{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:L6EMPCJEGBN45NRTUOEWDSLNPR","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":"be1156b9ff7dc3e0003203a2267911d97217cb9929aa7e1dc03777337b1d6a2c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-16T17:12:06Z","title_canon_sha256":"339160add5af2936053e26ea4f4c48febad27d31c96ffe5e938c10b7ebaf8fef"},"schema_version":"1.0","source":{"id":"2310.10591","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10591","created_at":"2026-07-05T07:01:21Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10591v1","created_at":"2026-07-05T07:01:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10591","created_at":"2026-07-05T07:01:21Z"},{"alias_kind":"pith_short_12","alias_value":"L6EMPCJEGBN4","created_at":"2026-07-05T07:01:21Z"},{"alias_kind":"pith_short_16","alias_value":"L6EMPCJEGBN45NRT","created_at":"2026-07-05T07:01:21Z"},{"alias_kind":"pith_short_8","alias_value":"L6EMPCJE","created_at":"2026-07-05T07:01:21Z"}],"graph_snapshots":[{"event_id":"sha256:995628b23a2c33ec39de49eb8d3f1bcced8401dc0b9ceafcf77323951507d32f","target":"graph","created_at":"2026-07-05T07:01:21Z","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/2310.10591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale pre-trained vision foundation models, such as CLIP, have become de facto backbones for various vision tasks. However, due to their black-box nature, understanding the underlying rules behind these models' predictions and controlling model behaviors have remained open challenges. We present a framework for interpreting vision transformer's latent tokens with natural language. Given a latent token, our framework retains its semantic information to the final layer using transformer's local operations and retrieves the closest text for explanation. Our approach enables understanding of","authors_text":"Carl Vondrick, Chengzhi Mao, Haozhe Chen, Junfeng Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-16T17:12:06Z","title":"Interpreting and Controlling Vision Foundation Models via Text Explanations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10591","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:ec59dd093595e4433fdfb1e67637b98a77d0ffa600336fa02dd8be2f4fba790c","target":"record","created_at":"2026-07-05T07:01:21Z","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":"be1156b9ff7dc3e0003203a2267911d97217cb9929aa7e1dc03777337b1d6a2c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-16T17:12:06Z","title_canon_sha256":"339160add5af2936053e26ea4f4c48febad27d31c96ffe5e938c10b7ebaf8fef"},"schema_version":"1.0","source":{"id":"2310.10591","kind":"arxiv","version":1}},"canonical_sha256":"5f88c78924305bceb633a38961c96d7c587cf6dce53ed0a7b69f20f04f872a4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f88c78924305bceb633a38961c96d7c587cf6dce53ed0a7b69f20f04f872a4f","first_computed_at":"2026-07-05T07:01:21.981719Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:21.981719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"85YMXK9r1jLjsYaaaaDGODDO8VeVWsgKoa921OlZ4P2TmsaakNabGW2S/laMUgH+Viu4zX6RAzwVdZ7GlnrQDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:21.982133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.10591","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec59dd093595e4433fdfb1e67637b98a77d0ffa600336fa02dd8be2f4fba790c","sha256:995628b23a2c33ec39de49eb8d3f1bcced8401dc0b9ceafcf77323951507d32f"],"state_sha256":"186878fc8c05d6d799a969d149d067e4a9c1513c9d707ed5dcafb1b2bb60fa3d"}