{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U54DINTTUM2SBTB4ASIB6UXV6M","short_pith_number":"pith:U54DINTT","schema_version":"1.0","canonical_sha256":"a778343673a33520cc3c04901f52f5f333acfb5869f12b43e605894207de0e43","source":{"kind":"arxiv","id":"2501.09221","version":2},"attestation_state":"computed","paper":{"title":"ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aidong Zhang, Guangzhi Xiong, Sanchit Sinha","submitted_at":"2025-01-16T00:45:05Z","abstract_excerpt":"As Vision Transformers (ViTs) are increasingly adopted in sensitive vision applications, there is a growing demand for improved interpretability. This has led to efforts to forward-align these models with carefully annotated abstract, human-understandable semantic entities - concepts. Concepts provide global rationales to the model predictions and can be quickly understood/intervened on by domain experts. Most current research focuses on designing model-agnostic, plug-and-play generic concept-based explainability modules that do not incorporate the inner workings of foundation models (e.g., in"},"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":"2501.09221","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-16T00:45:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"84ec80f4d48240b8871c666c78794af29b914df7f26a6de98347c02d90f8d39c","abstract_canon_sha256":"dc47a071fe106df9751f3ff2cf503aab278563fb5a1a643799516d662b3d4645"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:14.885082Z","signature_b64":"zCTXaGE6+Rj4AQvwNXdAngV1qrJeI5GnskZDayQQ7zK2618fo2q3iGAhka/jwsD2RebitkNOX1vWZCa78vudBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a778343673a33520cc3c04901f52f5f333acfb5869f12b43e605894207de0e43","last_reissued_at":"2026-07-05T10:09:14.884653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:14.884653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aidong Zhang, Guangzhi Xiong, Sanchit Sinha","submitted_at":"2025-01-16T00:45:05Z","abstract_excerpt":"As Vision Transformers (ViTs) are increasingly adopted in sensitive vision applications, there is a growing demand for improved interpretability. This has led to efforts to forward-align these models with carefully annotated abstract, human-understandable semantic entities - concepts. Concepts provide global rationales to the model predictions and can be quickly understood/intervened on by domain experts. Most current research focuses on designing model-agnostic, plug-and-play generic concept-based explainability modules that do not incorporate the inner workings of foundation models (e.g., in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09221","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/2501.09221/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":"2501.09221","created_at":"2026-07-05T10:09:14.884709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09221v2","created_at":"2026-07-05T10:09:14.884709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09221","created_at":"2026-07-05T10:09:14.884709+00:00"},{"alias_kind":"pith_short_12","alias_value":"U54DINTTUM2S","created_at":"2026-07-05T10:09:14.884709+00:00"},{"alias_kind":"pith_short_16","alias_value":"U54DINTTUM2SBTB4","created_at":"2026-07-05T10:09:14.884709+00:00"},{"alias_kind":"pith_short_8","alias_value":"U54DINTT","created_at":"2026-07-05T10:09:14.884709+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/U54DINTTUM2SBTB4ASIB6UXV6M","json":"https://pith.science/pith/U54DINTTUM2SBTB4ASIB6UXV6M.json","graph_json":"https://pith.science/api/pith-number/U54DINTTUM2SBTB4ASIB6UXV6M/graph.json","events_json":"https://pith.science/api/pith-number/U54DINTTUM2SBTB4ASIB6UXV6M/events.json","paper":"https://pith.science/paper/U54DINTT"},"agent_actions":{"view_html":"https://pith.science/pith/U54DINTTUM2SBTB4ASIB6UXV6M","download_json":"https://pith.science/pith/U54DINTTUM2SBTB4ASIB6UXV6M.json","view_paper":"https://pith.science/paper/U54DINTT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09221&json=true","fetch_graph":"https://pith.science/api/pith-number/U54DINTTUM2SBTB4ASIB6UXV6M/graph.json","fetch_events":"https://pith.science/api/pith-number/U54DINTTUM2SBTB4ASIB6UXV6M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U54DINTTUM2SBTB4ASIB6UXV6M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U54DINTTUM2SBTB4ASIB6UXV6M/action/storage_attestation","attest_author":"https://pith.science/pith/U54DINTTUM2SBTB4ASIB6UXV6M/action/author_attestation","sign_citation":"https://pith.science/pith/U54DINTTUM2SBTB4ASIB6UXV6M/action/citation_signature","submit_replication":"https://pith.science/pith/U54DINTTUM2SBTB4ASIB6UXV6M/action/replication_record"}},"created_at":"2026-07-05T10:09:14.884709+00:00","updated_at":"2026-07-05T10:09:14.884709+00:00"}