{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FH3XBLA24G3N7F4KLOBPMTI4SW","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":"036a04298c9f3068979c7decc97d1dc7f7698754347a5f4e4503e0100afa12b0","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-08T22:18:53Z","title_canon_sha256":"d825ea2be6fd6003f1c9718032ddefe7bd898a149cd61a10db64bea82eca70cc"},"schema_version":"1.0","source":{"id":"2311.05043","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.05043","created_at":"2026-07-05T07:10:53Z"},{"alias_kind":"arxiv_version","alias_value":"2311.05043v1","created_at":"2026-07-05T07:10:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05043","created_at":"2026-07-05T07:10:53Z"},{"alias_kind":"pith_short_12","alias_value":"FH3XBLA24G3N","created_at":"2026-07-05T07:10:53Z"},{"alias_kind":"pith_short_16","alias_value":"FH3XBLA24G3N7F4K","created_at":"2026-07-05T07:10:53Z"},{"alias_kind":"pith_short_8","alias_value":"FH3XBLA2","created_at":"2026-07-05T07:10:53Z"}],"graph_snapshots":[{"event_id":"sha256:9a62c67f4a631bf496707c6d4f7e0bce74bb2c5f0b4b5a39e2f161e74658bee6","target":"graph","created_at":"2026-07-05T07:10:53Z","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/2311.05043/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Converting a model's internals to text can yield human-understandable insights about the model. Inspired by the recent success of training-free approaches for image captioning, we propose ZS-A2T, a zero-shot framework that translates the transformer attention of a given model into natural language without requiring any training. We consider this in the context of Visual Question Answering (VQA). ZS-A2T builds on a pre-trained large language model (LLM), which receives a task prompt, question, and predicted answer, as inputs. The LLM is guided to select tokens which describe the regions in the ","authors_text":"A. Sophia Koepke, Hendrik P. A. Lensch, Leonard Salewski, Zeynep Akata","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-08T22:18:53Z","title":"Zero-shot Translation of Attention Patterns in VQA Models to Natural Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05043","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":"sha256:2641ca8d1657f2d723046eaf4c7ecd4db2f0165589af06c102b45691af451648","target":"record","created_at":"2026-07-05T07:10:53Z","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":"036a04298c9f3068979c7decc97d1dc7f7698754347a5f4e4503e0100afa12b0","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-08T22:18:53Z","title_canon_sha256":"d825ea2be6fd6003f1c9718032ddefe7bd898a149cd61a10db64bea82eca70cc"},"schema_version":"1.0","source":{"id":"2311.05043","kind":"arxiv","version":1}},"canonical_sha256":"29f770ac1ae1b6df978a5b82f64d1c9585454351f72d76e961a0e3c13327bb93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29f770ac1ae1b6df978a5b82f64d1c9585454351f72d76e961a0e3c13327bb93","first_computed_at":"2026-07-05T07:10:53.882220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:10:53.882220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kc4ftb6sO7cA2DiMG3Sruu8jMshmIX/lJT/1KfQSBgNMynDpMsU2QUYkMW8sJFCD2Jsx3X92jwCgnS5VaKZ+Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:10:53.882556Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.05043","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2641ca8d1657f2d723046eaf4c7ecd4db2f0165589af06c102b45691af451648","sha256:9a62c67f4a631bf496707c6d4f7e0bce74bb2c5f0b4b5a39e2f161e74658bee6"],"state_sha256":"c3c37ff091976018b0f0363ddf4153e0a07a9ef7225b59da2c91faae209f7ccd"}