{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7GM2MPHIZLQYZU4SEQTQCMCPAY","short_pith_number":"pith:7GM2MPHI","schema_version":"1.0","canonical_sha256":"f999a63ce8cae18cd392242701304f0635b5c44a9c8d2ee20d4e0d4519fddcd9","source":{"kind":"arxiv","id":"2506.07188","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Feature-level Reverse Propagation for Post-Training Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Keqiang Li, Lei He, Ni Ding, Shengbo Eben Li","submitted_at":"2025-06-08T15:19:03Z","abstract_excerpt":"End-to-end autonomous driving has emerged as a dominant paradigm, yet its highly entangled black-box models pose significant challenges in terms of interpretability and safety assurance. To improve model transparency and training flexibility, this paper proposes a hierarchical and decoupled post-training framework tailored for pretrained neural networks. By reconstructing intermediate feature maps from ground-truth labels, surrogate supervisory signals are introduced at transitional layers to enable independent training of specific components, thereby avoiding the complexity and coupling of co"},"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":"2506.07188","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-08T15:19:03Z","cross_cats_sorted":[],"title_canon_sha256":"e63fe80ea1b75c2a84db9232c6001ade9be7ad0104d72300ebf286f71c9014a7","abstract_canon_sha256":"3cbbf9df3e16bcfc4d24645d0aebfef432def8c978c84ba912054d9aae79603b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:03.243782Z","signature_b64":"iErfZ/CPkXcHt1zxWPKG50WYGqvisZESB2tCN394x1i71WUoO2VZo/29wqzetA5jeR03NiWPF5odWujAHzZ+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f999a63ce8cae18cd392242701304f0635b5c44a9c8d2ee20d4e0d4519fddcd9","last_reissued_at":"2026-07-05T11:18:03.243344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:03.243344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Feature-level Reverse Propagation for Post-Training Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Keqiang Li, Lei He, Ni Ding, Shengbo Eben Li","submitted_at":"2025-06-08T15:19:03Z","abstract_excerpt":"End-to-end autonomous driving has emerged as a dominant paradigm, yet its highly entangled black-box models pose significant challenges in terms of interpretability and safety assurance. To improve model transparency and training flexibility, this paper proposes a hierarchical and decoupled post-training framework tailored for pretrained neural networks. By reconstructing intermediate feature maps from ground-truth labels, surrogate supervisory signals are introduced at transitional layers to enable independent training of specific components, thereby avoiding the complexity and coupling of co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07188","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/2506.07188/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":"2506.07188","created_at":"2026-07-05T11:18:03.243399+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07188v1","created_at":"2026-07-05T11:18:03.243399+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07188","created_at":"2026-07-05T11:18:03.243399+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GM2MPHIZLQY","created_at":"2026-07-05T11:18:03.243399+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GM2MPHIZLQYZU4S","created_at":"2026-07-05T11:18:03.243399+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GM2MPHI","created_at":"2026-07-05T11:18:03.243399+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/7GM2MPHIZLQYZU4SEQTQCMCPAY","json":"https://pith.science/pith/7GM2MPHIZLQYZU4SEQTQCMCPAY.json","graph_json":"https://pith.science/api/pith-number/7GM2MPHIZLQYZU4SEQTQCMCPAY/graph.json","events_json":"https://pith.science/api/pith-number/7GM2MPHIZLQYZU4SEQTQCMCPAY/events.json","paper":"https://pith.science/paper/7GM2MPHI"},"agent_actions":{"view_html":"https://pith.science/pith/7GM2MPHIZLQYZU4SEQTQCMCPAY","download_json":"https://pith.science/pith/7GM2MPHIZLQYZU4SEQTQCMCPAY.json","view_paper":"https://pith.science/paper/7GM2MPHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07188&json=true","fetch_graph":"https://pith.science/api/pith-number/7GM2MPHIZLQYZU4SEQTQCMCPAY/graph.json","fetch_events":"https://pith.science/api/pith-number/7GM2MPHIZLQYZU4SEQTQCMCPAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GM2MPHIZLQYZU4SEQTQCMCPAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GM2MPHIZLQYZU4SEQTQCMCPAY/action/storage_attestation","attest_author":"https://pith.science/pith/7GM2MPHIZLQYZU4SEQTQCMCPAY/action/author_attestation","sign_citation":"https://pith.science/pith/7GM2MPHIZLQYZU4SEQTQCMCPAY/action/citation_signature","submit_replication":"https://pith.science/pith/7GM2MPHIZLQYZU4SEQTQCMCPAY/action/replication_record"}},"created_at":"2026-07-05T11:18:03.243399+00:00","updated_at":"2026-07-05T11:18:03.243399+00:00"}