{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2QUBORBG3YDSG3PNIUPUKJI3L7","short_pith_number":"pith:2QUBORBG","canonical_record":{"source":{"id":"2603.05256","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-05T15:08:06Z","cross_cats_sorted":[],"title_canon_sha256":"7b2e53911fdbe7a2ee253afacc04cce896b6d3438d594dd42c76d293d3a963d9","abstract_canon_sha256":"7d9d1b9288005432efc050d4bf223bf998f134ef75e373bc2a45bb58ecaffc8e"},"schema_version":"1.0"},"canonical_sha256":"d428174426de07236ded451f45251b5feb013b3f42f297c7ec37094e719ad4c8","source":{"kind":"arxiv","id":"2603.05256","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.05256","created_at":"2026-07-03T01:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"2603.05256v2","created_at":"2026-07-03T01:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.05256","created_at":"2026-07-03T01:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"2QUBORBG3YDS","created_at":"2026-07-03T01:17:54Z"},{"alias_kind":"pith_short_16","alias_value":"2QUBORBG3YDSG3PN","created_at":"2026-07-03T01:17:54Z"},{"alias_kind":"pith_short_8","alias_value":"2QUBORBG","created_at":"2026-07-03T01:17:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2QUBORBG3YDSG3PNIUPUKJI3L7","target":"record","payload":{"canonical_record":{"source":{"id":"2603.05256","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-05T15:08:06Z","cross_cats_sorted":[],"title_canon_sha256":"7b2e53911fdbe7a2ee253afacc04cce896b6d3438d594dd42c76d293d3a963d9","abstract_canon_sha256":"7d9d1b9288005432efc050d4bf223bf998f134ef75e373bc2a45bb58ecaffc8e"},"schema_version":"1.0"},"canonical_sha256":"d428174426de07236ded451f45251b5feb013b3f42f297c7ec37094e719ad4c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:54.639743Z","signature_b64":"IZku8vD6Krzj7sn6ratYgjZnbqNatVvk7wLhqNA3bDUk5hONZ9swibB4F2zOb6D/4sEt0lIevDGzGbs+F11dCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d428174426de07236ded451f45251b5feb013b3f42f297c7ec37094e719ad4c8","last_reissued_at":"2026-07-03T01:17:54.639205Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:54.639205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.05256","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":"2026-07-03T01:17:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1dfBR7ZW1j0wU12O7ptH0jctWpUaMKwBkIHxApxfplNnWxoGOlG6XLRXXZN+dvEWy6trgA+qujKya3G7RnGxAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:26:48.359694Z"},"content_sha256":"828ba4a5c88e8e4eca7d170c6bb8a5a5de158628972db4d2bc46226584a3979a","schema_version":"1.0","event_id":"sha256:828ba4a5c88e8e4eca7d170c6bb8a5a5de158628972db4d2bc46226584a3979a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2QUBORBG3YDSG3PNIUPUKJI3L7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Wiki-R1: Incentivizing Multimodal Reasoning for Knowledge-based VQA via Data and Sampling Curriculum","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Longtian Qiu, Shan Ning, Xuming He","submitted_at":"2026-03-05T15:08:06Z","abstract_excerpt":"Knowledge-Based Visual Question Answering (KB-VQA) requires models to answer questions about an image by integrating external knowledge, posing significant challenges due to noisy retrieval and the structured, encyclopedic nature of the knowledge base. These characteristics create a distributional gap from pretrained multimodal large language models (MLLMs), making effective reasoning and domain adaptation difficult in the post-training stage. In this work, we propose \\textit{Wiki-R1}, a data-generation-based curriculum reinforcement learning framework that systematically incentivizes reasonin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.05256","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/2603.05256/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":"2026-07-03T01:17:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UMdw9NqfiCqbKBieZRCjjbInogX9VNBJERQw5gA/em6LcDBByM0fb3ko/6ooJoaFB+3xx/4Kyoo8twL1cel+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:26:48.360255Z"},"content_sha256":"b876b59811fc4beaa1b9665afbec1328b297c450858bdafda6368d8936507856","schema_version":"1.0","event_id":"sha256:b876b59811fc4beaa1b9665afbec1328b297c450858bdafda6368d8936507856"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2QUBORBG3YDSG3PNIUPUKJI3L7/bundle.json","state_url":"https://pith.science/pith/2QUBORBG3YDSG3PNIUPUKJI3L7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2QUBORBG3YDSG3PNIUPUKJI3L7/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":"2026-08-04T14:26:48Z","links":{"resolver":"https://pith.science/pith/2QUBORBG3YDSG3PNIUPUKJI3L7","bundle":"https://pith.science/pith/2QUBORBG3YDSG3PNIUPUKJI3L7/bundle.json","state":"https://pith.science/pith/2QUBORBG3YDSG3PNIUPUKJI3L7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2QUBORBG3YDSG3PNIUPUKJI3L7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2QUBORBG3YDSG3PNIUPUKJI3L7","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":"7d9d1b9288005432efc050d4bf223bf998f134ef75e373bc2a45bb58ecaffc8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-05T15:08:06Z","title_canon_sha256":"7b2e53911fdbe7a2ee253afacc04cce896b6d3438d594dd42c76d293d3a963d9"},"schema_version":"1.0","source":{"id":"2603.05256","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.05256","created_at":"2026-07-03T01:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"2603.05256v2","created_at":"2026-07-03T01:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.05256","created_at":"2026-07-03T01:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"2QUBORBG3YDS","created_at":"2026-07-03T01:17:54Z"},{"alias_kind":"pith_short_16","alias_value":"2QUBORBG3YDSG3PN","created_at":"2026-07-03T01:17:54Z"},{"alias_kind":"pith_short_8","alias_value":"2QUBORBG","created_at":"2026-07-03T01:17:54Z"}],"graph_snapshots":[{"event_id":"sha256:b876b59811fc4beaa1b9665afbec1328b297c450858bdafda6368d8936507856","target":"graph","created_at":"2026-07-03T01:17:54Z","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/2603.05256/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge-Based Visual Question Answering (KB-VQA) requires models to answer questions about an image by integrating external knowledge, posing significant challenges due to noisy retrieval and the structured, encyclopedic nature of the knowledge base. These characteristics create a distributional gap from pretrained multimodal large language models (MLLMs), making effective reasoning and domain adaptation difficult in the post-training stage. In this work, we propose \\textit{Wiki-R1}, a data-generation-based curriculum reinforcement learning framework that systematically incentivizes reasonin","authors_text":"Longtian Qiu, Shan Ning, Xuming He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-05T15:08:06Z","title":"Wiki-R1: Incentivizing Multimodal Reasoning for Knowledge-based VQA via Data and Sampling Curriculum"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.05256","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":"sha256:828ba4a5c88e8e4eca7d170c6bb8a5a5de158628972db4d2bc46226584a3979a","target":"record","created_at":"2026-07-03T01:17:54Z","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":"7d9d1b9288005432efc050d4bf223bf998f134ef75e373bc2a45bb58ecaffc8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-05T15:08:06Z","title_canon_sha256":"7b2e53911fdbe7a2ee253afacc04cce896b6d3438d594dd42c76d293d3a963d9"},"schema_version":"1.0","source":{"id":"2603.05256","kind":"arxiv","version":2}},"canonical_sha256":"d428174426de07236ded451f45251b5feb013b3f42f297c7ec37094e719ad4c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d428174426de07236ded451f45251b5feb013b3f42f297c7ec37094e719ad4c8","first_computed_at":"2026-07-03T01:17:54.639205Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:54.639205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IZku8vD6Krzj7sn6ratYgjZnbqNatVvk7wLhqNA3bDUk5hONZ9swibB4F2zOb6D/4sEt0lIevDGzGbs+F11dCA==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:54.639743Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.05256","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:828ba4a5c88e8e4eca7d170c6bb8a5a5de158628972db4d2bc46226584a3979a","sha256:b876b59811fc4beaa1b9665afbec1328b297c450858bdafda6368d8936507856"],"state_sha256":"88c3834dca617e2871812dca96ecba2a1ff0552194d7deeb86f38fe5b27a0c82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fvwboTHdjekEmS64MvsfposWSvJMdEHTvbaMy5DnWkEAteq1CtetDvsJdZq1obbURZpCAZw43L0EXmqT98iVDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T14:26:48.398893Z","bundle_sha256":"7c7fd5b29a0b4820e096fa68ed31a40ed5de7187f526df688680c8efa6d5bad3"}}