{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZWYJUMOZBN2YUMOS4B3V7KF5ZD","short_pith_number":"pith:ZWYJUMOZ","schema_version":"1.0","canonical_sha256":"cdb09a31d90b758a31d2e0775fa8bdc8df0e41d1a36c08cf2c8e8f36b85f75b3","source":{"kind":"arxiv","id":"2412.14598","version":2},"attestation_state":"computed","paper":{"title":"Can We Get Rid of Handcrafted Feature Extractors? SparseViT: Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization through Spare-Coding Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoqun Niu, Ji-Zhe Zhou, Lei Su, Xiaochen Ma, Xuekang Zhu, Zeyu Lei","submitted_at":"2024-12-19T07:39:06Z","abstract_excerpt":"Non-semantic features or semantic-agnostic features, which are irrelevant to image context but sensitive to image manipulations, are recognized as evidential to Image Manipulation Localization (IML). Since manual labels are impossible, existing works rely on handcrafted methods to extract non-semantic features. Handcrafted non-semantic features jeopardize IML model's generalization ability in unseen or complex scenarios. Therefore, for IML, the elephant in the room is: How to adaptively extract non-semantic features? Non-semantic features are context-irrelevant and manipulation-sensitive. That"},"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":"2412.14598","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T07:39:06Z","cross_cats_sorted":[],"title_canon_sha256":"02c03242f0fa6fef2f20a665c63e41e8c342b7cf64bdc6b7e56c151d3d8d49a6","abstract_canon_sha256":"a5a8617da7dc263b34c9c2de2bdfa9821bb99549aa493f7ee52ea57ad2d1ef4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:09.466336Z","signature_b64":"OSg7eZF8992b8d3gLSIz4G5xHwYAfQ9mFpZLzWYc7hR1zESOjrj9I0J0LanlxxhSDxBOfIQzd4fvHX8Q/eiaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdb09a31d90b758a31d2e0775fa8bdc8df0e41d1a36c08cf2c8e8f36b85f75b3","last_reissued_at":"2026-07-05T09:53:09.465863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:09.465863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can We Get Rid of Handcrafted Feature Extractors? SparseViT: Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization through Spare-Coding Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoqun Niu, Ji-Zhe Zhou, Lei Su, Xiaochen Ma, Xuekang Zhu, Zeyu Lei","submitted_at":"2024-12-19T07:39:06Z","abstract_excerpt":"Non-semantic features or semantic-agnostic features, which are irrelevant to image context but sensitive to image manipulations, are recognized as evidential to Image Manipulation Localization (IML). Since manual labels are impossible, existing works rely on handcrafted methods to extract non-semantic features. Handcrafted non-semantic features jeopardize IML model's generalization ability in unseen or complex scenarios. Therefore, for IML, the elephant in the room is: How to adaptively extract non-semantic features? Non-semantic features are context-irrelevant and manipulation-sensitive. That"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14598","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/2412.14598/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":"2412.14598","created_at":"2026-07-05T09:53:09.465921+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14598v2","created_at":"2026-07-05T09:53:09.465921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14598","created_at":"2026-07-05T09:53:09.465921+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWYJUMOZBN2Y","created_at":"2026-07-05T09:53:09.465921+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWYJUMOZBN2YUMOS","created_at":"2026-07-05T09:53:09.465921+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWYJUMOZ","created_at":"2026-07-05T09:53:09.465921+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21157","citing_title":"Unmasking Synthetic Realities in Generative AI: A Comprehensive Review of Adversarially Robust Deepfake Detection Systems","ref_index":214,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZWYJUMOZBN2YUMOS4B3V7KF5ZD","json":"https://pith.science/pith/ZWYJUMOZBN2YUMOS4B3V7KF5ZD.json","graph_json":"https://pith.science/api/pith-number/ZWYJUMOZBN2YUMOS4B3V7KF5ZD/graph.json","events_json":"https://pith.science/api/pith-number/ZWYJUMOZBN2YUMOS4B3V7KF5ZD/events.json","paper":"https://pith.science/paper/ZWYJUMOZ"},"agent_actions":{"view_html":"https://pith.science/pith/ZWYJUMOZBN2YUMOS4B3V7KF5ZD","download_json":"https://pith.science/pith/ZWYJUMOZBN2YUMOS4B3V7KF5ZD.json","view_paper":"https://pith.science/paper/ZWYJUMOZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14598&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWYJUMOZBN2YUMOS4B3V7KF5ZD/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWYJUMOZBN2YUMOS4B3V7KF5ZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWYJUMOZBN2YUMOS4B3V7KF5ZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWYJUMOZBN2YUMOS4B3V7KF5ZD/action/storage_attestation","attest_author":"https://pith.science/pith/ZWYJUMOZBN2YUMOS4B3V7KF5ZD/action/author_attestation","sign_citation":"https://pith.science/pith/ZWYJUMOZBN2YUMOS4B3V7KF5ZD/action/citation_signature","submit_replication":"https://pith.science/pith/ZWYJUMOZBN2YUMOS4B3V7KF5ZD/action/replication_record"}},"created_at":"2026-07-05T09:53:09.465921+00:00","updated_at":"2026-07-05T09:53:09.465921+00:00"}