{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IRPP6HHPJJDFGVTHERMQX3CUFJ","short_pith_number":"pith:IRPP6HHP","schema_version":"1.0","canonical_sha256":"445eff1cef4a4653566724590bec542a7f69b8e5df10bc69d8243f8dbe271be3","source":{"kind":"arxiv","id":"2403.14566","version":2},"attestation_state":"computed","paper":{"title":"A survey on Concept-based Approaches For Model Improvement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Avani Gupta, P J Narayanan","submitted_at":"2024-03-21T17:09:20Z","abstract_excerpt":"The focus of recent research has shifted from merely improving the metrics based performance of Deep Neural Networks (DNNs) to DNNs which are more interpretable to humans. The field of eXplainable Artificial Intelligence (XAI) has observed various techniques, including saliency-based and concept-based approaches. These approaches explain the model's decisions in simple human understandable terms called Concepts. Concepts are known to be the thinking ground of humans}. Explanations in terms of concepts enable detecting spurious correlations, inherent biases, or clever-hans. With the advent of c"},"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":"2403.14566","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-21T17:09:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dae9da36242ff129f33e045058e636908b21a0c4203d39a5e9aa4360e05c17b6","abstract_canon_sha256":"5640972e442974e2a1e017d3e85ad3c08005aed12a3713dc81be85104ac76240"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:04.350731Z","signature_b64":"JS4f195/8UUC7PQmpQyaWNuDHpS63jJTs52ncQ/gXdAlaC8PtNKLCvr4q7xr1qgbAa5vlUOO/k2WUbDMw5BHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"445eff1cef4a4653566724590bec542a7f69b8e5df10bc69d8243f8dbe271be3","last_reissued_at":"2026-07-05T08:00:04.350286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:04.350286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A survey on Concept-based Approaches For Model Improvement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Avani Gupta, P J Narayanan","submitted_at":"2024-03-21T17:09:20Z","abstract_excerpt":"The focus of recent research has shifted from merely improving the metrics based performance of Deep Neural Networks (DNNs) to DNNs which are more interpretable to humans. The field of eXplainable Artificial Intelligence (XAI) has observed various techniques, including saliency-based and concept-based approaches. These approaches explain the model's decisions in simple human understandable terms called Concepts. Concepts are known to be the thinking ground of humans}. Explanations in terms of concepts enable detecting spurious correlations, inherent biases, or clever-hans. With the advent of c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14566","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/2403.14566/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":"2403.14566","created_at":"2026-07-05T08:00:04.350350+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.14566v2","created_at":"2026-07-05T08:00:04.350350+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14566","created_at":"2026-07-05T08:00:04.350350+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRPP6HHPJJDF","created_at":"2026-07-05T08:00:04.350350+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRPP6HHPJJDFGVTH","created_at":"2026-07-05T08:00:04.350350+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRPP6HHP","created_at":"2026-07-05T08:00:04.350350+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/IRPP6HHPJJDFGVTHERMQX3CUFJ","json":"https://pith.science/pith/IRPP6HHPJJDFGVTHERMQX3CUFJ.json","graph_json":"https://pith.science/api/pith-number/IRPP6HHPJJDFGVTHERMQX3CUFJ/graph.json","events_json":"https://pith.science/api/pith-number/IRPP6HHPJJDFGVTHERMQX3CUFJ/events.json","paper":"https://pith.science/paper/IRPP6HHP"},"agent_actions":{"view_html":"https://pith.science/pith/IRPP6HHPJJDFGVTHERMQX3CUFJ","download_json":"https://pith.science/pith/IRPP6HHPJJDFGVTHERMQX3CUFJ.json","view_paper":"https://pith.science/paper/IRPP6HHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.14566&json=true","fetch_graph":"https://pith.science/api/pith-number/IRPP6HHPJJDFGVTHERMQX3CUFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/IRPP6HHPJJDFGVTHERMQX3CUFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRPP6HHPJJDFGVTHERMQX3CUFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRPP6HHPJJDFGVTHERMQX3CUFJ/action/storage_attestation","attest_author":"https://pith.science/pith/IRPP6HHPJJDFGVTHERMQX3CUFJ/action/author_attestation","sign_citation":"https://pith.science/pith/IRPP6HHPJJDFGVTHERMQX3CUFJ/action/citation_signature","submit_replication":"https://pith.science/pith/IRPP6HHPJJDFGVTHERMQX3CUFJ/action/replication_record"}},"created_at":"2026-07-05T08:00:04.350350+00:00","updated_at":"2026-07-05T08:00:04.350350+00:00"}