{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NLBDJIXQPOCUVKEWMI6LGT6CGD","short_pith_number":"pith:NLBDJIXQ","canonical_record":{"source":{"id":"2607.10966","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-13T00:21:30Z","cross_cats_sorted":[],"title_canon_sha256":"2805ec4842bb440d5f384d8bf587562dfb571e01cc86b1ebdce17b08540fa102","abstract_canon_sha256":"d3cd9c593a42a9e657e83be4002f9b3fd6f7c644aa71e0c8f000abd00721f560"},"schema_version":"1.0"},"canonical_sha256":"6ac234a2f07b854aa896623cb34fc230dfa43fb69ccbb83ea3d5a442e984908a","source":{"kind":"arxiv","id":"2607.10966","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10966","created_at":"2026-07-14T01:21:49Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10966v1","created_at":"2026-07-14T01:21:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10966","created_at":"2026-07-14T01:21:49Z"},{"alias_kind":"pith_short_12","alias_value":"NLBDJIXQPOCU","created_at":"2026-07-14T01:21:49Z"},{"alias_kind":"pith_short_16","alias_value":"NLBDJIXQPOCUVKEW","created_at":"2026-07-14T01:21:49Z"},{"alias_kind":"pith_short_8","alias_value":"NLBDJIXQ","created_at":"2026-07-14T01:21:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NLBDJIXQPOCUVKEWMI6LGT6CGD","target":"record","payload":{"canonical_record":{"source":{"id":"2607.10966","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-13T00:21:30Z","cross_cats_sorted":[],"title_canon_sha256":"2805ec4842bb440d5f384d8bf587562dfb571e01cc86b1ebdce17b08540fa102","abstract_canon_sha256":"d3cd9c593a42a9e657e83be4002f9b3fd6f7c644aa71e0c8f000abd00721f560"},"schema_version":"1.0"},"canonical_sha256":"6ac234a2f07b854aa896623cb34fc230dfa43fb69ccbb83ea3d5a442e984908a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:21:49.904785Z","signature_b64":"o2P6INjmsU0+EciquNi1U71qDVCxCEpSVzZ8LuullP9TtZZhwho6JvXQ4N2f7yeZ4RnIjIHVTQA0I5vkAScgBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ac234a2f07b854aa896623cb34fc230dfa43fb69ccbb83ea3d5a442e984908a","last_reissued_at":"2026-07-14T01:21:49.903940Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:21:49.903940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.10966","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":"2026-07-14T01:21:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3p1Efq35MCK9aWErsgs78cQmk54DoreXIYii0RSRbYybDzDJ7ULa1rDrixcEJtS+Xenx46xcOeyyCupHIQiNCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:15:32.902075Z"},"content_sha256":"fc41791c383e23e42c9f8c5f931ddfa8b7f74ecd1b095c2f8642326494e01117","schema_version":"1.0","event_id":"sha256:fc41791c383e23e42c9f8c5f931ddfa8b7f74ecd1b095c2f8642326494e01117"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NLBDJIXQPOCUVKEWMI6LGT6CGD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SVR-R1: Bootstrapping Multi-modal Reasoning with Self-verification in Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aashu Singh, Fei Liu, Hanchao Yu, Jianyu Wang, Jingcheng Yang, Jize Jiang, Khoi Pham, Klara Nahrstedt, Mingyuan Wu, Qifan Wang, Shengyi Qian, Xudong Wang, Zhaolun Su, Zhuokai Zhao","submitted_at":"2026-07-13T00:21:30Z","abstract_excerpt":"We introduce Self-Verified Reasoner (SVR-R1), a multi-turn RL framework that turns a model's own verification into a learning signal for multimodal reasoning. For each query, the model proposes an answer using the same weights, and issues a binary self-verdict (Yes/No). A 'No' triggers a second-chance rethink; a 'Yes,' or a turn cap, finalizes the output for computing the outcome-based reward. SVR-R1 is implemented with GRPO and an asynchronous multi-turn rollout framework and needs no external supervision or auxiliary critics. We evaluate SVR-R1 on vision-language reasoning benchmarks and sho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10966","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/2607.10966/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":"2026-07-14T01:21:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kNq1tPSw7mxr5gdFUqnrD7wyjk8JxK6nZK0plzjmp9OIUbSRWJUMD+oYTf3FlOTyIv4JpCQZ7zR2X3rNbXYABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:15:32.903087Z"},"content_sha256":"5e7627deda2b052bc8488c457f59b019fdfba1eb3cd4477c5296554945257451","schema_version":"1.0","event_id":"sha256:5e7627deda2b052bc8488c457f59b019fdfba1eb3cd4477c5296554945257451"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NLBDJIXQPOCUVKEWMI6LGT6CGD/bundle.json","state_url":"https://pith.science/pith/NLBDJIXQPOCUVKEWMI6LGT6CGD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NLBDJIXQPOCUVKEWMI6LGT6CGD/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":"2026-08-04T16:15:32Z","links":{"resolver":"https://pith.science/pith/NLBDJIXQPOCUVKEWMI6LGT6CGD","bundle":"https://pith.science/pith/NLBDJIXQPOCUVKEWMI6LGT6CGD/bundle.json","state":"https://pith.science/pith/NLBDJIXQPOCUVKEWMI6LGT6CGD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NLBDJIXQPOCUVKEWMI6LGT6CGD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NLBDJIXQPOCUVKEWMI6LGT6CGD","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":"d3cd9c593a42a9e657e83be4002f9b3fd6f7c644aa71e0c8f000abd00721f560","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-13T00:21:30Z","title_canon_sha256":"2805ec4842bb440d5f384d8bf587562dfb571e01cc86b1ebdce17b08540fa102"},"schema_version":"1.0","source":{"id":"2607.10966","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10966","created_at":"2026-07-14T01:21:49Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10966v1","created_at":"2026-07-14T01:21:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10966","created_at":"2026-07-14T01:21:49Z"},{"alias_kind":"pith_short_12","alias_value":"NLBDJIXQPOCU","created_at":"2026-07-14T01:21:49Z"},{"alias_kind":"pith_short_16","alias_value":"NLBDJIXQPOCUVKEW","created_at":"2026-07-14T01:21:49Z"},{"alias_kind":"pith_short_8","alias_value":"NLBDJIXQ","created_at":"2026-07-14T01:21:49Z"}],"graph_snapshots":[{"event_id":"sha256:5e7627deda2b052bc8488c457f59b019fdfba1eb3cd4477c5296554945257451","target":"graph","created_at":"2026-07-14T01:21:49Z","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/2607.10966/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Self-Verified Reasoner (SVR-R1), a multi-turn RL framework that turns a model's own verification into a learning signal for multimodal reasoning. For each query, the model proposes an answer using the same weights, and issues a binary self-verdict (Yes/No). A 'No' triggers a second-chance rethink; a 'Yes,' or a turn cap, finalizes the output for computing the outcome-based reward. SVR-R1 is implemented with GRPO and an asynchronous multi-turn rollout framework and needs no external supervision or auxiliary critics. We evaluate SVR-R1 on vision-language reasoning benchmarks and sho","authors_text":"Aashu Singh, Fei Liu, Hanchao Yu, Jianyu Wang, Jingcheng Yang, Jize Jiang, Khoi Pham, Klara Nahrstedt, Mingyuan Wu, Qifan Wang, Shengyi Qian, Xudong Wang, Zhaolun Su, Zhuokai Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-13T00:21:30Z","title":"SVR-R1: Bootstrapping Multi-modal Reasoning with Self-verification in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10966","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:fc41791c383e23e42c9f8c5f931ddfa8b7f74ecd1b095c2f8642326494e01117","target":"record","created_at":"2026-07-14T01:21:49Z","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":"d3cd9c593a42a9e657e83be4002f9b3fd6f7c644aa71e0c8f000abd00721f560","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-13T00:21:30Z","title_canon_sha256":"2805ec4842bb440d5f384d8bf587562dfb571e01cc86b1ebdce17b08540fa102"},"schema_version":"1.0","source":{"id":"2607.10966","kind":"arxiv","version":1}},"canonical_sha256":"6ac234a2f07b854aa896623cb34fc230dfa43fb69ccbb83ea3d5a442e984908a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ac234a2f07b854aa896623cb34fc230dfa43fb69ccbb83ea3d5a442e984908a","first_computed_at":"2026-07-14T01:21:49.903940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:21:49.903940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o2P6INjmsU0+EciquNi1U71qDVCxCEpSVzZ8LuullP9TtZZhwho6JvXQ4N2f7yeZ4RnIjIHVTQA0I5vkAScgBw==","signature_status":"signed_v1","signed_at":"2026-07-14T01:21:49.904785Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.10966","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc41791c383e23e42c9f8c5f931ddfa8b7f74ecd1b095c2f8642326494e01117","sha256:5e7627deda2b052bc8488c457f59b019fdfba1eb3cd4477c5296554945257451"],"state_sha256":"3fadf6fdf2597dc6050fe7895e85605a79a7bd81427af5c3a8709a65b3eea3a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3TMlHDhCsvGBdT5i1XNrZLDM53ciullgmsXuY9G6IsJSf3gsNaGn8jiFsCJ0LibDwB/gGCIT94e3tqJ2100sCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:15:32.911593Z","bundle_sha256":"8c37e95686e6782d90731224e437ba2f4d124f13ca97642e890491b648b2f167"}}