{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U2PBPQBR26U4U4VRELXATOWH7V","short_pith_number":"pith:U2PBPQBR","schema_version":"1.0","canonical_sha256":"a69e17c031d7a9ca72b122ee09bac7fd5c9d4274585738ceb6941ef68c13fc36","source":{"kind":"arxiv","id":"2508.06109","version":2},"attestation_state":"computed","paper":{"title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lei He, Renyu Huang, Zhibo Zhu","submitted_at":"2025-08-08T08:15:26Z","abstract_excerpt":"Deep Neural Networks (DNNs) face interpretability challenges due to their opaque internal representations. While Feature Map Convergence Evaluation (FMCE) quantifies module-level convergence via Feature Map Convergence Scores (FMCS), it lacks experimental validation and closed-loop integration. To address this limitation, we propose FMCE-Net++, a novel training framework that integrates a pretrained, frozen FMCE-Net as an auxiliary head. This module generates FMCS predictions, which, combined with task labels, jointly supervise backbone optimization through a Representation Auxiliary Loss. The"},"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":"2508.06109","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-08T08:15:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4d77f61ccd6e858b2f5c1af780291755b0d61c7ea1eb943c81ad6e076f91215e","abstract_canon_sha256":"0c32c9ca083bbed7c9e93fe2dadc722144f33569e14925e55acb44260aad3f1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:50.472937Z","signature_b64":"ciCHrERJfpPjCf5qN0Ulou0esPSuC25x60hxNHFt08aAvxgCvFvkt0pGaua4Jjj30hq1r1hcJ3NXSAKvTWS/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a69e17c031d7a9ca72b122ee09bac7fd5c9d4274585738ceb6941ef68c13fc36","last_reissued_at":"2026-07-05T11:54:50.472480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:50.472480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lei He, Renyu Huang, Zhibo Zhu","submitted_at":"2025-08-08T08:15:26Z","abstract_excerpt":"Deep Neural Networks (DNNs) face interpretability challenges due to their opaque internal representations. While Feature Map Convergence Evaluation (FMCE) quantifies module-level convergence via Feature Map Convergence Scores (FMCS), it lacks experimental validation and closed-loop integration. To address this limitation, we propose FMCE-Net++, a novel training framework that integrates a pretrained, frozen FMCE-Net as an auxiliary head. This module generates FMCS predictions, which, combined with task labels, jointly supervise backbone optimization through a Representation Auxiliary Loss. The"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06109","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/2508.06109/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":"2508.06109","created_at":"2026-07-05T11:54:50.472536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.06109v2","created_at":"2026-07-05T11:54:50.472536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06109","created_at":"2026-07-05T11:54:50.472536+00:00"},{"alias_kind":"pith_short_12","alias_value":"U2PBPQBR26U4","created_at":"2026-07-05T11:54:50.472536+00:00"},{"alias_kind":"pith_short_16","alias_value":"U2PBPQBR26U4U4VR","created_at":"2026-07-05T11:54:50.472536+00:00"},{"alias_kind":"pith_short_8","alias_value":"U2PBPQBR","created_at":"2026-07-05T11:54:50.472536+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/U2PBPQBR26U4U4VRELXATOWH7V","json":"https://pith.science/pith/U2PBPQBR26U4U4VRELXATOWH7V.json","graph_json":"https://pith.science/api/pith-number/U2PBPQBR26U4U4VRELXATOWH7V/graph.json","events_json":"https://pith.science/api/pith-number/U2PBPQBR26U4U4VRELXATOWH7V/events.json","paper":"https://pith.science/paper/U2PBPQBR"},"agent_actions":{"view_html":"https://pith.science/pith/U2PBPQBR26U4U4VRELXATOWH7V","download_json":"https://pith.science/pith/U2PBPQBR26U4U4VRELXATOWH7V.json","view_paper":"https://pith.science/paper/U2PBPQBR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.06109&json=true","fetch_graph":"https://pith.science/api/pith-number/U2PBPQBR26U4U4VRELXATOWH7V/graph.json","fetch_events":"https://pith.science/api/pith-number/U2PBPQBR26U4U4VRELXATOWH7V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U2PBPQBR26U4U4VRELXATOWH7V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U2PBPQBR26U4U4VRELXATOWH7V/action/storage_attestation","attest_author":"https://pith.science/pith/U2PBPQBR26U4U4VRELXATOWH7V/action/author_attestation","sign_citation":"https://pith.science/pith/U2PBPQBR26U4U4VRELXATOWH7V/action/citation_signature","submit_replication":"https://pith.science/pith/U2PBPQBR26U4U4VRELXATOWH7V/action/replication_record"}},"created_at":"2026-07-05T11:54:50.472536+00:00","updated_at":"2026-07-05T11:54:50.472536+00:00"}