{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2DRCF2GY5P3MFW7G6XVAVRNMKQ","short_pith_number":"pith:2DRCF2GY","schema_version":"1.0","canonical_sha256":"d0e222e8d8ebf6c2dbe6f5ea0ac5ac540785797218b058842800ff8e00a7b26a","source":{"kind":"arxiv","id":"2311.03547","version":2},"attestation_state":"computed","paper":{"title":"InterVLS: Interactive Model Understanding and Improvement with Vision-Language Surrogates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.HC","cs.LG"],"primary_cat":"cs.AI","authors_text":"Chris Bryan, Jinbin Huang, Liang Gou, Liu Ren, WenBin He","submitted_at":"2023-11-06T21:30:59Z","abstract_excerpt":"Deep learning models are widely used in critical applications, highlighting the need for pre-deployment model understanding and improvement. Visual concept-based methods, while increasingly used for this purpose, face challenges: (1) most concepts lack interpretability, (2) existing methods require model knowledge, often unavailable at run time. Additionally, (3) there lacks a no-code method for post-understanding model improvement. Addressing these, we present InterVLS. The system facilitates model understanding by discovering text-aligned concepts, measuring their influence with model-agnost"},"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":"2311.03547","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-11-06T21:30:59Z","cross_cats_sorted":["cs.CV","cs.HC","cs.LG"],"title_canon_sha256":"d156a588bb06041af3d3a74b3e9caee15d84a2ee3349fac4b2af81273bff32de","abstract_canon_sha256":"19d3f13861535b4e6fc112428ed6fbd2328dc92c15a8d9d74617859c3e626fb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:04.346806Z","signature_b64":"YLymLxk7TY1//M/juBl2SzCiEekgEn9dMzwrNtd46qf8rT7xmiNj+NdfTpONXxvMNbNA5/Nac07UFoVOo9XMAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0e222e8d8ebf6c2dbe6f5ea0ac5ac540785797218b058842800ff8e00a7b26a","last_reissued_at":"2026-07-05T08:37:04.346366Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:04.346366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InterVLS: Interactive Model Understanding and Improvement with Vision-Language Surrogates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.HC","cs.LG"],"primary_cat":"cs.AI","authors_text":"Chris Bryan, Jinbin Huang, Liang Gou, Liu Ren, WenBin He","submitted_at":"2023-11-06T21:30:59Z","abstract_excerpt":"Deep learning models are widely used in critical applications, highlighting the need for pre-deployment model understanding and improvement. Visual concept-based methods, while increasingly used for this purpose, face challenges: (1) most concepts lack interpretability, (2) existing methods require model knowledge, often unavailable at run time. Additionally, (3) there lacks a no-code method for post-understanding model improvement. Addressing these, we present InterVLS. The system facilitates model understanding by discovering text-aligned concepts, measuring their influence with model-agnost"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.03547","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/2311.03547/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":"2311.03547","created_at":"2026-07-05T08:37:04.346428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.03547v2","created_at":"2026-07-05T08:37:04.346428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.03547","created_at":"2026-07-05T08:37:04.346428+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DRCF2GY5P3M","created_at":"2026-07-05T08:37:04.346428+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DRCF2GY5P3MFW7G","created_at":"2026-07-05T08:37:04.346428+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DRCF2GY","created_at":"2026-07-05T08:37:04.346428+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2DRCF2GY5P3MFW7G6XVAVRNMKQ","json":"https://pith.science/pith/2DRCF2GY5P3MFW7G6XVAVRNMKQ.json","graph_json":"https://pith.science/api/pith-number/2DRCF2GY5P3MFW7G6XVAVRNMKQ/graph.json","events_json":"https://pith.science/api/pith-number/2DRCF2GY5P3MFW7G6XVAVRNMKQ/events.json","paper":"https://pith.science/paper/2DRCF2GY"},"agent_actions":{"view_html":"https://pith.science/pith/2DRCF2GY5P3MFW7G6XVAVRNMKQ","download_json":"https://pith.science/pith/2DRCF2GY5P3MFW7G6XVAVRNMKQ.json","view_paper":"https://pith.science/paper/2DRCF2GY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.03547&json=true","fetch_graph":"https://pith.science/api/pith-number/2DRCF2GY5P3MFW7G6XVAVRNMKQ/graph.json","fetch_events":"https://pith.science/api/pith-number/2DRCF2GY5P3MFW7G6XVAVRNMKQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DRCF2GY5P3MFW7G6XVAVRNMKQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DRCF2GY5P3MFW7G6XVAVRNMKQ/action/storage_attestation","attest_author":"https://pith.science/pith/2DRCF2GY5P3MFW7G6XVAVRNMKQ/action/author_attestation","sign_citation":"https://pith.science/pith/2DRCF2GY5P3MFW7G6XVAVRNMKQ/action/citation_signature","submit_replication":"https://pith.science/pith/2DRCF2GY5P3MFW7G6XVAVRNMKQ/action/replication_record"}},"created_at":"2026-07-05T08:37:04.346428+00:00","updated_at":"2026-07-05T08:37:04.346428+00:00"}