{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UYPYA65UMN2ZDYHJY7IERK6MF2","short_pith_number":"pith:UYPYA65U","schema_version":"1.0","canonical_sha256":"a61f807bb4637591e0e9c7d048abcc2e841cb3f59a1689530f2b5992b26cb6d1","source":{"kind":"arxiv","id":"2411.12643","version":2},"attestation_state":"computed","paper":{"title":"DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Chintan Chitroda, Neeraj Kumar Singh, Pratinav Seth, Vinay Kumar Sankarapu, Yashwardhan Rathore","submitted_at":"2024-11-19T16:54:30Z","abstract_excerpt":"The rapid growth of AI has led to more complex deep learning models, often operating as opaque \"black boxes\" with limited transparency in their decision-making. This lack of interpretability poses challenges, especially in high-stakes applications where understanding model output is crucial. This work highlights the importance of interpretability in fostering trust, accountability, and responsible deployment. To address these challenges, we introduce DLBacktrace, a novel, model-agnostic technique designed to provide clear insights into deep learning model decisions across a wide range of domai"},"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":"2411.12643","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-19T16:54:30Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"195a01ce934bb3f67b9fbd0f3bc3a0422c543f93f87d30949cd9555b7af49f52","abstract_canon_sha256":"fe78eded007364489eb643722d23ceb5b71b7b81e18e78c08bb5538c66523b7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:12.135191Z","signature_b64":"R0Uz6yArq0SBh9yfQ+pr2nLdtldQsOhvo7wISVEAIh7V2l27IOF1z9AenSJ7C8kUGxFDyoav7r8QoEfblwdqBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a61f807bb4637591e0e9c7d048abcc2e841cb3f59a1689530f2b5992b26cb6d1","last_reissued_at":"2026-07-05T10:09:12.134781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:12.134781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Chintan Chitroda, Neeraj Kumar Singh, Pratinav Seth, Vinay Kumar Sankarapu, Yashwardhan Rathore","submitted_at":"2024-11-19T16:54:30Z","abstract_excerpt":"The rapid growth of AI has led to more complex deep learning models, often operating as opaque \"black boxes\" with limited transparency in their decision-making. This lack of interpretability poses challenges, especially in high-stakes applications where understanding model output is crucial. This work highlights the importance of interpretability in fostering trust, accountability, and responsible deployment. To address these challenges, we introduce DLBacktrace, a novel, model-agnostic technique designed to provide clear insights into deep learning model decisions across a wide range of domai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12643","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/2411.12643/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":"2411.12643","created_at":"2026-07-05T10:09:12.134836+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.12643v2","created_at":"2026-07-05T10:09:12.134836+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12643","created_at":"2026-07-05T10:09:12.134836+00:00"},{"alias_kind":"pith_short_12","alias_value":"UYPYA65UMN2Z","created_at":"2026-07-05T10:09:12.134836+00:00"},{"alias_kind":"pith_short_16","alias_value":"UYPYA65UMN2ZDYHJ","created_at":"2026-07-05T10:09:12.134836+00:00"},{"alias_kind":"pith_short_8","alias_value":"UYPYA65U","created_at":"2026-07-05T10:09:12.134836+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05355","citing_title":"Faithfulness to Refusal: A Causal Audit of Neuron Selectors","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UYPYA65UMN2ZDYHJY7IERK6MF2","json":"https://pith.science/pith/UYPYA65UMN2ZDYHJY7IERK6MF2.json","graph_json":"https://pith.science/api/pith-number/UYPYA65UMN2ZDYHJY7IERK6MF2/graph.json","events_json":"https://pith.science/api/pith-number/UYPYA65UMN2ZDYHJY7IERK6MF2/events.json","paper":"https://pith.science/paper/UYPYA65U"},"agent_actions":{"view_html":"https://pith.science/pith/UYPYA65UMN2ZDYHJY7IERK6MF2","download_json":"https://pith.science/pith/UYPYA65UMN2ZDYHJY7IERK6MF2.json","view_paper":"https://pith.science/paper/UYPYA65U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.12643&json=true","fetch_graph":"https://pith.science/api/pith-number/UYPYA65UMN2ZDYHJY7IERK6MF2/graph.json","fetch_events":"https://pith.science/api/pith-number/UYPYA65UMN2ZDYHJY7IERK6MF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UYPYA65UMN2ZDYHJY7IERK6MF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UYPYA65UMN2ZDYHJY7IERK6MF2/action/storage_attestation","attest_author":"https://pith.science/pith/UYPYA65UMN2ZDYHJY7IERK6MF2/action/author_attestation","sign_citation":"https://pith.science/pith/UYPYA65UMN2ZDYHJY7IERK6MF2/action/citation_signature","submit_replication":"https://pith.science/pith/UYPYA65UMN2ZDYHJY7IERK6MF2/action/replication_record"}},"created_at":"2026-07-05T10:09:12.134836+00:00","updated_at":"2026-07-05T10:09:12.134836+00:00"}