{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KS2LNLUF4RNFSMYH74RVZKF5SZ","short_pith_number":"pith:KS2LNLUF","schema_version":"1.0","canonical_sha256":"54b4b6ae85e45a593307ff235ca8bd964cbf729ad36ff41bda97f92d815abb65","source":{"kind":"arxiv","id":"2511.04260","version":3},"attestation_state":"computed","paper":{"title":"Proto-LeakNet: Towards Signal-Leak Aware Attribution in Synthetic Human Face Imagery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Claudio Giusti, Luca Guarnera, Sebastiano Battiato","submitted_at":"2025-11-06T10:51:11Z","abstract_excerpt":"The growing sophistication of synthetic image and deepfake generation models has turned source attribution and authenticity verification into a critical challenge for modern computer vision systems. Recent studies suggest that diffusion pipelines unintentionally imprint persistent statistical traces, known as signal-leaks, within their outputs, particularly in latent representations. Building on this observation, we propose Proto-LeakNet, a signal-leak-aware and interpretable attribution framework that integrates Closed-set classification with a density-based Open-set evaluation on the learned"},"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":"2511.04260","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-06T10:51:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"03ceca92c2dd7b7a9a6cea28a9a6d9b87dee1499056f4740c0dc8c21f7789a29","abstract_canon_sha256":"79b018aa0c2228381ae8d0b772042451233b77c778e78d66511d65d750f356da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:15.760545Z","signature_b64":"Y0Ow1oSPOao0Ckwr+y1AgsV+5tvdM5ZZgd0yjdrAzeYvZZgw90SCXaruCcDntGIKTREzPc/SygcAac4dMYxJAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54b4b6ae85e45a593307ff235ca8bd964cbf729ad36ff41bda97f92d815abb65","last_reissued_at":"2026-06-12T01:09:15.759644Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:15.759644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Proto-LeakNet: Towards Signal-Leak Aware Attribution in Synthetic Human Face Imagery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Claudio Giusti, Luca Guarnera, Sebastiano Battiato","submitted_at":"2025-11-06T10:51:11Z","abstract_excerpt":"The growing sophistication of synthetic image and deepfake generation models has turned source attribution and authenticity verification into a critical challenge for modern computer vision systems. Recent studies suggest that diffusion pipelines unintentionally imprint persistent statistical traces, known as signal-leaks, within their outputs, particularly in latent representations. Building on this observation, we propose Proto-LeakNet, a signal-leak-aware and interpretable attribution framework that integrates Closed-set classification with a density-based Open-set evaluation on the learned"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.04260","kind":"arxiv","version":3},"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/2511.04260/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":"2511.04260","created_at":"2026-06-12T01:09:15.759749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.04260v3","created_at":"2026-06-12T01:09:15.759749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.04260","created_at":"2026-06-12T01:09:15.759749+00:00"},{"alias_kind":"pith_short_12","alias_value":"KS2LNLUF4RNF","created_at":"2026-06-12T01:09:15.759749+00:00"},{"alias_kind":"pith_short_16","alias_value":"KS2LNLUF4RNFSMYH","created_at":"2026-06-12T01:09:15.759749+00:00"},{"alias_kind":"pith_short_8","alias_value":"KS2LNLUF","created_at":"2026-06-12T01:09:15.759749+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/KS2LNLUF4RNFSMYH74RVZKF5SZ","json":"https://pith.science/pith/KS2LNLUF4RNFSMYH74RVZKF5SZ.json","graph_json":"https://pith.science/api/pith-number/KS2LNLUF4RNFSMYH74RVZKF5SZ/graph.json","events_json":"https://pith.science/api/pith-number/KS2LNLUF4RNFSMYH74RVZKF5SZ/events.json","paper":"https://pith.science/paper/KS2LNLUF"},"agent_actions":{"view_html":"https://pith.science/pith/KS2LNLUF4RNFSMYH74RVZKF5SZ","download_json":"https://pith.science/pith/KS2LNLUF4RNFSMYH74RVZKF5SZ.json","view_paper":"https://pith.science/paper/KS2LNLUF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.04260&json=true","fetch_graph":"https://pith.science/api/pith-number/KS2LNLUF4RNFSMYH74RVZKF5SZ/graph.json","fetch_events":"https://pith.science/api/pith-number/KS2LNLUF4RNFSMYH74RVZKF5SZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KS2LNLUF4RNFSMYH74RVZKF5SZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KS2LNLUF4RNFSMYH74RVZKF5SZ/action/storage_attestation","attest_author":"https://pith.science/pith/KS2LNLUF4RNFSMYH74RVZKF5SZ/action/author_attestation","sign_citation":"https://pith.science/pith/KS2LNLUF4RNFSMYH74RVZKF5SZ/action/citation_signature","submit_replication":"https://pith.science/pith/KS2LNLUF4RNFSMYH74RVZKF5SZ/action/replication_record"}},"created_at":"2026-06-12T01:09:15.759749+00:00","updated_at":"2026-06-12T01:09:15.759749+00:00"}