{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FPWTMOSYYVP42ATWA4MJTWGSKH","short_pith_number":"pith:FPWTMOSY","canonical_record":{"source":{"id":"2304.14986","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-28T17:10:08Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"111b082440b52f258a2395035261478d50a5370e8b53b8839890de7eed2d14e6","abstract_canon_sha256":"1ae4b0c427232a28decc0f029c48d67038fa30cda5d6b9b741e4deea6ead1922"},"schema_version":"1.0"},"canonical_sha256":"2bed363a58c55fcd0276071899d8d251eecf99fc557941594ac8cce37ec3d32b","source":{"kind":"arxiv","id":"2304.14986","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14986","created_at":"2026-07-05T06:53:37Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14986v2","created_at":"2026-07-05T06:53:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14986","created_at":"2026-07-05T06:53:37Z"},{"alias_kind":"pith_short_12","alias_value":"FPWTMOSYYVP4","created_at":"2026-07-05T06:53:37Z"},{"alias_kind":"pith_short_16","alias_value":"FPWTMOSYYVP42ATW","created_at":"2026-07-05T06:53:37Z"},{"alias_kind":"pith_short_8","alias_value":"FPWTMOSY","created_at":"2026-07-05T06:53:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FPWTMOSYYVP42ATWA4MJTWGSKH","target":"record","payload":{"canonical_record":{"source":{"id":"2304.14986","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-28T17:10:08Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"111b082440b52f258a2395035261478d50a5370e8b53b8839890de7eed2d14e6","abstract_canon_sha256":"1ae4b0c427232a28decc0f029c48d67038fa30cda5d6b9b741e4deea6ead1922"},"schema_version":"1.0"},"canonical_sha256":"2bed363a58c55fcd0276071899d8d251eecf99fc557941594ac8cce37ec3d32b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:37.184158Z","signature_b64":"IIDf0nkqIX95WQBJeCwxsGKZ90gJ7qNdxPl/uCaG15jpwN9scCmD2LsgHo/4qA087McM6erIgnlI8WmTkcJ9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bed363a58c55fcd0276071899d8d251eecf99fc557941594ac8cce37ec3d32b","last_reissued_at":"2026-07-05T06:53:37.183632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:37.183632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.14986","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:53:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v7DO4xfLSy3HKYIvCCxSHgHYimuZO8z4gX+OQh05ARlEv6S8qyESaqPQy2neteB1COnn+iw7NlGWlbl+dnPPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T00:49:07.546008Z"},"content_sha256":"0d5627fe09532621c1b0987e695d954be07a35dad221058711c34a404f2f4b40","schema_version":"1.0","event_id":"sha256:0d5627fe09532621c1b0987e695d954be07a35dad221058711c34a404f2f4b40"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FPWTMOSYYVP42ATWA4MJTWGSKH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Interpreting Vision and Language Generative Models with Semantic Visual Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Albert Gatt, Kees van Deemter, Lina M. Rojas-Barahona, Michele Cafagna","submitted_at":"2023-04-28T17:10:08Z","abstract_excerpt":"When applied to Image-to-text models, interpretability methods often provide token-by-token explanations namely, they compute a visual explanation for each token of the generated sequence. Those explanations are expensive to compute and unable to comprehensively explain the model's output. Therefore, these models often require some sort of approximation that eventually leads to misleading explanations. We develop a framework based on SHAP, that allows for generating comprehensive, meaningful explanations leveraging the meaning representation of the output sequence as a whole. Moreover, by expl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14986","kind":"arxiv","version":2},"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/2304.14986/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:53:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UDYN6m0mvDjJukqpBMYj6/C7TFYybx3TXhFZGRvIaVe3Y2EjAmHajvE0zid+XgkHZ6xkPGD/jaMV3XV34LEOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T00:49:07.548459Z"},"content_sha256":"4de8f5c98cc5ab204024f440b62f43bf1469fb93399dc01fa4c4a62396281dff","schema_version":"1.0","event_id":"sha256:4de8f5c98cc5ab204024f440b62f43bf1469fb93399dc01fa4c4a62396281dff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FPWTMOSYYVP42ATWA4MJTWGSKH/bundle.json","state_url":"https://pith.science/pith/FPWTMOSYYVP42ATWA4MJTWGSKH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FPWTMOSYYVP42ATWA4MJTWGSKH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-24T00:49:07Z","links":{"resolver":"https://pith.science/pith/FPWTMOSYYVP42ATWA4MJTWGSKH","bundle":"https://pith.science/pith/FPWTMOSYYVP42ATWA4MJTWGSKH/bundle.json","state":"https://pith.science/pith/FPWTMOSYYVP42ATWA4MJTWGSKH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FPWTMOSYYVP42ATWA4MJTWGSKH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FPWTMOSYYVP42ATWA4MJTWGSKH","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":"1ae4b0c427232a28decc0f029c48d67038fa30cda5d6b9b741e4deea6ead1922","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-28T17:10:08Z","title_canon_sha256":"111b082440b52f258a2395035261478d50a5370e8b53b8839890de7eed2d14e6"},"schema_version":"1.0","source":{"id":"2304.14986","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14986","created_at":"2026-07-05T06:53:37Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14986v2","created_at":"2026-07-05T06:53:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14986","created_at":"2026-07-05T06:53:37Z"},{"alias_kind":"pith_short_12","alias_value":"FPWTMOSYYVP4","created_at":"2026-07-05T06:53:37Z"},{"alias_kind":"pith_short_16","alias_value":"FPWTMOSYYVP42ATW","created_at":"2026-07-05T06:53:37Z"},{"alias_kind":"pith_short_8","alias_value":"FPWTMOSY","created_at":"2026-07-05T06:53:37Z"}],"graph_snapshots":[{"event_id":"sha256:4de8f5c98cc5ab204024f440b62f43bf1469fb93399dc01fa4c4a62396281dff","target":"graph","created_at":"2026-07-05T06:53:37Z","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/2304.14986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When applied to Image-to-text models, interpretability methods often provide token-by-token explanations namely, they compute a visual explanation for each token of the generated sequence. Those explanations are expensive to compute and unable to comprehensively explain the model's output. Therefore, these models often require some sort of approximation that eventually leads to misleading explanations. We develop a framework based on SHAP, that allows for generating comprehensive, meaningful explanations leveraging the meaning representation of the output sequence as a whole. Moreover, by expl","authors_text":"Albert Gatt, Kees van Deemter, Lina M. Rojas-Barahona, Michele Cafagna","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-28T17:10:08Z","title":"Interpreting Vision and Language Generative Models with Semantic Visual Priors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14986","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":"sha256:0d5627fe09532621c1b0987e695d954be07a35dad221058711c34a404f2f4b40","target":"record","created_at":"2026-07-05T06:53:37Z","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":"1ae4b0c427232a28decc0f029c48d67038fa30cda5d6b9b741e4deea6ead1922","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-28T17:10:08Z","title_canon_sha256":"111b082440b52f258a2395035261478d50a5370e8b53b8839890de7eed2d14e6"},"schema_version":"1.0","source":{"id":"2304.14986","kind":"arxiv","version":2}},"canonical_sha256":"2bed363a58c55fcd0276071899d8d251eecf99fc557941594ac8cce37ec3d32b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bed363a58c55fcd0276071899d8d251eecf99fc557941594ac8cce37ec3d32b","first_computed_at":"2026-07-05T06:53:37.183632Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:53:37.183632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IIDf0nkqIX95WQBJeCwxsGKZ90gJ7qNdxPl/uCaG15jpwN9scCmD2LsgHo/4qA087McM6erIgnlI8WmTkcJ9Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:53:37.184158Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.14986","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d5627fe09532621c1b0987e695d954be07a35dad221058711c34a404f2f4b40","sha256:4de8f5c98cc5ab204024f440b62f43bf1469fb93399dc01fa4c4a62396281dff"],"state_sha256":"b7badd9185299b34191bfbfc2ea078d91d92e6cf44f8e0d80c0d646e726bb313"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8vB8+V0Balq69C0XZYL4iXQKWdCBpHkStvp0NEARJOarvHFLxN80+kFGHL5dP39WLYzyxYpK+0FJoeC5I1ZmAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T00:49:07.553718Z","bundle_sha256":"21dce6ac48257b7075ed6ffdd9c9ef6eb6fa948c38e3c233daaf8de19d17309c"}}