{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UYHPPMKUN6A4R72BLTQOHBLORI","short_pith_number":"pith:UYHPPMKU","schema_version":"1.0","canonical_sha256":"a60ef7b1546f81c8ff415ce0e3856e8a195eb98ce323fc00878aff0bfd97d381","source":{"kind":"arxiv","id":"2605.15672","version":1},"attestation_state":"computed","paper":{"title":"VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Albert No, Dongjae Jeon, Hyesoo Hong, Minsoo Kim, Sangyeon Yoon, Wonje Jeung","submitted_at":"2026-05-15T06:48:53Z","abstract_excerpt":"Vision-language models (VLMs) achieve strong performance on multimodal benchmarks, but may still lack robust control over basic visual operations. We study \\textit{line tracing}, where a model must follow a selected visual path through successive local continuations. To isolate this ability, we design controlled tracing tasks that introduce nearby competitors while reducing semantic and topological ambiguity such as crossings and overlaps. Across these tasks, even state-of-the-art VLMs frequently lose the target path and switch to nearby alternatives, especially when those alternatives look lo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.15672","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T06:48:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"65b83806028285b40d29f3c2c13f6e19a94702d7454b500427ab15e59eaa91fa","abstract_canon_sha256":"fe8ad0c55710d3f3378e248ecb51bc069fb2f228a55b2e27956e4fe100a49e86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:11.474617Z","signature_b64":"Q875ceWEzyjGY5FNE+luXPn6FlYpD/4p0YxDqgWxLyUJ7S89/DuX/i4OumiDXiFCSMTo1cplKjtk2svs81Z6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a60ef7b1546f81c8ff415ce0e3856e8a195eb98ce323fc00878aff0bfd97d381","last_reissued_at":"2026-05-20T00:01:11.473562Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:11.473562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Albert No, Dongjae Jeon, Hyesoo Hong, Minsoo Kim, Sangyeon Yoon, Wonje Jeung","submitted_at":"2026-05-15T06:48:53Z","abstract_excerpt":"Vision-language models (VLMs) achieve strong performance on multimodal benchmarks, but may still lack robust control over basic visual operations. We study \\textit{line tracing}, where a model must follow a selected visual path through successive local continuations. To isolate this ability, we design controlled tracing tasks that introduce nearby competitors while reducing semantic and topological ambiguity such as crossings and overlaps. Across these tasks, even state-of-the-art VLMs frequently lose the target path and switch to nearby alternatives, especially when those alternatives look lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15672","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/2605.15672/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:34.070620Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:21:56.062351Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"8e1e9f4c5052c30ca295da39af4d28ca69d1523c39b08775b76f21d13b53de82"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.15672","created_at":"2026-05-20T00:01:11.473704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15672v1","created_at":"2026-05-20T00:01:11.473704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15672","created_at":"2026-05-20T00:01:11.473704+00:00"},{"alias_kind":"pith_short_12","alias_value":"UYHPPMKUN6A4","created_at":"2026-05-20T00:01:11.473704+00:00"},{"alias_kind":"pith_short_16","alias_value":"UYHPPMKUN6A4R72B","created_at":"2026-05-20T00:01:11.473704+00:00"},{"alias_kind":"pith_short_8","alias_value":"UYHPPMKU","created_at":"2026-05-20T00:01:11.473704+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UYHPPMKUN6A4R72BLTQOHBLORI","json":"https://pith.science/pith/UYHPPMKUN6A4R72BLTQOHBLORI.json","graph_json":"https://pith.science/api/pith-number/UYHPPMKUN6A4R72BLTQOHBLORI/graph.json","events_json":"https://pith.science/api/pith-number/UYHPPMKUN6A4R72BLTQOHBLORI/events.json","paper":"https://pith.science/paper/UYHPPMKU"},"agent_actions":{"view_html":"https://pith.science/pith/UYHPPMKUN6A4R72BLTQOHBLORI","download_json":"https://pith.science/pith/UYHPPMKUN6A4R72BLTQOHBLORI.json","view_paper":"https://pith.science/paper/UYHPPMKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15672&json=true","fetch_graph":"https://pith.science/api/pith-number/UYHPPMKUN6A4R72BLTQOHBLORI/graph.json","fetch_events":"https://pith.science/api/pith-number/UYHPPMKUN6A4R72BLTQOHBLORI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UYHPPMKUN6A4R72BLTQOHBLORI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UYHPPMKUN6A4R72BLTQOHBLORI/action/storage_attestation","attest_author":"https://pith.science/pith/UYHPPMKUN6A4R72BLTQOHBLORI/action/author_attestation","sign_citation":"https://pith.science/pith/UYHPPMKUN6A4R72BLTQOHBLORI/action/citation_signature","submit_replication":"https://pith.science/pith/UYHPPMKUN6A4R72BLTQOHBLORI/action/replication_record"}},"created_at":"2026-05-20T00:01:11.473704+00:00","updated_at":"2026-05-20T00:01:11.473704+00:00"}