{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2XTA3TII524RUBOZMB4WWEMATB","short_pith_number":"pith:2XTA3TII","canonical_record":{"source":{"id":"2412.03704","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T20:35:07Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"478b5c979cbbbf51c6e33b67ead3be1004c018c2f0fa7e87f75aa407d6b48a41","abstract_canon_sha256":"f9e02807ce58d195c52a025d3c74a2bbe66280adc61c0eafdf8a1651fa313de0"},"schema_version":"1.0"},"canonical_sha256":"d5e60dcd08eeb91a05d960796b118098716add6a7bb5d40376a74bb0cba94abf","source":{"kind":"arxiv","id":"2412.03704","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03704","created_at":"2026-07-05T11:29:52Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03704v3","created_at":"2026-07-05T11:29:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03704","created_at":"2026-07-05T11:29:52Z"},{"alias_kind":"pith_short_12","alias_value":"2XTA3TII524R","created_at":"2026-07-05T11:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"2XTA3TII524RUBOZ","created_at":"2026-07-05T11:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"2XTA3TII","created_at":"2026-07-05T11:29:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2XTA3TII524RUBOZMB4WWEMATB","target":"record","payload":{"canonical_record":{"source":{"id":"2412.03704","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T20:35:07Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"478b5c979cbbbf51c6e33b67ead3be1004c018c2f0fa7e87f75aa407d6b48a41","abstract_canon_sha256":"f9e02807ce58d195c52a025d3c74a2bbe66280adc61c0eafdf8a1651fa313de0"},"schema_version":"1.0"},"canonical_sha256":"d5e60dcd08eeb91a05d960796b118098716add6a7bb5d40376a74bb0cba94abf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:52.877174Z","signature_b64":"Qq4chJRagY0+VcV3xLYPsnArJFU7CjHTdDozPREwHufLVeoojeffMIThpglGj3CIGmTZ+1g7DR49e9tLgrMuAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5e60dcd08eeb91a05d960796b118098716add6a7bb5d40376a74bb0cba94abf","last_reissued_at":"2026-07-05T11:29:52.876720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:52.876720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.03704","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:29:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HDhDvpUkVmwPKKOISpcDAR3Mmtc5pG0npbsThLcffUSsHB+YNKX31AONks2YR8uhPMs7L+Z3jig8C6BokfD0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:55:59.408766Z"},"content_sha256":"f58a442edbc0c1b4fbfdab0c4a26490039781a996b8c7d6078b113b44e8cc21c","schema_version":"1.0","event_id":"sha256:f58a442edbc0c1b4fbfdab0c4a26490039781a996b8c7d6078b113b44e8cc21c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2XTA3TII524RUBOZMB4WWEMATB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chung-Ching Lin, Furong Huang, Hongjin Lu, Kevin Lin, Lijuan Wang, Linjie Li, Xiyao Wang, Yuancheng Xu, Zhengyuan Yang","submitted_at":"2024-12-04T20:35:07Z","abstract_excerpt":"Despite significant advancements in vision-language models (VLMs), there lacks effective approaches to enhance response quality by scaling inference-time computation. This capability is known to be a core step towards the self-improving models in recent large language model studies. In this paper, we present Vision Value Model (VisVM) that can guide VLM inference-time search to generate responses with better visual comprehension. Specifically, VisVM not only evaluates the generated sentence quality in the current search step, but also anticipates the quality of subsequent sentences that may re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03704","kind":"arxiv","version":3},"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/2412.03704/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":"2026-07-05T11:29:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nsOcg/TCUq3Z2hWNiuSl5LkzfWcRCZRQHyBRz2X1PVpdZsnpwdexpFWkyD5LVmZMFXt+fADGnBIGTQVlvkK4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:55:59.409426Z"},"content_sha256":"64b98ecc99f7b0f78f8f5399806714d436364edf15a73556fe345062824e60ee","schema_version":"1.0","event_id":"sha256:64b98ecc99f7b0f78f8f5399806714d436364edf15a73556fe345062824e60ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2XTA3TII524RUBOZMB4WWEMATB/bundle.json","state_url":"https://pith.science/pith/2XTA3TII524RUBOZMB4WWEMATB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2XTA3TII524RUBOZMB4WWEMATB/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":"2026-08-07T17:55:59Z","links":{"resolver":"https://pith.science/pith/2XTA3TII524RUBOZMB4WWEMATB","bundle":"https://pith.science/pith/2XTA3TII524RUBOZMB4WWEMATB/bundle.json","state":"https://pith.science/pith/2XTA3TII524RUBOZMB4WWEMATB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2XTA3TII524RUBOZMB4WWEMATB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2XTA3TII524RUBOZMB4WWEMATB","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":"f9e02807ce58d195c52a025d3c74a2bbe66280adc61c0eafdf8a1651fa313de0","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T20:35:07Z","title_canon_sha256":"478b5c979cbbbf51c6e33b67ead3be1004c018c2f0fa7e87f75aa407d6b48a41"},"schema_version":"1.0","source":{"id":"2412.03704","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03704","created_at":"2026-07-05T11:29:52Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03704v3","created_at":"2026-07-05T11:29:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03704","created_at":"2026-07-05T11:29:52Z"},{"alias_kind":"pith_short_12","alias_value":"2XTA3TII524R","created_at":"2026-07-05T11:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"2XTA3TII524RUBOZ","created_at":"2026-07-05T11:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"2XTA3TII","created_at":"2026-07-05T11:29:52Z"}],"graph_snapshots":[{"event_id":"sha256:64b98ecc99f7b0f78f8f5399806714d436364edf15a73556fe345062824e60ee","target":"graph","created_at":"2026-07-05T11:29:52Z","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/2412.03704/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite significant advancements in vision-language models (VLMs), there lacks effective approaches to enhance response quality by scaling inference-time computation. This capability is known to be a core step towards the self-improving models in recent large language model studies. In this paper, we present Vision Value Model (VisVM) that can guide VLM inference-time search to generate responses with better visual comprehension. Specifically, VisVM not only evaluates the generated sentence quality in the current search step, but also anticipates the quality of subsequent sentences that may re","authors_text":"Chung-Ching Lin, Furong Huang, Hongjin Lu, Kevin Lin, Lijuan Wang, Linjie Li, Xiyao Wang, Yuancheng Xu, Zhengyuan Yang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T20:35:07Z","title":"Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03704","kind":"arxiv","version":3},"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:f58a442edbc0c1b4fbfdab0c4a26490039781a996b8c7d6078b113b44e8cc21c","target":"record","created_at":"2026-07-05T11:29:52Z","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":"f9e02807ce58d195c52a025d3c74a2bbe66280adc61c0eafdf8a1651fa313de0","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T20:35:07Z","title_canon_sha256":"478b5c979cbbbf51c6e33b67ead3be1004c018c2f0fa7e87f75aa407d6b48a41"},"schema_version":"1.0","source":{"id":"2412.03704","kind":"arxiv","version":3}},"canonical_sha256":"d5e60dcd08eeb91a05d960796b118098716add6a7bb5d40376a74bb0cba94abf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5e60dcd08eeb91a05d960796b118098716add6a7bb5d40376a74bb0cba94abf","first_computed_at":"2026-07-05T11:29:52.876720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:52.876720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qq4chJRagY0+VcV3xLYPsnArJFU7CjHTdDozPREwHufLVeoojeffMIThpglGj3CIGmTZ+1g7DR49e9tLgrMuAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:52.877174Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03704","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f58a442edbc0c1b4fbfdab0c4a26490039781a996b8c7d6078b113b44e8cc21c","sha256:64b98ecc99f7b0f78f8f5399806714d436364edf15a73556fe345062824e60ee"],"state_sha256":"154fde617db7f6ec6eb803b9df163ba29cd95f02eb7cdda16ef612b134fe5a6d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hNMBKh7RpL51HYXKjXg+qPa14dSLAUKWyzGKyXHoEb14f5moEt58w1BJZR3zrFt9iX+BvYQ3MlnV3M9hG5R3CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:55:59.413778Z","bundle_sha256":"b2dac580d9c347177ab5ffbf0a6270c81949a8296a6536fdb981b051f6b2e4fc"}}