{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6PYB7QHF6XA4DNX5VU3QCJC7MI","short_pith_number":"pith:6PYB7QHF","canonical_record":{"source":{"id":"2509.01656","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-01T17:57:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"92c0565b85098db6333372e853675a5900580b8f130f9aa975b8568e937a32cd","abstract_canon_sha256":"1660d75470e376dc3808bb5b7f3c1774b5eebb9a27fe6eb33418d7efc49b4a93"},"schema_version":"1.0"},"canonical_sha256":"f3f01fc0e5f5c1c1b6fdad3701245f620a080307864aed69a911368705c6176d","source":{"kind":"arxiv","id":"2509.01656","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.01656","created_at":"2026-07-05T12:03:05Z"},{"alias_kind":"arxiv_version","alias_value":"2509.01656v1","created_at":"2026-07-05T12:03:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01656","created_at":"2026-07-05T12:03:05Z"},{"alias_kind":"pith_short_12","alias_value":"6PYB7QHF6XA4","created_at":"2026-07-05T12:03:05Z"},{"alias_kind":"pith_short_16","alias_value":"6PYB7QHF6XA4DNX5","created_at":"2026-07-05T12:03:05Z"},{"alias_kind":"pith_short_8","alias_value":"6PYB7QHF","created_at":"2026-07-05T12:03:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6PYB7QHF6XA4DNX5VU3QCJC7MI","target":"record","payload":{"canonical_record":{"source":{"id":"2509.01656","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-01T17:57:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"92c0565b85098db6333372e853675a5900580b8f130f9aa975b8568e937a32cd","abstract_canon_sha256":"1660d75470e376dc3808bb5b7f3c1774b5eebb9a27fe6eb33418d7efc49b4a93"},"schema_version":"1.0"},"canonical_sha256":"f3f01fc0e5f5c1c1b6fdad3701245f620a080307864aed69a911368705c6176d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:05.310677Z","signature_b64":"EjC1BUAW9tQALw5hx2NnabJMF9412y3Bu1Dgv3R5HxdXuQT/5quZizlrZznH9dvtGtQkVk913lNqtGNcLDzQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3f01fc0e5f5c1c1b6fdad3701245f620a080307864aed69a911368705c6176d","last_reissued_at":"2026-07-05T12:03:05.310088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:05.310088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.01656","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":"2026-07-05T12:03:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/BS0HYrCUabe5QUY0iuNFwpCQRKyV5dJ1Ltoju9lwt0gaNsNPeR6VoMDqLjc/Ny89m6Sqa87FLaC3w6E0ba3CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:48:10.250681Z"},"content_sha256":"fb88a0da0a4b89042f64bf55e6ca25f524e03851f3f96aed262c976a4eaa8bf0","schema_version":"1.0","event_id":"sha256:fb88a0da0a4b89042f64bf55e6ca25f524e03851f3f96aed262c976a4eaa8bf0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6PYB7QHF6XA4DNX5VU3QCJC7MI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforced Visual Perception with Tools","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dongping Chen, Mingyang Fu, Ranjay Krishna, Sinan Wang, Yao Wan, Zetong Zhou, Zhihan Hu, Zhou Zhao, Zixian Ma","submitted_at":"2025-09-01T17:57:49Z","abstract_excerpt":"Visual reasoning, a cornerstone of human intelligence, encompasses complex perceptual and logical processes essential for solving diverse visual problems. While advances in computer vision have produced powerful models for various perceptual tasks, leveraging these for general visual reasoning remains challenging. Prior work demonstrates that augmenting LLMs with vision models via supervised finetuning improves performance, but faces key limitations such as expensive data generation, reliance on careful data filtering, and poor generalization. To address these issues, we propose ReVPT to enhan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01656","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/2509.01656/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":"2026-07-05T12:03:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SDStqoLq4fJGmMwJwE+Z5umOSGekhRgUiduyDInyW15pZ4yiPsg2ddQDAqwoVGbrW4iBDox++3wdXx7z2cuNBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:48:10.251594Z"},"content_sha256":"c525ce9f8d7f3ea3131c3be62d94641d026bcba13220fa39c3600d9892bfe6b2","schema_version":"1.0","event_id":"sha256:c525ce9f8d7f3ea3131c3be62d94641d026bcba13220fa39c3600d9892bfe6b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6PYB7QHF6XA4DNX5VU3QCJC7MI/bundle.json","state_url":"https://pith.science/pith/6PYB7QHF6XA4DNX5VU3QCJC7MI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6PYB7QHF6XA4DNX5VU3QCJC7MI/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":"2026-08-03T17:48:10Z","links":{"resolver":"https://pith.science/pith/6PYB7QHF6XA4DNX5VU3QCJC7MI","bundle":"https://pith.science/pith/6PYB7QHF6XA4DNX5VU3QCJC7MI/bundle.json","state":"https://pith.science/pith/6PYB7QHF6XA4DNX5VU3QCJC7MI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6PYB7QHF6XA4DNX5VU3QCJC7MI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6PYB7QHF6XA4DNX5VU3QCJC7MI","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":"1660d75470e376dc3808bb5b7f3c1774b5eebb9a27fe6eb33418d7efc49b4a93","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-01T17:57:49Z","title_canon_sha256":"92c0565b85098db6333372e853675a5900580b8f130f9aa975b8568e937a32cd"},"schema_version":"1.0","source":{"id":"2509.01656","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.01656","created_at":"2026-07-05T12:03:05Z"},{"alias_kind":"arxiv_version","alias_value":"2509.01656v1","created_at":"2026-07-05T12:03:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01656","created_at":"2026-07-05T12:03:05Z"},{"alias_kind":"pith_short_12","alias_value":"6PYB7QHF6XA4","created_at":"2026-07-05T12:03:05Z"},{"alias_kind":"pith_short_16","alias_value":"6PYB7QHF6XA4DNX5","created_at":"2026-07-05T12:03:05Z"},{"alias_kind":"pith_short_8","alias_value":"6PYB7QHF","created_at":"2026-07-05T12:03:05Z"}],"graph_snapshots":[{"event_id":"sha256:c525ce9f8d7f3ea3131c3be62d94641d026bcba13220fa39c3600d9892bfe6b2","target":"graph","created_at":"2026-07-05T12:03:05Z","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/2509.01656/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual reasoning, a cornerstone of human intelligence, encompasses complex perceptual and logical processes essential for solving diverse visual problems. While advances in computer vision have produced powerful models for various perceptual tasks, leveraging these for general visual reasoning remains challenging. Prior work demonstrates that augmenting LLMs with vision models via supervised finetuning improves performance, but faces key limitations such as expensive data generation, reliance on careful data filtering, and poor generalization. To address these issues, we propose ReVPT to enhan","authors_text":"Dongping Chen, Mingyang Fu, Ranjay Krishna, Sinan Wang, Yao Wan, Zetong Zhou, Zhihan Hu, Zhou Zhao, Zixian Ma","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-01T17:57:49Z","title":"Reinforced Visual Perception with Tools"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01656","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:fb88a0da0a4b89042f64bf55e6ca25f524e03851f3f96aed262c976a4eaa8bf0","target":"record","created_at":"2026-07-05T12:03:05Z","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":"1660d75470e376dc3808bb5b7f3c1774b5eebb9a27fe6eb33418d7efc49b4a93","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-01T17:57:49Z","title_canon_sha256":"92c0565b85098db6333372e853675a5900580b8f130f9aa975b8568e937a32cd"},"schema_version":"1.0","source":{"id":"2509.01656","kind":"arxiv","version":1}},"canonical_sha256":"f3f01fc0e5f5c1c1b6fdad3701245f620a080307864aed69a911368705c6176d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3f01fc0e5f5c1c1b6fdad3701245f620a080307864aed69a911368705c6176d","first_computed_at":"2026-07-05T12:03:05.310088Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:05.310088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EjC1BUAW9tQALw5hx2NnabJMF9412y3Bu1Dgv3R5HxdXuQT/5quZizlrZznH9dvtGtQkVk913lNqtGNcLDzQCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:05.310677Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.01656","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb88a0da0a4b89042f64bf55e6ca25f524e03851f3f96aed262c976a4eaa8bf0","sha256:c525ce9f8d7f3ea3131c3be62d94641d026bcba13220fa39c3600d9892bfe6b2"],"state_sha256":"bf33c0511a55e364d30569f5c2a697e87f35ec4239c9cbdf93eb42c3be3a1fa3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"llJ31vvJxWmc/6VlwytnV2+TXJSEkqefaBQUP+eRd4j4kSHFxIj7ktfdlqf9p0kJT33hMMjFyC9T7JLwUsgjBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:48:10.259354Z","bundle_sha256":"e6033e3d0a54576487a247e170e7fe13c73104836f1e02b2fec235156436f2e8"}}