{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HY4ULPRJN6JFB6MMCPHDZWFOT6","short_pith_number":"pith:HY4ULPRJ","schema_version":"1.0","canonical_sha256":"3e3945be296f9250f98c13ce3cd8ae9f92dbbbf3a5872403e284e137b13c8f2d","source":{"kind":"arxiv","id":"2412.16277","version":1},"attestation_state":"computed","paper":{"title":"Mapping the Mind of an Instruction-based Image Editing using SMILE","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.HC"],"primary_cat":"cs.AI","authors_text":"Adil Khan, Ad\\'in Ram\\'irez Rivera, Franky George, Koorosh Aslansefat, Muhammad Khalid, Zeinab Dehghani","submitted_at":"2024-12-20T18:33:23Z","abstract_excerpt":"Despite recent advancements in Instruct-based Image Editing models for generating high-quality images, they are known as black boxes and a significant barrier to transparency and user trust. To solve this issue, we introduce SMILE (Statistical Model-agnostic Interpretability with Local Explanations), a novel model-agnostic for localized interpretability that provides a visual heatmap to clarify the textual elements' influence on image-generating models. We applied our method to various Instruction-based Image Editing models like Pix2Pix, Image2Image-turbo and Diffusers-Inpaint and showed how o"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.16277","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-20T18:33:23Z","cross_cats_sorted":["cs.CV","cs.HC"],"title_canon_sha256":"54ec02adf37ed2c930c790e3c8de3ef4797129638193a9cd11a6e116b5e21888","abstract_canon_sha256":"7fb7684a40afce7050d224f282e7e5d91194fd1aa36f600a9ba17b5e9e0c2042"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:44.152190Z","signature_b64":"8oBjV/FhjTO8osPQQfJVCT4gdrzPOI6RvZNGW2dba9G76wJ5yE6MjU2CSmWTVX6WArOR1b03LzQgo702liRMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e3945be296f9250f98c13ce3cd8ae9f92dbbbf3a5872403e284e137b13c8f2d","last_reissued_at":"2026-07-05T09:52:44.151737Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:44.151737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mapping the Mind of an Instruction-based Image Editing using SMILE","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.HC"],"primary_cat":"cs.AI","authors_text":"Adil Khan, Ad\\'in Ram\\'irez Rivera, Franky George, Koorosh Aslansefat, Muhammad Khalid, Zeinab Dehghani","submitted_at":"2024-12-20T18:33:23Z","abstract_excerpt":"Despite recent advancements in Instruct-based Image Editing models for generating high-quality images, they are known as black boxes and a significant barrier to transparency and user trust. To solve this issue, we introduce SMILE (Statistical Model-agnostic Interpretability with Local Explanations), a novel model-agnostic for localized interpretability that provides a visual heatmap to clarify the textual elements' influence on image-generating models. We applied our method to various Instruction-based Image Editing models like Pix2Pix, Image2Image-turbo and Diffusers-Inpaint and showed how o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16277","kind":"arxiv","version":1},"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/2412.16277/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.16277","created_at":"2026-07-05T09:52:44.151795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16277v1","created_at":"2026-07-05T09:52:44.151795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16277","created_at":"2026-07-05T09:52:44.151795+00:00"},{"alias_kind":"pith_short_12","alias_value":"HY4ULPRJN6JF","created_at":"2026-07-05T09:52:44.151795+00:00"},{"alias_kind":"pith_short_16","alias_value":"HY4ULPRJN6JFB6MM","created_at":"2026-07-05T09:52:44.151795+00:00"},{"alias_kind":"pith_short_8","alias_value":"HY4ULPRJ","created_at":"2026-07-05T09:52:44.151795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.03626","citing_title":"Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HY4ULPRJN6JFB6MMCPHDZWFOT6","json":"https://pith.science/pith/HY4ULPRJN6JFB6MMCPHDZWFOT6.json","graph_json":"https://pith.science/api/pith-number/HY4ULPRJN6JFB6MMCPHDZWFOT6/graph.json","events_json":"https://pith.science/api/pith-number/HY4ULPRJN6JFB6MMCPHDZWFOT6/events.json","paper":"https://pith.science/paper/HY4ULPRJ"},"agent_actions":{"view_html":"https://pith.science/pith/HY4ULPRJN6JFB6MMCPHDZWFOT6","download_json":"https://pith.science/pith/HY4ULPRJN6JFB6MMCPHDZWFOT6.json","view_paper":"https://pith.science/paper/HY4ULPRJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16277&json=true","fetch_graph":"https://pith.science/api/pith-number/HY4ULPRJN6JFB6MMCPHDZWFOT6/graph.json","fetch_events":"https://pith.science/api/pith-number/HY4ULPRJN6JFB6MMCPHDZWFOT6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HY4ULPRJN6JFB6MMCPHDZWFOT6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HY4ULPRJN6JFB6MMCPHDZWFOT6/action/storage_attestation","attest_author":"https://pith.science/pith/HY4ULPRJN6JFB6MMCPHDZWFOT6/action/author_attestation","sign_citation":"https://pith.science/pith/HY4ULPRJN6JFB6MMCPHDZWFOT6/action/citation_signature","submit_replication":"https://pith.science/pith/HY4ULPRJN6JFB6MMCPHDZWFOT6/action/replication_record"}},"created_at":"2026-07-05T09:52:44.151795+00:00","updated_at":"2026-07-05T09:52:44.151795+00:00"}