{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4475NSN3HOHXTWFKZJABPQK64R","short_pith_number":"pith:4475NSN3","schema_version":"1.0","canonical_sha256":"e73fd6c9bb3b8f79d8aaca4017c15ee4660487df3f00e3df64bf3c96cbdc020a","source":{"kind":"arxiv","id":"2507.00234","version":1},"attestation_state":"computed","paper":{"title":"Interpretable AI for Time-Series: Multi-Model Heatmap Fusion with Global Attention and NLP-Generated Explanations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jiztom Kavalakkatt Francis, Matthew J Darr","submitted_at":"2025-06-30T20:04:35Z","abstract_excerpt":"In this paper, we present a novel framework for enhancing model interpretability by integrating heatmaps produced separately by ResNet and a restructured 2D Transformer with globally weighted input saliency. We address the critical problem of spatial-temporal misalignment in existing interpretability methods, where convolutional networks fail to capture global context and Transformers lack localized precision - a limitation that impedes actionable insights in safety-critical domains like healthcare and industrial monitoring. Our method merges gradient-weighted activation maps (ResNet) and Tran"},"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":"2507.00234","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-30T20:04:35Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c4a600f559ab844f6ebc4114b4b7394a8554dcee1dff49d9d4c450d44297c64c","abstract_canon_sha256":"c3ab1b353019ea3bc0ad551eab416a39664c28f8996698c8c9cadd2915e1075f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:04.893361Z","signature_b64":"4PfLgf/SRu8cPmNQPkNkVHYf5Z2ZBATFoESFeMaTT2hr72iQu/FkmcuzoX9CfhWRkVGMWa4r+vQqZNOfH4QoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e73fd6c9bb3b8f79d8aaca4017c15ee4660487df3f00e3df64bf3c96cbdc020a","last_reissued_at":"2026-07-05T11:30:04.892917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:04.892917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable AI for Time-Series: Multi-Model Heatmap Fusion with Global Attention and NLP-Generated Explanations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jiztom Kavalakkatt Francis, Matthew J Darr","submitted_at":"2025-06-30T20:04:35Z","abstract_excerpt":"In this paper, we present a novel framework for enhancing model interpretability by integrating heatmaps produced separately by ResNet and a restructured 2D Transformer with globally weighted input saliency. We address the critical problem of spatial-temporal misalignment in existing interpretability methods, where convolutional networks fail to capture global context and Transformers lack localized precision - a limitation that impedes actionable insights in safety-critical domains like healthcare and industrial monitoring. Our method merges gradient-weighted activation maps (ResNet) and Tran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00234","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/2507.00234/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":"2507.00234","created_at":"2026-07-05T11:30:04.892971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00234v1","created_at":"2026-07-05T11:30:04.892971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00234","created_at":"2026-07-05T11:30:04.892971+00:00"},{"alias_kind":"pith_short_12","alias_value":"4475NSN3HOHX","created_at":"2026-07-05T11:30:04.892971+00:00"},{"alias_kind":"pith_short_16","alias_value":"4475NSN3HOHXTWFK","created_at":"2026-07-05T11:30:04.892971+00:00"},{"alias_kind":"pith_short_8","alias_value":"4475NSN3","created_at":"2026-07-05T11:30:04.892971+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/4475NSN3HOHXTWFKZJABPQK64R","json":"https://pith.science/pith/4475NSN3HOHXTWFKZJABPQK64R.json","graph_json":"https://pith.science/api/pith-number/4475NSN3HOHXTWFKZJABPQK64R/graph.json","events_json":"https://pith.science/api/pith-number/4475NSN3HOHXTWFKZJABPQK64R/events.json","paper":"https://pith.science/paper/4475NSN3"},"agent_actions":{"view_html":"https://pith.science/pith/4475NSN3HOHXTWFKZJABPQK64R","download_json":"https://pith.science/pith/4475NSN3HOHXTWFKZJABPQK64R.json","view_paper":"https://pith.science/paper/4475NSN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00234&json=true","fetch_graph":"https://pith.science/api/pith-number/4475NSN3HOHXTWFKZJABPQK64R/graph.json","fetch_events":"https://pith.science/api/pith-number/4475NSN3HOHXTWFKZJABPQK64R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4475NSN3HOHXTWFKZJABPQK64R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4475NSN3HOHXTWFKZJABPQK64R/action/storage_attestation","attest_author":"https://pith.science/pith/4475NSN3HOHXTWFKZJABPQK64R/action/author_attestation","sign_citation":"https://pith.science/pith/4475NSN3HOHXTWFKZJABPQK64R/action/citation_signature","submit_replication":"https://pith.science/pith/4475NSN3HOHXTWFKZJABPQK64R/action/replication_record"}},"created_at":"2026-07-05T11:30:04.892971+00:00","updated_at":"2026-07-05T11:30:04.892971+00:00"}