{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MWIPRXHBIWFTNIWRBC6WPQ4R3N","short_pith_number":"pith:MWIPRXHB","canonical_record":{"source":{"id":"2606.17678","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-16T08:45:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f8c78da3202262898553d1d997fe75565a15a50caa7b0a5685ce511d1d309353","abstract_canon_sha256":"68aace796077fdd3c2a25ad2db6fee9fecb577807dc2b4f691f244378cec960d"},"schema_version":"1.0"},"canonical_sha256":"6590f8dce1458b36a2d108bd67c391db683485c086b4b57cd5ab2bc585fa4c5b","source":{"kind":"arxiv","id":"2606.17678","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.17678","created_at":"2026-06-19T16:10:19Z"},{"alias_kind":"arxiv_version","alias_value":"2606.17678v1","created_at":"2026-06-19T16:10:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17678","created_at":"2026-06-19T16:10:19Z"},{"alias_kind":"pith_short_12","alias_value":"MWIPRXHBIWFT","created_at":"2026-06-19T16:10:19Z"},{"alias_kind":"pith_short_16","alias_value":"MWIPRXHBIWFTNIWR","created_at":"2026-06-19T16:10:19Z"},{"alias_kind":"pith_short_8","alias_value":"MWIPRXHB","created_at":"2026-06-19T16:10:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MWIPRXHBIWFTNIWRBC6WPQ4R3N","target":"record","payload":{"canonical_record":{"source":{"id":"2606.17678","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-16T08:45:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f8c78da3202262898553d1d997fe75565a15a50caa7b0a5685ce511d1d309353","abstract_canon_sha256":"68aace796077fdd3c2a25ad2db6fee9fecb577807dc2b4f691f244378cec960d"},"schema_version":"1.0"},"canonical_sha256":"6590f8dce1458b36a2d108bd67c391db683485c086b4b57cd5ab2bc585fa4c5b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:19.171584Z","signature_b64":"LivR9D90HTiX4bjNHCvJupJ2JBWjoOvT7WwlMo+JjT3pwFq/KTX4dSV/FScqyj4uXBmxf/wMKhQ1AlvjbGGGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6590f8dce1458b36a2d108bd67c391db683485c086b4b57cd5ab2bc585fa4c5b","last_reissued_at":"2026-06-19T16:10:19.171210Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:19.171210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.17678","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":"2026-06-19T16:10:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kdK3boUVpXzqnLi01OvdULElUlhaTIPJP63wHAJJu3G4h6eH8+ae34fEO5lW246u8UkW0dLnesEnuqr0giqXAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T01:42:42.802155Z"},"content_sha256":"9589f2f2f438366907ba1d95987849dd43d88ef91fd65e5239dae8c85dd31b0a","schema_version":"1.0","event_id":"sha256:9589f2f2f438366907ba1d95987849dd43d88ef91fd65e5239dae8c85dd31b0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MWIPRXHBIWFTNIWRBC6WPQ4R3N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"See First, Answer Later: Visual Evidence Pre-Alignment via Sufficiency-Driven RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guoshun Nan, Jiayu Huang, Junyi Zhu, Minghao Sun, Sicong Leng, Xiaofeng Tao, Xuancheng Zhu, Yilian Liu, Yisong Chen, Zexian Wei","submitted_at":"2026-06-16T08:45:24Z","abstract_excerpt":"Multimodal large language models (MLLMs) integrate strong text reasoning with visual inputs, yet their responses can be inconsistent with the underlying images, indicating ineffective utilization of visual evidence during inference. The prevailing training paradigm relies on large-scale caption-based pretraining for general alignment, followed by supervised fine-tuning and reinforcement learning to enable instruction following and complex reasoning. However, such pretraining provides only weak visual grounding: short, coarse captions bias models toward salient objects while neglecting fine-gra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17678","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/2606.17678/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":"2026-06-19T16:10:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H1Crsyngz4duRkvXXzrOylTyd+NG7WlLSLd5PUWWn3HF9lyzbs2qanS38Mgzfb4mw1Fa59HyyQjznb6zEOaqAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T01:42:42.802558Z"},"content_sha256":"9feae344a54a949902b8638d47e89b04676539a70d445c2f6d2b44eae184d8f3","schema_version":"1.0","event_id":"sha256:9feae344a54a949902b8638d47e89b04676539a70d445c2f6d2b44eae184d8f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MWIPRXHBIWFTNIWRBC6WPQ4R3N/bundle.json","state_url":"https://pith.science/pith/MWIPRXHBIWFTNIWRBC6WPQ4R3N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MWIPRXHBIWFTNIWRBC6WPQ4R3N/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":"2026-06-27T01:42:42Z","links":{"resolver":"https://pith.science/pith/MWIPRXHBIWFTNIWRBC6WPQ4R3N","bundle":"https://pith.science/pith/MWIPRXHBIWFTNIWRBC6WPQ4R3N/bundle.json","state":"https://pith.science/pith/MWIPRXHBIWFTNIWRBC6WPQ4R3N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MWIPRXHBIWFTNIWRBC6WPQ4R3N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MWIPRXHBIWFTNIWRBC6WPQ4R3N","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":"68aace796077fdd3c2a25ad2db6fee9fecb577807dc2b4f691f244378cec960d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-16T08:45:24Z","title_canon_sha256":"f8c78da3202262898553d1d997fe75565a15a50caa7b0a5685ce511d1d309353"},"schema_version":"1.0","source":{"id":"2606.17678","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.17678","created_at":"2026-06-19T16:10:19Z"},{"alias_kind":"arxiv_version","alias_value":"2606.17678v1","created_at":"2026-06-19T16:10:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17678","created_at":"2026-06-19T16:10:19Z"},{"alias_kind":"pith_short_12","alias_value":"MWIPRXHBIWFT","created_at":"2026-06-19T16:10:19Z"},{"alias_kind":"pith_short_16","alias_value":"MWIPRXHBIWFTNIWR","created_at":"2026-06-19T16:10:19Z"},{"alias_kind":"pith_short_8","alias_value":"MWIPRXHB","created_at":"2026-06-19T16:10:19Z"}],"graph_snapshots":[{"event_id":"sha256:9feae344a54a949902b8638d47e89b04676539a70d445c2f6d2b44eae184d8f3","target":"graph","created_at":"2026-06-19T16:10:19Z","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/2606.17678/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) integrate strong text reasoning with visual inputs, yet their responses can be inconsistent with the underlying images, indicating ineffective utilization of visual evidence during inference. The prevailing training paradigm relies on large-scale caption-based pretraining for general alignment, followed by supervised fine-tuning and reinforcement learning to enable instruction following and complex reasoning. However, such pretraining provides only weak visual grounding: short, coarse captions bias models toward salient objects while neglecting fine-gra","authors_text":"Guoshun Nan, Jiayu Huang, Junyi Zhu, Minghao Sun, Sicong Leng, Xiaofeng Tao, Xuancheng Zhu, Yilian Liu, Yisong Chen, Zexian Wei","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-16T08:45:24Z","title":"See First, Answer Later: Visual Evidence Pre-Alignment via Sufficiency-Driven RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17678","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":"sha256:9589f2f2f438366907ba1d95987849dd43d88ef91fd65e5239dae8c85dd31b0a","target":"record","created_at":"2026-06-19T16:10:19Z","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":"68aace796077fdd3c2a25ad2db6fee9fecb577807dc2b4f691f244378cec960d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-16T08:45:24Z","title_canon_sha256":"f8c78da3202262898553d1d997fe75565a15a50caa7b0a5685ce511d1d309353"},"schema_version":"1.0","source":{"id":"2606.17678","kind":"arxiv","version":1}},"canonical_sha256":"6590f8dce1458b36a2d108bd67c391db683485c086b4b57cd5ab2bc585fa4c5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6590f8dce1458b36a2d108bd67c391db683485c086b4b57cd5ab2bc585fa4c5b","first_computed_at":"2026-06-19T16:10:19.171210Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:19.171210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LivR9D90HTiX4bjNHCvJupJ2JBWjoOvT7WwlMo+JjT3pwFq/KTX4dSV/FScqyj4uXBmxf/wMKhQ1AlvjbGGGDg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:19.171584Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.17678","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9589f2f2f438366907ba1d95987849dd43d88ef91fd65e5239dae8c85dd31b0a","sha256:9feae344a54a949902b8638d47e89b04676539a70d445c2f6d2b44eae184d8f3"],"state_sha256":"81106c9ca68086acdebe90bc77dde3badec5033e27410f1c85118f1bf0b67010"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JsKyvwYsRixN/NHe0Q0tAWKLAxGJE+nBYPQlXy6RZAoIIw5X1iUWVS6ea4lXwbo/1hRSyOOyG4AB+Ophd/VvBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T01:42:42.804504Z","bundle_sha256":"34caf9fb8454dfde0b16019cd20c37534a6aa5a7b443515ee375464c0ed4d3ec"}}