{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YQKWMRID7BLHSJ4GTHWJMY65F7","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":"6df3d42b66e56170f19c828535c05731e32753d1df7b79b7f7609053966849a0","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T16:55:32Z","title_canon_sha256":"9f237381de49ff9065e8db1921f758f891d2e481d4194623df0b133c3038bfda"},"schema_version":"1.0","source":{"id":"2506.07936","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07936","created_at":"2026-07-05T11:18:35Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07936v1","created_at":"2026-07-05T11:18:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07936","created_at":"2026-07-05T11:18:35Z"},{"alias_kind":"pith_short_12","alias_value":"YQKWMRID7BLH","created_at":"2026-07-05T11:18:35Z"},{"alias_kind":"pith_short_16","alias_value":"YQKWMRID7BLHSJ4G","created_at":"2026-07-05T11:18:35Z"},{"alias_kind":"pith_short_8","alias_value":"YQKWMRID","created_at":"2026-07-05T11:18:35Z"}],"graph_snapshots":[{"event_id":"sha256:22ad608ce001ae89302c6e6235dac450a5266fd6c97d35bdffd7105d6bde8959","target":"graph","created_at":"2026-07-05T11:18:35Z","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/2506.07936/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) are widely assumed to exhibit in-context learning (ICL), a property similar to that of their language-only counterparts. While recent work suggests VLMs can perform multimodal ICL (MM-ICL), studies show they often rely on shallow heuristics -- such as copying or majority voting -- rather than true task understanding. We revisit this assumption by evaluating VLMs under distribution shifts, where support examples come from a dataset different from the query. Surprisingly, performance often degrades with more demonstrations, and models tend to copy answers rather tha","authors_text":"Chengyue Huang, Jingyun Xiao, Moises Andrade, Shivang Chopra, Sichen Zhu, Yuchen Zhu, Zsolt Kira","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T16:55:32Z","title":"Mimicking or Reasoning: Rethinking Multi-Modal In-Context Learning in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07936","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:fb70161ce393c4afa2f9fca9ece8ec7b3068b158da005ee77ba77f8ac8626748","target":"record","created_at":"2026-07-05T11:18:35Z","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":"6df3d42b66e56170f19c828535c05731e32753d1df7b79b7f7609053966849a0","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T16:55:32Z","title_canon_sha256":"9f237381de49ff9065e8db1921f758f891d2e481d4194623df0b133c3038bfda"},"schema_version":"1.0","source":{"id":"2506.07936","kind":"arxiv","version":1}},"canonical_sha256":"c415664503f85679278699ec9663dd2fed634893681b4c1f3e00df1979e93f8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c415664503f85679278699ec9663dd2fed634893681b4c1f3e00df1979e93f8d","first_computed_at":"2026-07-05T11:18:35.687004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:35.687004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A6VZOvIdFs3xflkb6/dqLXNpagIMd69jeHmECWSxgalDvUB8eedNO5f5m2GDFHUAbISlZKvimsktCyZeQf3iAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:35.687462Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07936","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb70161ce393c4afa2f9fca9ece8ec7b3068b158da005ee77ba77f8ac8626748","sha256:22ad608ce001ae89302c6e6235dac450a5266fd6c97d35bdffd7105d6bde8959"],"state_sha256":"64ee4b52ef7dd18b3c08db61474bae76ca3fa411a0e1375ba4e3c39c18b82345"}