{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CB5VYPTNBLATOWOFLLGCAWB72N","short_pith_number":"pith:CB5VYPTN","canonical_record":{"source":{"id":"2505.07686","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T15:50:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3f5a187eb0fa036d92d430b8e2ddbe6ba5d3fd01a3437033341b094f490eb47b","abstract_canon_sha256":"e06991f835478ab215467373a201b5850f0e54c2f0eee7b53c31c0f7efab8e29"},"schema_version":"1.0"},"canonical_sha256":"107b5c3e6d0ac13759c55acc20583fd36c841be29a97ed2810c33df6e769f129","source":{"kind":"arxiv","id":"2505.07686","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07686","created_at":"2026-07-05T11:04:22Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07686v2","created_at":"2026-07-05T11:04:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07686","created_at":"2026-07-05T11:04:22Z"},{"alias_kind":"pith_short_12","alias_value":"CB5VYPTNBLAT","created_at":"2026-07-05T11:04:22Z"},{"alias_kind":"pith_short_16","alias_value":"CB5VYPTNBLATOWOF","created_at":"2026-07-05T11:04:22Z"},{"alias_kind":"pith_short_8","alias_value":"CB5VYPTN","created_at":"2026-07-05T11:04:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CB5VYPTNBLATOWOFLLGCAWB72N","target":"record","payload":{"canonical_record":{"source":{"id":"2505.07686","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T15:50:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3f5a187eb0fa036d92d430b8e2ddbe6ba5d3fd01a3437033341b094f490eb47b","abstract_canon_sha256":"e06991f835478ab215467373a201b5850f0e54c2f0eee7b53c31c0f7efab8e29"},"schema_version":"1.0"},"canonical_sha256":"107b5c3e6d0ac13759c55acc20583fd36c841be29a97ed2810c33df6e769f129","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:22.325849Z","signature_b64":"qsNErJlN3R99Z+EoJaroQiOqY71HWs8iPL9rtywNriIGml8Nprtp5QWrFD1JJowaQSGUd4TtIhcN3AFUwqkIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"107b5c3e6d0ac13759c55acc20583fd36c841be29a97ed2810c33df6e769f129","last_reissued_at":"2026-07-05T11:04:22.325330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:22.325330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.07686","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:04:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xqqp7KVf765yoXoQYBAxeabWU6KHRPCIx/IRYzZSCGKXNeuZJkKbJg9ZMySj/vKNe2+euY2fSADh0DyhvFVrAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T11:45:05.263916Z"},"content_sha256":"3a61c6d813ab73b806cb1415c35aa8906007e756146e17b5194d31dcb34ef98f","schema_version":"1.0","event_id":"sha256:3a61c6d813ab73b806cb1415c35aa8906007e756146e17b5194d31dcb34ef98f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CB5VYPTNBLATOWOFLLGCAWB72N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Chenxu Yang, Muzhi Dai, Qingyi Si","submitted_at":"2025-05-12T15:50:44Z","abstract_excerpt":"As Test-Time Scaling emerges as an active research focus in the large language model community, advanced post-training methods increasingly emphasize extending chain-of-thought (CoT) generation length, thereby enhancing reasoning capabilities to approach Deepseek R1-like reasoning models. However, recent studies reveal that reasoning models (even Qwen3) consistently exhibit excessive thought redundancy in CoT generation. This overthinking issue arises from the inherent limitations of conventional outcome-reward reinforcement learning, which systematically overlooks the regulation of intermedia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07686","kind":"arxiv","version":2},"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/2505.07686/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":"2026-07-05T11:04:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3iJB/otwd4R0i02KvZOip5NBOFZ3rZRdf9VABTxD0MEXIHv+FJ2DtxPHvRxA8pFcTrYevC+gVdo7uEurG5/VDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T11:45:05.264297Z"},"content_sha256":"472fba9fcd912a78652f63520f0803a280e97e76ace368662dcb4f6c2716b1ee","schema_version":"1.0","event_id":"sha256:472fba9fcd912a78652f63520f0803a280e97e76ace368662dcb4f6c2716b1ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CB5VYPTNBLATOWOFLLGCAWB72N/bundle.json","state_url":"https://pith.science/pith/CB5VYPTNBLATOWOFLLGCAWB72N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CB5VYPTNBLATOWOFLLGCAWB72N/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":"2026-07-06T11:45:05Z","links":{"resolver":"https://pith.science/pith/CB5VYPTNBLATOWOFLLGCAWB72N","bundle":"https://pith.science/pith/CB5VYPTNBLATOWOFLLGCAWB72N/bundle.json","state":"https://pith.science/pith/CB5VYPTNBLATOWOFLLGCAWB72N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CB5VYPTNBLATOWOFLLGCAWB72N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CB5VYPTNBLATOWOFLLGCAWB72N","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":"e06991f835478ab215467373a201b5850f0e54c2f0eee7b53c31c0f7efab8e29","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T15:50:44Z","title_canon_sha256":"3f5a187eb0fa036d92d430b8e2ddbe6ba5d3fd01a3437033341b094f490eb47b"},"schema_version":"1.0","source":{"id":"2505.07686","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07686","created_at":"2026-07-05T11:04:22Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07686v2","created_at":"2026-07-05T11:04:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07686","created_at":"2026-07-05T11:04:22Z"},{"alias_kind":"pith_short_12","alias_value":"CB5VYPTNBLAT","created_at":"2026-07-05T11:04:22Z"},{"alias_kind":"pith_short_16","alias_value":"CB5VYPTNBLATOWOF","created_at":"2026-07-05T11:04:22Z"},{"alias_kind":"pith_short_8","alias_value":"CB5VYPTN","created_at":"2026-07-05T11:04:22Z"}],"graph_snapshots":[{"event_id":"sha256:472fba9fcd912a78652f63520f0803a280e97e76ace368662dcb4f6c2716b1ee","target":"graph","created_at":"2026-07-05T11:04:22Z","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/2505.07686/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As Test-Time Scaling emerges as an active research focus in the large language model community, advanced post-training methods increasingly emphasize extending chain-of-thought (CoT) generation length, thereby enhancing reasoning capabilities to approach Deepseek R1-like reasoning models. However, recent studies reveal that reasoning models (even Qwen3) consistently exhibit excessive thought redundancy in CoT generation. This overthinking issue arises from the inherent limitations of conventional outcome-reward reinforcement learning, which systematically overlooks the regulation of intermedia","authors_text":"Chenxu Yang, Muzhi Dai, Qingyi Si","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T15:50:44Z","title":"S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07686","kind":"arxiv","version":2},"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":"sha256:3a61c6d813ab73b806cb1415c35aa8906007e756146e17b5194d31dcb34ef98f","target":"record","created_at":"2026-07-05T11:04:22Z","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":"e06991f835478ab215467373a201b5850f0e54c2f0eee7b53c31c0f7efab8e29","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T15:50:44Z","title_canon_sha256":"3f5a187eb0fa036d92d430b8e2ddbe6ba5d3fd01a3437033341b094f490eb47b"},"schema_version":"1.0","source":{"id":"2505.07686","kind":"arxiv","version":2}},"canonical_sha256":"107b5c3e6d0ac13759c55acc20583fd36c841be29a97ed2810c33df6e769f129","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"107b5c3e6d0ac13759c55acc20583fd36c841be29a97ed2810c33df6e769f129","first_computed_at":"2026-07-05T11:04:22.325330Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:22.325330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qsNErJlN3R99Z+EoJaroQiOqY71HWs8iPL9rtywNriIGml8Nprtp5QWrFD1JJowaQSGUd4TtIhcN3AFUwqkIDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:22.325849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07686","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a61c6d813ab73b806cb1415c35aa8906007e756146e17b5194d31dcb34ef98f","sha256:472fba9fcd912a78652f63520f0803a280e97e76ace368662dcb4f6c2716b1ee"],"state_sha256":"2c697cfd599bda20ed65173c76532642780f60624fa459539a6219a1454ca7bd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XU32MC/34rPKfv926oKvsxDFGvbXWqtX/2i+Dh59FUcnNeM5C0PfGzlmt9ZY6evvs6GSXKe0lR+8+o4SYKRtDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T11:45:05.266269Z","bundle_sha256":"62b6ff96991c7222959ff443539aed66eaad165d21815f9bb6ae343c8014c341"}}