{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3A2N7B4PQHNEVGRQHUFEGTUCO4","short_pith_number":"pith:3A2N7B4P","schema_version":"1.0","canonical_sha256":"d834df878f81da4a9a303d0a434e82771a8a8408ff2175efd2b7898e9bcdb864","source":{"kind":"arxiv","id":"2606.17423","version":1},"attestation_state":"computed","paper":{"title":"Martingale Doppelg\\\"anger-Eval: An Identification Framework for Auditing Candlestick Understanding in Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"q-fin.CP","authors_text":"Ziyao Wang","submitted_at":"2026-06-16T02:10:37Z","abstract_excerpt":"We introduce Martingale Doppelg\\\"anger-Eval, a public shadow-market benchmark for auditing whether vision-language models (VLMs) use candlestick evidence rather than extrapolate past trends. The central difficulty is identification: on real market histories, chart evidence and trend are strongly coupled, so an observational score cannot determine whether a fluent technical-analysis narrative is grounded in local visual evidence. We prove this limitation formally: no evaluation functional computed from observational chart--label data can distinguish a grounded responder from a trend-shortcut re"},"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":"2606.17423","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.CP","submitted_at":"2026-06-16T02:10:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4ab0a5661d1536b1757b4c9a0c7bbc40194871ea06406d9c678d2140475b1def","abstract_canon_sha256":"619f5644b5f9190ece25a44f4a96f198a3c023e6d07c502ad8beaf18b02bd546"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:12.456739Z","signature_b64":"0rSK/6rmCmKpGJ9Lj9aFcDvUJYFpH9ep3V9rmhx3of/iI6PlRacl0FSDDu4VrxW2odpkW9jlH5/8rclbStFYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d834df878f81da4a9a303d0a434e82771a8a8408ff2175efd2b7898e9bcdb864","last_reissued_at":"2026-06-19T16:10:12.456393Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:12.456393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Martingale Doppelg\\\"anger-Eval: An Identification Framework for Auditing Candlestick Understanding in Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"q-fin.CP","authors_text":"Ziyao Wang","submitted_at":"2026-06-16T02:10:37Z","abstract_excerpt":"We introduce Martingale Doppelg\\\"anger-Eval, a public shadow-market benchmark for auditing whether vision-language models (VLMs) use candlestick evidence rather than extrapolate past trends. The central difficulty is identification: on real market histories, chart evidence and trend are strongly coupled, so an observational score cannot determine whether a fluent technical-analysis narrative is grounded in local visual evidence. We prove this limitation formally: no evaluation functional computed from observational chart--label data can distinguish a grounded responder from a trend-shortcut re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17423","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/2606.17423/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.17423","created_at":"2026-06-19T16:10:12.456457+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17423v1","created_at":"2026-06-19T16:10:12.456457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17423","created_at":"2026-06-19T16:10:12.456457+00:00"},{"alias_kind":"pith_short_12","alias_value":"3A2N7B4PQHNE","created_at":"2026-06-19T16:10:12.456457+00:00"},{"alias_kind":"pith_short_16","alias_value":"3A2N7B4PQHNEVGRQ","created_at":"2026-06-19T16:10:12.456457+00:00"},{"alias_kind":"pith_short_8","alias_value":"3A2N7B4P","created_at":"2026-06-19T16:10:12.456457+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/3A2N7B4PQHNEVGRQHUFEGTUCO4","json":"https://pith.science/pith/3A2N7B4PQHNEVGRQHUFEGTUCO4.json","graph_json":"https://pith.science/api/pith-number/3A2N7B4PQHNEVGRQHUFEGTUCO4/graph.json","events_json":"https://pith.science/api/pith-number/3A2N7B4PQHNEVGRQHUFEGTUCO4/events.json","paper":"https://pith.science/paper/3A2N7B4P"},"agent_actions":{"view_html":"https://pith.science/pith/3A2N7B4PQHNEVGRQHUFEGTUCO4","download_json":"https://pith.science/pith/3A2N7B4PQHNEVGRQHUFEGTUCO4.json","view_paper":"https://pith.science/paper/3A2N7B4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17423&json=true","fetch_graph":"https://pith.science/api/pith-number/3A2N7B4PQHNEVGRQHUFEGTUCO4/graph.json","fetch_events":"https://pith.science/api/pith-number/3A2N7B4PQHNEVGRQHUFEGTUCO4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3A2N7B4PQHNEVGRQHUFEGTUCO4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3A2N7B4PQHNEVGRQHUFEGTUCO4/action/storage_attestation","attest_author":"https://pith.science/pith/3A2N7B4PQHNEVGRQHUFEGTUCO4/action/author_attestation","sign_citation":"https://pith.science/pith/3A2N7B4PQHNEVGRQHUFEGTUCO4/action/citation_signature","submit_replication":"https://pith.science/pith/3A2N7B4PQHNEVGRQHUFEGTUCO4/action/replication_record"}},"created_at":"2026-06-19T16:10:12.456457+00:00","updated_at":"2026-06-19T16:10:12.456457+00:00"}