{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:A325CT6LKQEKUFICPQKXH62WE3","short_pith_number":"pith:A325CT6L","canonical_record":{"source":{"id":"2606.27369","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T17:59:36Z","cross_cats_sorted":[],"title_canon_sha256":"3ebae9108e9356a8d9026e7d924f18ea579620e823b7b28b146b4231e52a65a9","abstract_canon_sha256":"28db7998274c084c2582d78e4bfd8e69a38833d9ed59ff8cb5e9148af199833f"},"schema_version":"1.0"},"canonical_sha256":"06f5d14fcb5408aa15027c1573fb5626cc024c81436c7c7d7418ed1ef92b7cbc","source":{"kind":"arxiv","id":"2606.27369","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27369","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27369v1","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27369","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"pith_short_12","alias_value":"A325CT6LKQEK","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"pith_short_16","alias_value":"A325CT6LKQEKUFIC","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"pith_short_8","alias_value":"A325CT6L","created_at":"2026-06-26T01:16:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:A325CT6LKQEKUFICPQKXH62WE3","target":"record","payload":{"canonical_record":{"source":{"id":"2606.27369","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T17:59:36Z","cross_cats_sorted":[],"title_canon_sha256":"3ebae9108e9356a8d9026e7d924f18ea579620e823b7b28b146b4231e52a65a9","abstract_canon_sha256":"28db7998274c084c2582d78e4bfd8e69a38833d9ed59ff8cb5e9148af199833f"},"schema_version":"1.0"},"canonical_sha256":"06f5d14fcb5408aa15027c1573fb5626cc024c81436c7c7d7418ed1ef92b7cbc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:16:20.089413Z","signature_b64":"zdkFbhdIxc8AkBBTIe8EQrPg82UHS0975S5FXClWUnwdjuvodlY0DJsVUxpbDzJ7cCXeHS49hYsABOJY82V6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06f5d14fcb5408aa15027c1573fb5626cc024c81436c7c7d7418ed1ef92b7cbc","last_reissued_at":"2026-06-26T01:16:20.089000Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:16:20.089000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.27369","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":"2026-06-26T01:16:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eNh5lM8502IoPWoPQtoQDiWmeBCZ87xEcpadTrriK5+SrKTnnpJhYACSC2MG56WkGCrr5jVOiuaDw2RF+D7pCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T14:00:34.863694Z"},"content_sha256":"2eeb637678863a6ec19ebd6ecd48b72d3d48babfe8de22c82c00a32daa785fc8","schema_version":"1.0","event_id":"sha256:2eeb637678863a6ec19ebd6ecd48b72d3d48babfe8de22c82c00a32daa785fc8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:A325CT6LKQEKUFICPQKXH62WE3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning without Ground-Truth Solutions can Improve LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kun Zhou, Nikki Lijing Kuang, Qiyue Gao, Tongtong Liang, Xunpeng Huang, Yi-An Ma, Yingyu Lin, Yuxiong He, Zhewei Yao","submitted_at":"2026-06-25T17:59:36Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) for training LLMs typically rely on ground-truth answers to assign rewards, limiting their applicability to tasks where the ground-truth solution is unknown. We introduce a \\textbf{R}anking-\\textbf{i}nduced \\textbf{VER}ifiable framework (RiVER) that trains LLMs on score-based optimization tasks without ground-truth solutions, using deterministic execution feedback as continuous-valued supervision. When applying group-relative RL to such continuous rewards, we identify two key challenges: \\emph{scale dominance}, where uncalibrated score magn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27369","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/2606.27369/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":"2026-06-26T01:16:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2zo7A4IPY/EzaC/lyPuN+nvQjyd1xbmh8ei2taWlU9/UtNi8vv9Td1nepnpFlFgLG9DK7vjn6rCLboRRacpNDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T14:00:34.864070Z"},"content_sha256":"9b1232fcfae7ac391d3480f7ca96e15044b08bc8fe3eb77fbe4003a1e54c7584","schema_version":"1.0","event_id":"sha256:9b1232fcfae7ac391d3480f7ca96e15044b08bc8fe3eb77fbe4003a1e54c7584"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A325CT6LKQEKUFICPQKXH62WE3/bundle.json","state_url":"https://pith.science/pith/A325CT6LKQEKUFICPQKXH62WE3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A325CT6LKQEKUFICPQKXH62WE3/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":"2026-06-26T14:00:34Z","links":{"resolver":"https://pith.science/pith/A325CT6LKQEKUFICPQKXH62WE3","bundle":"https://pith.science/pith/A325CT6LKQEKUFICPQKXH62WE3/bundle.json","state":"https://pith.science/pith/A325CT6LKQEKUFICPQKXH62WE3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A325CT6LKQEKUFICPQKXH62WE3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:A325CT6LKQEKUFICPQKXH62WE3","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":"28db7998274c084c2582d78e4bfd8e69a38833d9ed59ff8cb5e9148af199833f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T17:59:36Z","title_canon_sha256":"3ebae9108e9356a8d9026e7d924f18ea579620e823b7b28b146b4231e52a65a9"},"schema_version":"1.0","source":{"id":"2606.27369","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27369","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27369v1","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27369","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"pith_short_12","alias_value":"A325CT6LKQEK","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"pith_short_16","alias_value":"A325CT6LKQEKUFIC","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"pith_short_8","alias_value":"A325CT6L","created_at":"2026-06-26T01:16:20Z"}],"graph_snapshots":[{"event_id":"sha256:9b1232fcfae7ac391d3480f7ca96e15044b08bc8fe3eb77fbe4003a1e54c7584","target":"graph","created_at":"2026-06-26T01:16:20Z","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/2606.27369/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) for training LLMs typically rely on ground-truth answers to assign rewards, limiting their applicability to tasks where the ground-truth solution is unknown. We introduce a \\textbf{R}anking-\\textbf{i}nduced \\textbf{VER}ifiable framework (RiVER) that trains LLMs on score-based optimization tasks without ground-truth solutions, using deterministic execution feedback as continuous-valued supervision. When applying group-relative RL to such continuous rewards, we identify two key challenges: \\emph{scale dominance}, where uncalibrated score magn","authors_text":"Kun Zhou, Nikki Lijing Kuang, Qiyue Gao, Tongtong Liang, Xunpeng Huang, Yi-An Ma, Yingyu Lin, Yuxiong He, Zhewei Yao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T17:59:36Z","title":"Reinforcement Learning without Ground-Truth Solutions can Improve LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27369","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":"sha256:2eeb637678863a6ec19ebd6ecd48b72d3d48babfe8de22c82c00a32daa785fc8","target":"record","created_at":"2026-06-26T01:16:20Z","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":"28db7998274c084c2582d78e4bfd8e69a38833d9ed59ff8cb5e9148af199833f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T17:59:36Z","title_canon_sha256":"3ebae9108e9356a8d9026e7d924f18ea579620e823b7b28b146b4231e52a65a9"},"schema_version":"1.0","source":{"id":"2606.27369","kind":"arxiv","version":1}},"canonical_sha256":"06f5d14fcb5408aa15027c1573fb5626cc024c81436c7c7d7418ed1ef92b7cbc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06f5d14fcb5408aa15027c1573fb5626cc024c81436c7c7d7418ed1ef92b7cbc","first_computed_at":"2026-06-26T01:16:20.089000Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:16:20.089000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zdkFbhdIxc8AkBBTIe8EQrPg82UHS0975S5FXClWUnwdjuvodlY0DJsVUxpbDzJ7cCXeHS49hYsABOJY82V6CA==","signature_status":"signed_v1","signed_at":"2026-06-26T01:16:20.089413Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.27369","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2eeb637678863a6ec19ebd6ecd48b72d3d48babfe8de22c82c00a32daa785fc8","sha256:9b1232fcfae7ac391d3480f7ca96e15044b08bc8fe3eb77fbe4003a1e54c7584"],"state_sha256":"dbede6db756e7c5c2c7f5b48fd06e89584bd93eb079387b1feb7d8e7adb5a57e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oQesNbiKJ4gQ3Cvc5G1jzy7YZbpBRqoBYdwafEK7wHLpuyjDTjSXdadaJ0S6kIx3b/WGkXLQTQBY4bEzONh9CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T14:00:34.866080Z","bundle_sha256":"59855b5adfc553dfa812762fc85726c4faf03242f873822722244377ec9ff5f5"}}