E6njLa3y3xBo1arhQ+HNsoOkY/tlmjxCfzR7Pk4htkDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:42:51.051216Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.00829","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9a14fc449efaee7bb253ba12350d6f3997067983affbff09233a5f1bad14b2b","sha256:1c4292a68d159e0294e37cbef978548127f07d52762ca5ee9a6980230766a17b"],"state_sha256":"8c6157b36b4efd496e20e1ef1f3af000647eaaf7259504425cba2c8877eca07a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6hMUL2jAvgGXc3P5m8UCxywfx1DQ3oZUb6yEmLiW7RxqfGE3gFLszJejgAZOF05eDlWJ2L4Zwf3Td+lSk5IbBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:07:06.050032Z","bundle_sha256":"84e4ff7c1573e13e1cf09bb3fd5e8aa5cc90042329b90415caf13346992af5d3"}}