{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:K6XZZLPBHH7XA7BVF3EA4VQ7QL","short_pith_number":"pith:K6XZZLPB","canonical_record":{"source":{"id":"2608.02217","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T13:38:37Z","cross_cats_sorted":[],"title_canon_sha256":"936b6f85d3ca84a953a79c20348dc3fb93757dbdf5c8d510e6023d31a8cd7814","abstract_canon_sha256":"50df5b4724c403606fe2bf472622915d3c81d0f6508667a4267de9483c351a77"},"schema_version":"1.0"},"canonical_sha256":"57af9cade139ff707c352ec80e561f82f08ffffc498d251e9e733c9ab029a7e4","source":{"kind":"arxiv","id":"2608.02217","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02217","created_at":"2026-08-04T02:11:25Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02217v1","created_at":"2026-08-04T02:11:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02217","created_at":"2026-08-04T02:11:25Z"},{"alias_kind":"pith_short_12","alias_value":"K6XZZLPBHH7X","created_at":"2026-08-04T02:11:25Z"},{"alias_kind":"pith_short_16","alias_value":"K6XZZLPBHH7XA7BV","created_at":"2026-08-04T02:11:25Z"},{"alias_kind":"pith_short_8","alias_value":"K6XZZLPB","created_at":"2026-08-04T02:11:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:K6XZZLPBHH7XA7BVF3EA4VQ7QL","target":"record","payload":{"canonical_record":{"source":{"id":"2608.02217","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T13:38:37Z","cross_cats_sorted":[],"title_canon_sha256":"936b6f85d3ca84a953a79c20348dc3fb93757dbdf5c8d510e6023d31a8cd7814","abstract_canon_sha256":"50df5b4724c403606fe2bf472622915d3c81d0f6508667a4267de9483c351a77"},"schema_version":"1.0"},"canonical_sha256":"57af9cade139ff707c352ec80e561f82f08ffffc498d251e9e733c9ab029a7e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:11:25.695729Z","signature_b64":"cMNXeKzOipCX2uPmz8yY0wloLtmKhJtC3XarUfz8sIcDJl3a+WyZio0UlKDYokj5X7LLnMwKbOINaHCbz/Q1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57af9cade139ff707c352ec80e561f82f08ffffc498d251e9e733c9ab029a7e4","last_reissued_at":"2026-08-04T02:11:25.694179Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:11:25.694179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.02217","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":"2026-08-04T02:11:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7LRuN3CLmsH7c/rbp5GZZq+DxF5GLbexQNJY/jUj2R3Cj/tRFMfhERfpU54NB78Qv5az4TNmIzWxDufnPt4mDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:36:29.201328Z"},"content_sha256":"5b09948ed56e70740294f87f698e274ac978dd4218314c36fb466f6675a879c6","schema_version":"1.0","event_id":"sha256:5b09948ed56e70740294f87f698e274ac978dd4218314c36fb466f6675a879c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:K6XZZLPBHH7XA7BVF3EA4VQ7QL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VC-Tooler: Learning Compositional and Adaptive Visual Tool Use","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Deng, Jiashen Hua, Jieping Ye, Yizheng Wu","submitted_at":"2026-08-03T13:38:37Z","abstract_excerpt":"Agentic multimodal reasoning extends passive image understanding by allowing VLMs to actively acquire and refine visual evidence through visual tool interactions. Effective visual tool use requires three capabilities: grounding tool calls in visual context, composing tools across multiple steps, and adapting reasoning to tool-returned observations. However, existing approaches largely focus on grounding within fixed tool spaces and rigid invocation patterns, leaving composition and adaptation insufficiently addressed. We present VC-Tooler, which learns visual tool use as a compositional and ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02217","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/2608.02217/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":"2026-08-04T02:11:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hQeE8vVXPgHewgvbjir9Ahx5uwu49HUqJNcvzgqT9HN95C6vLu6IjOsJwwkqqL4aE5HnqMoNp6TlulQvPjQMDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:36:29.202377Z"},"content_sha256":"15f9f78b26809b148c0fc36831bfb1f67dfc2e8e0eb5e17ee6aaf600ff647543","schema_version":"1.0","event_id":"sha256:15f9f78b26809b148c0fc36831bfb1f67dfc2e8e0eb5e17ee6aaf600ff647543"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K6XZZLPBHH7XA7BVF3EA4VQ7QL/bundle.json","state_url":"https://pith.science/pith/K6XZZLPBHH7XA7BVF3EA4VQ7QL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K6XZZLPBHH7XA7BVF3EA4VQ7QL/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":"2026-08-05T10:36:29Z","links":{"resolver":"https://pith.science/pith/K6XZZLPBHH7XA7BVF3EA4VQ7QL","bundle":"https://pith.science/pith/K6XZZLPBHH7XA7BVF3EA4VQ7QL/bundle.json","state":"https://pith.science/pith/K6XZZLPBHH7XA7BVF3EA4VQ7QL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K6XZZLPBHH7XA7BVF3EA4VQ7QL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:K6XZZLPBHH7XA7BVF3EA4VQ7QL","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":"50df5b4724c403606fe2bf472622915d3c81d0f6508667a4267de9483c351a77","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T13:38:37Z","title_canon_sha256":"936b6f85d3ca84a953a79c20348dc3fb93757dbdf5c8d510e6023d31a8cd7814"},"schema_version":"1.0","source":{"id":"2608.02217","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02217","created_at":"2026-08-04T02:11:25Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02217v1","created_at":"2026-08-04T02:11:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02217","created_at":"2026-08-04T02:11:25Z"},{"alias_kind":"pith_short_12","alias_value":"K6XZZLPBHH7X","created_at":"2026-08-04T02:11:25Z"},{"alias_kind":"pith_short_16","alias_value":"K6XZZLPBHH7XA7BV","created_at":"2026-08-04T02:11:25Z"},{"alias_kind":"pith_short_8","alias_value":"K6XZZLPB","created_at":"2026-08-04T02:11:25Z"}],"graph_snapshots":[{"event_id":"sha256:15f9f78b26809b148c0fc36831bfb1f67dfc2e8e0eb5e17ee6aaf600ff647543","target":"graph","created_at":"2026-08-04T02:11:25Z","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/2608.02217/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agentic multimodal reasoning extends passive image understanding by allowing VLMs to actively acquire and refine visual evidence through visual tool interactions. Effective visual tool use requires three capabilities: grounding tool calls in visual context, composing tools across multiple steps, and adapting reasoning to tool-returned observations. However, existing approaches largely focus on grounding within fixed tool spaces and rigid invocation patterns, leaving composition and adaptation insufficiently addressed. We present VC-Tooler, which learns visual tool use as a compositional and ad","authors_text":"Bing Deng, Jiashen Hua, Jieping Ye, Yizheng Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T13:38:37Z","title":"VC-Tooler: Learning Compositional and Adaptive Visual Tool Use"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02217","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":"sha256:5b09948ed56e70740294f87f698e274ac978dd4218314c36fb466f6675a879c6","target":"record","created_at":"2026-08-04T02:11:25Z","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":"50df5b4724c403606fe2bf472622915d3c81d0f6508667a4267de9483c351a77","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T13:38:37Z","title_canon_sha256":"936b6f85d3ca84a953a79c20348dc3fb93757dbdf5c8d510e6023d31a8cd7814"},"schema_version":"1.0","source":{"id":"2608.02217","kind":"arxiv","version":1}},"canonical_sha256":"57af9cade139ff707c352ec80e561f82f08ffffc498d251e9e733c9ab029a7e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57af9cade139ff707c352ec80e561f82f08ffffc498d251e9e733c9ab029a7e4","first_computed_at":"2026-08-04T02:11:25.694179Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:11:25.694179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cMNXeKzOipCX2uPmz8yY0wloLtmKhJtC3XarUfz8sIcDJl3a+WyZio0UlKDYokj5X7LLnMwKbOINaHCbz/Q1Cg==","signature_status":"signed_v1","signed_at":"2026-08-04T02:11:25.695729Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02217","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b09948ed56e70740294f87f698e274ac978dd4218314c36fb466f6675a879c6","sha256:15f9f78b26809b148c0fc36831bfb1f67dfc2e8e0eb5e17ee6aaf600ff647543"],"state_sha256":"5716f079002885d2e119883b78624a918665ce9ae2a9dd307efb6c7ec2ac12c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6FjLZD4FmClWOh0d1hiVqDdWJN/Ippth/uzGj5q7V+AtapHvfigNo2rJ1jp5DYD62lUnv73Tk65pKBRBEqq0Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:36:29.207403Z","bundle_sha256":"6cc2bdcf2ac670255ae8996017c3e849fb6e99bde7b35ca6fc875539ccb6df67"}}