{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FVVYSV3JI2U24CVLMRQTXGRY7B","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":"066545b2225c1a89d04a6d5f779b9a2039063c7359f357ffd791312d2732e223","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-13T17:47:41Z","title_canon_sha256":"b60dfea678d41e9aa97d738274f97612b79e9bde7acf72e670f00ba528368f54"},"schema_version":"1.0","source":{"id":"2008.06035","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.06035","created_at":"2026-07-05T01:42:56Z"},{"alias_kind":"arxiv_version","alias_value":"2008.06035v2","created_at":"2026-07-05T01:42:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.06035","created_at":"2026-07-05T01:42:56Z"},{"alias_kind":"pith_short_12","alias_value":"FVVYSV3JI2U2","created_at":"2026-07-05T01:42:56Z"},{"alias_kind":"pith_short_16","alias_value":"FVVYSV3JI2U24CVL","created_at":"2026-07-05T01:42:56Z"},{"alias_kind":"pith_short_8","alias_value":"FVVYSV3J","created_at":"2026-07-05T01:42:56Z"}],"graph_snapshots":[{"event_id":"sha256:0bb43980810b70186f1dd7f3ffa5d53c978203ed141744e410ebaf1102d9464a","target":"graph","created_at":"2026-07-05T01:42:56Z","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/2008.06035/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of visually explaining similarity models, i.e., explaining why a model predicts two images to be similar in addition to producing a scalar score. While much recent work in visual model interpretability has focused on gradient-based attention, these methods rely on a classification module to generate visual explanations. Consequently, they cannot readily explain other kinds of models that do not use or need classification-like loss functions (e.g., similarity models trained with a metric learning loss). In this work, we bridge this crucial gap, presenting a method to gen","authors_text":"Meng Zheng, Richard J. Radke, Srikrishna Karanam, Terrence Chen, Ziyan Wu","cross_cats":["cs.AI","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-13T17:47:41Z","title":"Towards Visually Explaining Similarity Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.06035","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:a1770d47cd374262efdd046f3aa6c7e9bc4f1d903b9e4ef65c1c5eb958b115c2","target":"record","created_at":"2026-07-05T01:42:56Z","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":"066545b2225c1a89d04a6d5f779b9a2039063c7359f357ffd791312d2732e223","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-13T17:47:41Z","title_canon_sha256":"b60dfea678d41e9aa97d738274f97612b79e9bde7acf72e670f00ba528368f54"},"schema_version":"1.0","source":{"id":"2008.06035","kind":"arxiv","version":2}},"canonical_sha256":"2d6b89576946a9ae0aab64613b9a38f8601b6311a96bdebfe19ff4133d66fc5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d6b89576946a9ae0aab64613b9a38f8601b6311a96bdebfe19ff4133d66fc5e","first_computed_at":"2026-07-05T01:42:56.076737Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:42:56.076737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3LTS5eGdSOLr1FnRGW19J50Fic4tQcSk1ebKuXJwf52CW0AlSmyHG/8t7qCDNug8ZKy3ozm9AjQv/e/3je24CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:42:56.077149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.06035","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1770d47cd374262efdd046f3aa6c7e9bc4f1d903b9e4ef65c1c5eb958b115c2","sha256:0bb43980810b70186f1dd7f3ffa5d53c978203ed141744e410ebaf1102d9464a"],"state_sha256":"c6a3bb1dc0d7b85275f54877f8b252165af6397b9288a7ade8d0ee4b2120dea8"}