{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:E35PDHT44WTTR2YGKYUBEVC5KP","short_pith_number":"pith:E35PDHT4","canonical_record":{"source":{"id":"2607.18470","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T19:40:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9ae80526c7104b311426804afe6ba8eca34deef471f7385c704a9650e7499845","abstract_canon_sha256":"a153a4b87dd0a315a34601da5d26f98cbd6f5351c6a4f5a78ae8bcac104afa2b"},"schema_version":"1.0"},"canonical_sha256":"26faf19e7ce5a738eb06562812545d53facb9fe93779bd4cf57851d1eb3f7180","source":{"kind":"arxiv","id":"2607.18470","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18470","created_at":"2026-07-22T00:22:50Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18470v1","created_at":"2026-07-22T00:22:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18470","created_at":"2026-07-22T00:22:50Z"},{"alias_kind":"pith_short_12","alias_value":"E35PDHT44WTT","created_at":"2026-07-22T00:22:50Z"},{"alias_kind":"pith_short_16","alias_value":"E35PDHT44WTTR2YG","created_at":"2026-07-22T00:22:50Z"},{"alias_kind":"pith_short_8","alias_value":"E35PDHT4","created_at":"2026-07-22T00:22:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:E35PDHT44WTTR2YGKYUBEVC5KP","target":"record","payload":{"canonical_record":{"source":{"id":"2607.18470","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T19:40:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9ae80526c7104b311426804afe6ba8eca34deef471f7385c704a9650e7499845","abstract_canon_sha256":"a153a4b87dd0a315a34601da5d26f98cbd6f5351c6a4f5a78ae8bcac104afa2b"},"schema_version":"1.0"},"canonical_sha256":"26faf19e7ce5a738eb06562812545d53facb9fe93779bd4cf57851d1eb3f7180","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T00:22:50.294027Z","signature_b64":"269Qrxe9IWrYhtfXu5nbp1ZzehgLPPo87uD8yzDf7n6S5st9/MuSQjROpAz66rUZWQo6tA88zbznLEC/8Ol0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26faf19e7ce5a738eb06562812545d53facb9fe93779bd4cf57851d1eb3f7180","last_reissued_at":"2026-07-22T00:22:50.293045Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T00:22:50.293045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.18470","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":"2026-07-22T00:22:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"24xkwTVvlmhgDCeZASkkHWrKaUcT/K/rGvKtMyOrH+3WRCxITt1Qj0OYdxheuQ0NSw9FSJUJ/ENcNTli3LnyBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:24:26.653844Z"},"content_sha256":"8da4ce5bdef7460dcacbe09146ea07dcb3f48e6de4d1f2033ea21d8399f930b8","schema_version":"1.0","event_id":"sha256:8da4ce5bdef7460dcacbe09146ea07dcb3f48e6de4d1f2033ea21d8399f930b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:E35PDHT44WTTR2YGKYUBEVC5KP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rollouts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jingbo Shang, Julian McAuley, Junda Wu, Nikki Lijing Kuang, Rohan Surana, Ryan A. Rossi, Sheldon Yu, Tong Yu, Xintong Li, Xunyi Jiang, Yuxin Xiong","submitted_at":"2026-07-20T19:40:25Z","abstract_excerpt":"Group Relative Policy Optimization (GRPO) has shown strong effectiveness in reinforcement learning from verifiable feedback, where sampled rollouts can be compared within a group using task-provided correctness signals. However, extending group-relative optimization beyond verifiable settings is challenging because success in many tasks is not captured by a single correctness criterion. We propose \\textbf{Reference-Relative Policy Optimization (RRPO)}, which generalizes GRPO by replacing direct correctness-based advantage construction with reference-relative contrastive comparisons. RRPO first"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18470","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/2607.18470/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":"2026-07-22T00:22:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6sEWEx2lW5TnGFrBHcEmuYCWFWAUSdl/GspVQjzucc/J0b5a7T7vY6qSv1xRJ35S80j9yiPzO7Ld2FB1ZT2GCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:24:26.654337Z"},"content_sha256":"0308f223ea2d7cfd01b3e7d7e9064a9e9f80d902b3ea03d6dff2a0419889bf4e","schema_version":"1.0","event_id":"sha256:0308f223ea2d7cfd01b3e7d7e9064a9e9f80d902b3ea03d6dff2a0419889bf4e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E35PDHT44WTTR2YGKYUBEVC5KP/bundle.json","state_url":"https://pith.science/pith/E35PDHT44WTTR2YGKYUBEVC5KP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E35PDHT44WTTR2YGKYUBEVC5KP/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":"2026-08-06T19:24:26Z","links":{"resolver":"https://pith.science/pith/E35PDHT44WTTR2YGKYUBEVC5KP","bundle":"https://pith.science/pith/E35PDHT44WTTR2YGKYUBEVC5KP/bundle.json","state":"https://pith.science/pith/E35PDHT44WTTR2YGKYUBEVC5KP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E35PDHT44WTTR2YGKYUBEVC5KP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:E35PDHT44WTTR2YGKYUBEVC5KP","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":"a153a4b87dd0a315a34601da5d26f98cbd6f5351c6a4f5a78ae8bcac104afa2b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T19:40:25Z","title_canon_sha256":"9ae80526c7104b311426804afe6ba8eca34deef471f7385c704a9650e7499845"},"schema_version":"1.0","source":{"id":"2607.18470","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18470","created_at":"2026-07-22T00:22:50Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18470v1","created_at":"2026-07-22T00:22:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18470","created_at":"2026-07-22T00:22:50Z"},{"alias_kind":"pith_short_12","alias_value":"E35PDHT44WTT","created_at":"2026-07-22T00:22:50Z"},{"alias_kind":"pith_short_16","alias_value":"E35PDHT44WTTR2YG","created_at":"2026-07-22T00:22:50Z"},{"alias_kind":"pith_short_8","alias_value":"E35PDHT4","created_at":"2026-07-22T00:22:50Z"}],"graph_snapshots":[{"event_id":"sha256:0308f223ea2d7cfd01b3e7d7e9064a9e9f80d902b3ea03d6dff2a0419889bf4e","target":"graph","created_at":"2026-07-22T00:22:50Z","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/2607.18470/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Group Relative Policy Optimization (GRPO) has shown strong effectiveness in reinforcement learning from verifiable feedback, where sampled rollouts can be compared within a group using task-provided correctness signals. However, extending group-relative optimization beyond verifiable settings is challenging because success in many tasks is not captured by a single correctness criterion. We propose \\textbf{Reference-Relative Policy Optimization (RRPO)}, which generalizes GRPO by replacing direct correctness-based advantage construction with reference-relative contrastive comparisons. RRPO first","authors_text":"Jingbo Shang, Julian McAuley, Junda Wu, Nikki Lijing Kuang, Rohan Surana, Ryan A. Rossi, Sheldon Yu, Tong Yu, Xintong Li, Xunyi Jiang, Yuxin Xiong","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T19:40:25Z","title":"RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rollouts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18470","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":"sha256:8da4ce5bdef7460dcacbe09146ea07dcb3f48e6de4d1f2033ea21d8399f930b8","target":"record","created_at":"2026-07-22T00:22:50Z","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":"a153a4b87dd0a315a34601da5d26f98cbd6f5351c6a4f5a78ae8bcac104afa2b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T19:40:25Z","title_canon_sha256":"9ae80526c7104b311426804afe6ba8eca34deef471f7385c704a9650e7499845"},"schema_version":"1.0","source":{"id":"2607.18470","kind":"arxiv","version":1}},"canonical_sha256":"26faf19e7ce5a738eb06562812545d53facb9fe93779bd4cf57851d1eb3f7180","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26faf19e7ce5a738eb06562812545d53facb9fe93779bd4cf57851d1eb3f7180","first_computed_at":"2026-07-22T00:22:50.293045Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T00:22:50.293045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"269Qrxe9IWrYhtfXu5nbp1ZzehgLPPo87uD8yzDf7n6S5st9/MuSQjROpAz66rUZWQo6tA88zbznLEC/8Ol0Dw==","signature_status":"signed_v1","signed_at":"2026-07-22T00:22:50.294027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18470","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8da4ce5bdef7460dcacbe09146ea07dcb3f48e6de4d1f2033ea21d8399f930b8","sha256:0308f223ea2d7cfd01b3e7d7e9064a9e9f80d902b3ea03d6dff2a0419889bf4e"],"state_sha256":"d9a596370020577f14b01ae8f3082f4d46d9e71fad8de776897808f468485bfe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3tD0a0df30f9N8AJ8KQoLGttTvhv8y7sbj2Czfs66cr/hcg++l7brIUcbAE5XunzwNI/DwrswhMq5o9TfLD1CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:24:26.659020Z","bundle_sha256":"fd346088c808f14ccd7f7f741ce426225ff7b049e9c9b48135ccbfc988443181"}}