{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6VOCLAC4GWNFJUA54R7VQKWAJU","short_pith_number":"pith:6VOCLAC4","canonical_record":{"source":{"id":"2608.09682","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T14:52:10Z","cross_cats_sorted":[],"title_canon_sha256":"4e60991bfcf06369183d5843d332f46e8a56fb988e60292cb9236e4edfecec05","abstract_canon_sha256":"8afba20b057909fd8b388f5886bf6830cc1db2b33458ac0b4f513f1481ee4dfc"},"schema_version":"1.0"},"canonical_sha256":"f55c25805c359a54d01de47f582ac04d3ab82be9014d2e360207cab58f75b68d","source":{"kind":"arxiv","id":"2608.09682","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09682","created_at":"2026-08-11T02:24:48Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09682v1","created_at":"2026-08-11T02:24:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09682","created_at":"2026-08-11T02:24:48Z"},{"alias_kind":"pith_short_12","alias_value":"6VOCLAC4GWNF","created_at":"2026-08-11T02:24:48Z"},{"alias_kind":"pith_short_16","alias_value":"6VOCLAC4GWNFJUA5","created_at":"2026-08-11T02:24:48Z"},{"alias_kind":"pith_short_8","alias_value":"6VOCLAC4","created_at":"2026-08-11T02:24:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6VOCLAC4GWNFJUA54R7VQKWAJU","target":"record","payload":{"canonical_record":{"source":{"id":"2608.09682","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T14:52:10Z","cross_cats_sorted":[],"title_canon_sha256":"4e60991bfcf06369183d5843d332f46e8a56fb988e60292cb9236e4edfecec05","abstract_canon_sha256":"8afba20b057909fd8b388f5886bf6830cc1db2b33458ac0b4f513f1481ee4dfc"},"schema_version":"1.0"},"canonical_sha256":"f55c25805c359a54d01de47f582ac04d3ab82be9014d2e360207cab58f75b68d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:24:48.441413Z","signature_b64":"AvzSku1EeY/H+kp9KvwB84frRD8/IzQGZORtSCg40aO6oOdvuMwbJ6jTewGn/jemh594v3FvI2VmibXtNP1qDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f55c25805c359a54d01de47f582ac04d3ab82be9014d2e360207cab58f75b68d","last_reissued_at":"2026-08-11T02:24:48.439649Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:24:48.439649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.09682","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":"2026-08-11T02:24:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FVrbaJo2/NgdNbzcR7M60sSc7um5mSX86C61RJ0EmVTqpyfHaZbkpQC7rkuh/DItu742puPOAJ4tObORhTxQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:48:54.649639Z"},"content_sha256":"8429d14246cdb2e48c0e5e3a8e3520c03062e57d2a7d42ce0b264176b621139d","schema_version":"1.0","event_id":"sha256:8429d14246cdb2e48c0e5e3a8e3520c03062e57d2a7d42ce0b264176b621139d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6VOCLAC4GWNFJUA54R7VQKWAJU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ceyuan Yang, Jiahao Shao, Yinghao Xu, Yiyi Liao, Yuanbo Yang, Yujun Shen","submitted_at":"2026-08-10T14:52:10Z","abstract_excerpt":"Tool-augmented vision-language models increasingly \"think with images\": they call crop, zoom, or code tools and reason over the returned pixels. However, recent work using blind tests, gain decompositions, and attention analyses has shown that returned images contribute little, raising the question: if pixels do not carry the gain, what does? We hypothesize that the load-bearing signal is the structured text emitted before any returned pixel arrives: tool name, coordinates, target description, and intent. This textual scaffold encodes where to look and what to find. We introduce TextCall (call"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09682","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/2608.09682/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":"2026-08-11T02:24:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MhdOkLAgb1/VLdFELiVnd5oE+q/+Qi7jEyeF+usy//vDYZu8Yxc0tCax+t9djTXge0l6irhAgqYEE0Z+9DD4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:48:54.650580Z"},"content_sha256":"8fdc0a5d9c99746412efd6055ce06863db3a8b12fe810982753a7f0f6118dc58","schema_version":"1.0","event_id":"sha256:8fdc0a5d9c99746412efd6055ce06863db3a8b12fe810982753a7f0f6118dc58"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6VOCLAC4GWNFJUA54R7VQKWAJU/bundle.json","state_url":"https://pith.science/pith/6VOCLAC4GWNFJUA54R7VQKWAJU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6VOCLAC4GWNFJUA54R7VQKWAJU/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":"2026-08-12T15:48:54Z","links":{"resolver":"https://pith.science/pith/6VOCLAC4GWNFJUA54R7VQKWAJU","bundle":"https://pith.science/pith/6VOCLAC4GWNFJUA54R7VQKWAJU/bundle.json","state":"https://pith.science/pith/6VOCLAC4GWNFJUA54R7VQKWAJU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6VOCLAC4GWNFJUA54R7VQKWAJU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6VOCLAC4GWNFJUA54R7VQKWAJU","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":"8afba20b057909fd8b388f5886bf6830cc1db2b33458ac0b4f513f1481ee4dfc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T14:52:10Z","title_canon_sha256":"4e60991bfcf06369183d5843d332f46e8a56fb988e60292cb9236e4edfecec05"},"schema_version":"1.0","source":{"id":"2608.09682","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09682","created_at":"2026-08-11T02:24:48Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09682v1","created_at":"2026-08-11T02:24:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09682","created_at":"2026-08-11T02:24:48Z"},{"alias_kind":"pith_short_12","alias_value":"6VOCLAC4GWNF","created_at":"2026-08-11T02:24:48Z"},{"alias_kind":"pith_short_16","alias_value":"6VOCLAC4GWNFJUA5","created_at":"2026-08-11T02:24:48Z"},{"alias_kind":"pith_short_8","alias_value":"6VOCLAC4","created_at":"2026-08-11T02:24:48Z"}],"graph_snapshots":[{"event_id":"sha256:8fdc0a5d9c99746412efd6055ce06863db3a8b12fe810982753a7f0f6118dc58","target":"graph","created_at":"2026-08-11T02:24:48Z","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/2608.09682/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tool-augmented vision-language models increasingly \"think with images\": they call crop, zoom, or code tools and reason over the returned pixels. However, recent work using blind tests, gain decompositions, and attention analyses has shown that returned images contribute little, raising the question: if pixels do not carry the gain, what does? We hypothesize that the load-bearing signal is the structured text emitted before any returned pixel arrives: tool name, coordinates, target description, and intent. This textual scaffold encodes where to look and what to find. We introduce TextCall (call","authors_text":"Ceyuan Yang, Jiahao Shao, Yinghao Xu, Yiyi Liao, Yuanbo Yang, Yujun Shen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T14:52:10Z","title":"Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09682","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":"sha256:8429d14246cdb2e48c0e5e3a8e3520c03062e57d2a7d42ce0b264176b621139d","target":"record","created_at":"2026-08-11T02:24:48Z","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":"8afba20b057909fd8b388f5886bf6830cc1db2b33458ac0b4f513f1481ee4dfc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T14:52:10Z","title_canon_sha256":"4e60991bfcf06369183d5843d332f46e8a56fb988e60292cb9236e4edfecec05"},"schema_version":"1.0","source":{"id":"2608.09682","kind":"arxiv","version":1}},"canonical_sha256":"f55c25805c359a54d01de47f582ac04d3ab82be9014d2e360207cab58f75b68d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f55c25805c359a54d01de47f582ac04d3ab82be9014d2e360207cab58f75b68d","first_computed_at":"2026-08-11T02:24:48.439649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:24:48.439649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AvzSku1EeY/H+kp9KvwB84frRD8/IzQGZORtSCg40aO6oOdvuMwbJ6jTewGn/jemh594v3FvI2VmibXtNP1qDw==","signature_status":"signed_v1","signed_at":"2026-08-11T02:24:48.441413Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.09682","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8429d14246cdb2e48c0e5e3a8e3520c03062e57d2a7d42ce0b264176b621139d","sha256:8fdc0a5d9c99746412efd6055ce06863db3a8b12fe810982753a7f0f6118dc58"],"state_sha256":"4571f647d1aaa31eac0b8ae540f9ba88c38f8218effad01bb2e1789681a76116"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5oYJXr8iVPjqWqLYKkBc8ce5svKY6+cVvkK+qVEjG5JIdXlA0XRi2bfGQqLTyhd7KG/9ZL4a/K7Dd96H56CwAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T15:48:54.658274Z","bundle_sha256":"31b9c33e06f1e8b0110a5c6ccd69f0b025eba475a7f48118bb3814705a4493aa"}}