{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2MUWKNKQINW3MG77QFMCV7ZJET","short_pith_number":"pith:2MUWKNKQ","canonical_record":{"source":{"id":"2508.02150","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-04T07:48:59Z","cross_cats_sorted":[],"title_canon_sha256":"f2030c0e3af6fb02c9db654194b98b0d1b9ed558b52ae4799c04e07d997dd8de","abstract_canon_sha256":"3c222014e8ee630961d52f71ec8d35374b026b5d49c6f69cbca401bcbbffb901"},"schema_version":"1.0"},"canonical_sha256":"d329653550436db61bff81582aff2924c4626dc689e8b390b63df9ff854c256d","source":{"kind":"arxiv","id":"2508.02150","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.02150","created_at":"2026-07-05T11:48:09Z"},{"alias_kind":"arxiv_version","alias_value":"2508.02150v1","created_at":"2026-07-05T11:48:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02150","created_at":"2026-07-05T11:48:09Z"},{"alias_kind":"pith_short_12","alias_value":"2MUWKNKQINW3","created_at":"2026-07-05T11:48:09Z"},{"alias_kind":"pith_short_16","alias_value":"2MUWKNKQINW3MG77","created_at":"2026-07-05T11:48:09Z"},{"alias_kind":"pith_short_8","alias_value":"2MUWKNKQ","created_at":"2026-07-05T11:48:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2MUWKNKQINW3MG77QFMCV7ZJET","target":"record","payload":{"canonical_record":{"source":{"id":"2508.02150","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-04T07:48:59Z","cross_cats_sorted":[],"title_canon_sha256":"f2030c0e3af6fb02c9db654194b98b0d1b9ed558b52ae4799c04e07d997dd8de","abstract_canon_sha256":"3c222014e8ee630961d52f71ec8d35374b026b5d49c6f69cbca401bcbbffb901"},"schema_version":"1.0"},"canonical_sha256":"d329653550436db61bff81582aff2924c4626dc689e8b390b63df9ff854c256d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:09.256820Z","signature_b64":"YyaPjC3kWGZaMHPQq1FDIkVl4pm/Sbc7jSbWWeavoGPAwYlJpZhJuWpkOM4HjdprqiEu3pdHE2F1QngGTZ0+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d329653550436db61bff81582aff2924c4626dc689e8b390b63df9ff854c256d","last_reissued_at":"2026-07-05T11:48:09.256287Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:09.256287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.02150","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":"2026-07-05T11:48:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"digLRXIo9EcaFFbz/Wnuvs6cnoSfqyG4BdcoAnnP6lBjoMb2XGlc8imi1MFlzRNaJpNeDA3at/d0Bl+CmVmwDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T01:11:34.136497Z"},"content_sha256":"6f083f6ea99b6456412692c21d798c97e203e29a816249347050ce431213f5c0","schema_version":"1.0","event_id":"sha256:6f083f6ea99b6456412692c21d798c97e203e29a816249347050ce431213f5c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2MUWKNKQINW3MG77QFMCV7ZJET","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models' Instruction Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bowei Zhang, Fei Yu, Jiaqing Liang, Jie Zeng, Qianyu He, Qingyu Ren, Weikang Zhou, Yanghua Xiao, Zeye Sun","submitted_at":"2025-08-04T07:48:59Z","abstract_excerpt":"Reasoning models excel in complex problem solving but exhibit a concerning trade off between reasoning capabilities and instruction following abilities. Existing approaches for improving instruction following rely on stronger external models, creating methodological bottlenecks and practical limitations including increased costs and accessibility constraints. We propose a self-supervised RL framework that leverages reasoning models' own internal signals to improve instruction following capabilities without external supervision. Extensive experiments demonstrate that our framework significantly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02150","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/2508.02150/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":"2026-07-05T11:48:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"scz7ZXxxKyW0x6uc9JhfZN7QcHiKR96ckel761ux3S3toYThvwMmpYoxNg6il2bWChRdcFRyHBaj7wfwf5xwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T01:11:34.137328Z"},"content_sha256":"44e31b29ef51c0ab53f6fbc87d3431e5a79fd0163f8f4b9e7539b46f9a5904b9","schema_version":"1.0","event_id":"sha256:44e31b29ef51c0ab53f6fbc87d3431e5a79fd0163f8f4b9e7539b46f9a5904b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2MUWKNKQINW3MG77QFMCV7ZJET/bundle.json","state_url":"https://pith.science/pith/2MUWKNKQINW3MG77QFMCV7ZJET/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2MUWKNKQINW3MG77QFMCV7ZJET/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":"2026-08-17T01:11:34Z","links":{"resolver":"https://pith.science/pith/2MUWKNKQINW3MG77QFMCV7ZJET","bundle":"https://pith.science/pith/2MUWKNKQINW3MG77QFMCV7ZJET/bundle.json","state":"https://pith.science/pith/2MUWKNKQINW3MG77QFMCV7ZJET/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2MUWKNKQINW3MG77QFMCV7ZJET/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2MUWKNKQINW3MG77QFMCV7ZJET","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":"3c222014e8ee630961d52f71ec8d35374b026b5d49c6f69cbca401bcbbffb901","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-04T07:48:59Z","title_canon_sha256":"f2030c0e3af6fb02c9db654194b98b0d1b9ed558b52ae4799c04e07d997dd8de"},"schema_version":"1.0","source":{"id":"2508.02150","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.02150","created_at":"2026-07-05T11:48:09Z"},{"alias_kind":"arxiv_version","alias_value":"2508.02150v1","created_at":"2026-07-05T11:48:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02150","created_at":"2026-07-05T11:48:09Z"},{"alias_kind":"pith_short_12","alias_value":"2MUWKNKQINW3","created_at":"2026-07-05T11:48:09Z"},{"alias_kind":"pith_short_16","alias_value":"2MUWKNKQINW3MG77","created_at":"2026-07-05T11:48:09Z"},{"alias_kind":"pith_short_8","alias_value":"2MUWKNKQ","created_at":"2026-07-05T11:48:09Z"}],"graph_snapshots":[{"event_id":"sha256:44e31b29ef51c0ab53f6fbc87d3431e5a79fd0163f8f4b9e7539b46f9a5904b9","target":"graph","created_at":"2026-07-05T11:48:09Z","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/2508.02150/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reasoning models excel in complex problem solving but exhibit a concerning trade off between reasoning capabilities and instruction following abilities. Existing approaches for improving instruction following rely on stronger external models, creating methodological bottlenecks and practical limitations including increased costs and accessibility constraints. We propose a self-supervised RL framework that leverages reasoning models' own internal signals to improve instruction following capabilities without external supervision. Extensive experiments demonstrate that our framework significantly","authors_text":"Bowei Zhang, Fei Yu, Jiaqing Liang, Jie Zeng, Qianyu He, Qingyu Ren, Weikang Zhou, Yanghua Xiao, Zeye Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-04T07:48:59Z","title":"Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models' Instruction Following"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02150","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":"sha256:6f083f6ea99b6456412692c21d798c97e203e29a816249347050ce431213f5c0","target":"record","created_at":"2026-07-05T11:48:09Z","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":"3c222014e8ee630961d52f71ec8d35374b026b5d49c6f69cbca401bcbbffb901","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-04T07:48:59Z","title_canon_sha256":"f2030c0e3af6fb02c9db654194b98b0d1b9ed558b52ae4799c04e07d997dd8de"},"schema_version":"1.0","source":{"id":"2508.02150","kind":"arxiv","version":1}},"canonical_sha256":"d329653550436db61bff81582aff2924c4626dc689e8b390b63df9ff854c256d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d329653550436db61bff81582aff2924c4626dc689e8b390b63df9ff854c256d","first_computed_at":"2026-07-05T11:48:09.256287Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:09.256287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YyaPjC3kWGZaMHPQq1FDIkVl4pm/Sbc7jSbWWeavoGPAwYlJpZhJuWpkOM4HjdprqiEu3pdHE2F1QngGTZ0+DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:09.256820Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.02150","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f083f6ea99b6456412692c21d798c97e203e29a816249347050ce431213f5c0","sha256:44e31b29ef51c0ab53f6fbc87d3431e5a79fd0163f8f4b9e7539b46f9a5904b9"],"state_sha256":"9c7e58d221fff5d659d8422c3e429c945140dafc954bc77ed5cc570f4eb7fdf7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1yT9yK+QN/VEamXjysWDwnFwF9gZr9HQHFjPXDG+lclSpamxuXjVL5eftsLa6okSUJDnbzusYkC77mHjN/eWDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T01:11:34.144410Z","bundle_sha256":"6b6d1cb0a0211b6a527d13b6394ba7073615b56d4b4700ab2ecdbcd90485244f"}}