{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HCLAGTVB6IH3XULPFPF7XIDS4X","short_pith_number":"pith:HCLAGTVB","canonical_record":{"source":{"id":"2603.09803","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-10T15:33:07Z","cross_cats_sorted":[],"title_canon_sha256":"33b54919422f9415d7a6d3257c8a5be70cf8c87c0664d3293a63daea40df427a","abstract_canon_sha256":"574bfdc58f79114205ff942d87f45f7b601afdc6b2f2169df0fe89a57b6cc282"},"schema_version":"1.0"},"canonical_sha256":"3896034ea1f20fbbd16f2bcbfba072e5e97e43ec025724b97ba647ac119b0a88","source":{"kind":"arxiv","id":"2603.09803","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.09803","created_at":"2026-06-04T01:08:47Z"},{"alias_kind":"arxiv_version","alias_value":"2603.09803v2","created_at":"2026-06-04T01:08:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.09803","created_at":"2026-06-04T01:08:47Z"},{"alias_kind":"pith_short_12","alias_value":"HCLAGTVB6IH3","created_at":"2026-06-04T01:08:47Z"},{"alias_kind":"pith_short_16","alias_value":"HCLAGTVB6IH3XULP","created_at":"2026-06-04T01:08:47Z"},{"alias_kind":"pith_short_8","alias_value":"HCLAGTVB","created_at":"2026-06-04T01:08:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HCLAGTVB6IH3XULPFPF7XIDS4X","target":"record","payload":{"canonical_record":{"source":{"id":"2603.09803","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-10T15:33:07Z","cross_cats_sorted":[],"title_canon_sha256":"33b54919422f9415d7a6d3257c8a5be70cf8c87c0664d3293a63daea40df427a","abstract_canon_sha256":"574bfdc58f79114205ff942d87f45f7b601afdc6b2f2169df0fe89a57b6cc282"},"schema_version":"1.0"},"canonical_sha256":"3896034ea1f20fbbd16f2bcbfba072e5e97e43ec025724b97ba647ac119b0a88","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:47.953583Z","signature_b64":"25s+OqFYwyXDeA1rTWE6LRgIXsG1DUs5iC87wnEpN4YQyVmf3uvXOq4vDR1b0sHohgwDjh8hjdx2bzEBq2XpCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3896034ea1f20fbbd16f2bcbfba072e5e97e43ec025724b97ba647ac119b0a88","last_reissued_at":"2026-06-04T01:08:47.953067Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:47.953067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.09803","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":"2026-06-04T01:08:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k1lXfygMrZIudeJQeDNYSBbZzHjbYIj8hklJrKRePfqUCLeO15Fkb5gl7GY87jyf3U2GWrpQ9aHiDLsi9O5CBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T08:27:39.828753Z"},"content_sha256":"46e6c7157409a5bcd1974e6f3f91dc11028ae21e8d7c411aac58079c2966a78f","schema_version":"1.0","event_id":"sha256:46e6c7157409a5bcd1974e6f3f91dc11028ae21e8d7c411aac58079c2966a78f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HCLAGTVB6IH3XULPFPF7XIDS4X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ao Xu, Deqing Yang, Hengrui Chen, Hongru Hou, Leiyu Pan, Minxuan Lv, Tiehua Mei, Zhenpeng Su","submitted_at":"2026-03-10T15:33:07Z","abstract_excerpt":"Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that arrive at correct answers by chance. We observe that \\emph{better reasoning makes better demonstrations}: high-quality solutions serve as more effective in-context examples than low-quality ones. We term this teaching ability \\textbf{Demonstration Utility}, and show that the policy model's own in-context learning ability provides an efficient way to measure it, yielding a quality signal termed \\textbf{Evidence Gai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.09803","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/2603.09803/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":"2026-06-04T01:08:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H5aa3CbMnRv5ntRD/vMksO+4xm+Je1NUxDBoiB/3lmCY/qbxVb+MT3djZ4H48/+uigy1ZL8RyYViP+zlIyAiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T08:27:39.829139Z"},"content_sha256":"fe45558e4ed8ea2ba62f868264c77f1cabd3473f5ded28aca682fab029a5748d","schema_version":"1.0","event_id":"sha256:fe45558e4ed8ea2ba62f868264c77f1cabd3473f5ded28aca682fab029a5748d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HCLAGTVB6IH3XULPFPF7XIDS4X/bundle.json","state_url":"https://pith.science/pith/HCLAGTVB6IH3XULPFPF7XIDS4X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HCLAGTVB6IH3XULPFPF7XIDS4X/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":"2026-06-05T08:27:39Z","links":{"resolver":"https://pith.science/pith/HCLAGTVB6IH3XULPFPF7XIDS4X","bundle":"https://pith.science/pith/HCLAGTVB6IH3XULPFPF7XIDS4X/bundle.json","state":"https://pith.science/pith/HCLAGTVB6IH3XULPFPF7XIDS4X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HCLAGTVB6IH3XULPFPF7XIDS4X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HCLAGTVB6IH3XULPFPF7XIDS4X","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":"574bfdc58f79114205ff942d87f45f7b601afdc6b2f2169df0fe89a57b6cc282","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-10T15:33:07Z","title_canon_sha256":"33b54919422f9415d7a6d3257c8a5be70cf8c87c0664d3293a63daea40df427a"},"schema_version":"1.0","source":{"id":"2603.09803","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.09803","created_at":"2026-06-04T01:08:47Z"},{"alias_kind":"arxiv_version","alias_value":"2603.09803v2","created_at":"2026-06-04T01:08:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.09803","created_at":"2026-06-04T01:08:47Z"},{"alias_kind":"pith_short_12","alias_value":"HCLAGTVB6IH3","created_at":"2026-06-04T01:08:47Z"},{"alias_kind":"pith_short_16","alias_value":"HCLAGTVB6IH3XULP","created_at":"2026-06-04T01:08:47Z"},{"alias_kind":"pith_short_8","alias_value":"HCLAGTVB","created_at":"2026-06-04T01:08:47Z"}],"graph_snapshots":[{"event_id":"sha256:fe45558e4ed8ea2ba62f868264c77f1cabd3473f5ded28aca682fab029a5748d","target":"graph","created_at":"2026-06-04T01:08:47Z","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/2603.09803/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that arrive at correct answers by chance. We observe that \\emph{better reasoning makes better demonstrations}: high-quality solutions serve as more effective in-context examples than low-quality ones. We term this teaching ability \\textbf{Demonstration Utility}, and show that the policy model's own in-context learning ability provides an efficient way to measure it, yielding a quality signal termed \\textbf{Evidence Gai","authors_text":"Ao Xu, Deqing Yang, Hengrui Chen, Hongru Hou, Leiyu Pan, Minxuan Lv, Tiehua Mei, Zhenpeng Su","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-10T15:33:07Z","title":"Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.09803","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":"sha256:46e6c7157409a5bcd1974e6f3f91dc11028ae21e8d7c411aac58079c2966a78f","target":"record","created_at":"2026-06-04T01:08:47Z","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":"574bfdc58f79114205ff942d87f45f7b601afdc6b2f2169df0fe89a57b6cc282","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-10T15:33:07Z","title_canon_sha256":"33b54919422f9415d7a6d3257c8a5be70cf8c87c0664d3293a63daea40df427a"},"schema_version":"1.0","source":{"id":"2603.09803","kind":"arxiv","version":2}},"canonical_sha256":"3896034ea1f20fbbd16f2bcbfba072e5e97e43ec025724b97ba647ac119b0a88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3896034ea1f20fbbd16f2bcbfba072e5e97e43ec025724b97ba647ac119b0a88","first_computed_at":"2026-06-04T01:08:47.953067Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:08:47.953067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"25s+OqFYwyXDeA1rTWE6LRgIXsG1DUs5iC87wnEpN4YQyVmf3uvXOq4vDR1b0sHohgwDjh8hjdx2bzEBq2XpCQ==","signature_status":"signed_v1","signed_at":"2026-06-04T01:08:47.953583Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.09803","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46e6c7157409a5bcd1974e6f3f91dc11028ae21e8d7c411aac58079c2966a78f","sha256:fe45558e4ed8ea2ba62f868264c77f1cabd3473f5ded28aca682fab029a5748d"],"state_sha256":"127498226194af1ab0bb545da817f48ef2a5b1519747790e43a2129152e23321"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/xT7iL4xZ/VF0ilzp5/9NfxcuA7EpwW3iN3X8PzywFHJ5RrA00weDGlySx1/nSmgfhU2Abr/doFypEmzAQ2TDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T08:27:39.831235Z","bundle_sha256":"b3f161ca2fbb267aa5d651d16b8b1aacd3ba3170c5d1730a7472d1ecf1954b76"}}