{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XHWROLYGU6IABZFS2OEX5M2XHM","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":"300372a0d41c52809a13edfdb0ac91cb22cfe20913949af16dccb18e1e0ca07e","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T17:59:45Z","title_canon_sha256":"d9a926d8c7ddc14d23d88653897954cd6080ee10f1ba8a60d3ecfb505ef41c2b"},"schema_version":"1.0","source":{"id":"2410.22330","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22330","created_at":"2026-07-05T10:59:48Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22330v2","created_at":"2026-07-05T10:59:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22330","created_at":"2026-07-05T10:59:48Z"},{"alias_kind":"pith_short_12","alias_value":"XHWROLYGU6IA","created_at":"2026-07-05T10:59:48Z"},{"alias_kind":"pith_short_16","alias_value":"XHWROLYGU6IABZFS","created_at":"2026-07-05T10:59:48Z"},{"alias_kind":"pith_short_8","alias_value":"XHWROLYG","created_at":"2026-07-05T10:59:48Z"}],"graph_snapshots":[{"event_id":"sha256:df64283d64702f95f721b0bbac6eb0ca788a483e34b1e7ebc8d3c8b41be2b77f","target":"graph","created_at":"2026-07-05T10:59:48Z","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/2410.22330/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregressive vision-language models (VLMs) can handle many tasks within a single model, yet the representations that enable this capability remain opaque. We find that VLMs align conceptually equivalent inputs into a shared task vector, which is invariant to modality (text, image) and format (examples, instruction), and may simplify VLM processing. We measure this alignment via cross-modal transfer -- the ability of a task vector derived in one modality to trigger the correct generation in another -- on a range of tasks and model architectures. Although the task vector is highly compressed, ","authors_text":"Amir Bar, Grace Luo, Trevor Darrell","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T17:59:45Z","title":"Vision-Language Models Create Cross-Modal Task Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22330","kind":"arxiv","version":2},"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:d5ffe37e0979b7364bf6074303664c3c8fd830a80f63268a7e00a5a449d74939","target":"record","created_at":"2026-07-05T10:59:48Z","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":"300372a0d41c52809a13edfdb0ac91cb22cfe20913949af16dccb18e1e0ca07e","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T17:59:45Z","title_canon_sha256":"d9a926d8c7ddc14d23d88653897954cd6080ee10f1ba8a60d3ecfb505ef41c2b"},"schema_version":"1.0","source":{"id":"2410.22330","kind":"arxiv","version":2}},"canonical_sha256":"b9ed172f06a79000e4b2d3897eb3573b0dae06af88767e222687be2e73506398","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9ed172f06a79000e4b2d3897eb3573b0dae06af88767e222687be2e73506398","first_computed_at":"2026-07-05T10:59:48.083005Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:48.083005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PthU4HJfAROTaBdAu5Zkz6QOpa8OaEnIoGbGUUc3Rm7dCYAe63+lUMFJcl9H7aiObbhzFaVufOFvAFx0YjmpDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:48.083482Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.22330","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5ffe37e0979b7364bf6074303664c3c8fd830a80f63268a7e00a5a449d74939","sha256:df64283d64702f95f721b0bbac6eb0ca788a483e34b1e7ebc8d3c8b41be2b77f"],"state_sha256":"6c1566eb098755011f50cd3aa0f434f4a220d01e0b40bf99dc34e2ca4943e5cd"}