{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YER45XPBBQFOA2GSISPGBYIF45","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"62263ae63dafad58291d982776f6e1a16bea20e2c13717e7f870bce567e892be","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-14T22:43:30Z","title_canon_sha256":"4a18356291197261c8689a35ef5c251e3318b10835fcc221d96182ce65e48f61"},"schema_version":"1.0","source":{"id":"2605.15460","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15460","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15460v1","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15460","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"pith_short_12","alias_value":"YER45XPBBQFO","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"pith_short_16","alias_value":"YER45XPBBQFOA2GS","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"pith_short_8","alias_value":"YER45XPB","created_at":"2026-05-20T00:00:59Z"}],"graph_snapshots":[{"event_id":"sha256:a0f75dd6059fce34f925e7840ac563017aea52d6856d35376d9185588a3e775e","target":"graph","created_at":"2026-05-20T00:00:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"DMP-MH outperforms private baselines by up to 11.4 mAP points while retaining up to 92.5% of non-private performance on MIRFlickr-25K and NUS-WIDE under a strict inductive protocol."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That deterministically clipping node degrees to a fixed threshold caps the L2-sensitivity of triangle motifs independently of dataset size and still leaves enough structural signal for the downstream hashing loss to recover useful cross-modal alignments."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"DMP-MH clips degrees to control triangle sensitivity, synthesizes an edge-DP graph with Noisy Mirror Descent, and distills it into dual-stream hash networks, beating private baselines by up to 11.4 mAP on MIRFlickr-25K and NUS-WIDE while keeping 92.5% of non-private performance."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Degree clipping before noisy synthesis lets differentially private multi-modal hashing retain up to 92.5 percent of non-private retrieval accuracy."}],"snapshot_sha256":"ce1da16fdb504972485685a17f04fceee3da3b5d5de010b9948395866451d9c0"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"aff0a6b49c4f9799e365224268e0e61d70dc22050fad5ec07625766f10eeb7d6"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"citation_quote_validity","ran_at":"2026-05-19T15:49:45.738120Z","status":"completed","version":"0.1.0"},{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T15:23:28.905635Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T15:01:17.604419Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T15:00:38.907785Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.098784Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.671046Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15460/integrity.json","findings":[],"snapshot_sha256":"6a8459b9fcbd0cdd56d40a23a17bd7b1b2bf49e3466d9ea4e9a0c015b8fe53df","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-modal hashing enables efficient retrieval by encoding images and text into compact binary codes. State-of-the-art methods rely on semantic similarity graphs derived from user interactions for supervision, yet these graphs encode sensitive behavioral patterns vulnerable to link reconstruction attacks. Existing privacy-preserving approaches fail on graph-structured data: Differentially Private SGD destroys relational motifs by treating samples independently, while graph synthesis methods suffer from unbounded local sensitivity in scale-free networks, hub nodes cause single-edge modificatio","authors_text":"Jiahao Sun, Wei Dai, Zehua Cheng","cross_cats":["cs.AI"],"headline":"Degree clipping before noisy synthesis lets differentially private multi-modal hashing retain up to 92.5 percent of non-private retrieval accuracy.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-14T22:43:30Z","title":"Differentially Private Motif-Preserving Multi-modal Hashing"},"references":{"count":43,"internal_anchors":5,"resolved_work":43,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Martin Abadi, Andy Chu, Ian Goodfellow, H Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang. 2016. Deep learning with differential privacy. In Proceedings of the 2016 ACM SIGSAC conference on ","work_id":"c9059fb9-6d33-40b8-a53f-cdec0e3f03eb","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Tadas Baltrušaitis, Chaitanya Ahuja, and Louis-Philippe Morency. 2018. Multi- modal machine learning: A survey and taxonomy.IEEE transactions on pattern analysis and machine intelligence41, 2 (2018), ","work_id":"454c840f-6b47-4250-a841-76bb7db96606","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Albert-László Barabási and Réka Albert. 1999. Emergence of scaling in random networks.science286, 5439 (1999), 509–512","work_id":"6bd5dcd3-9949-418d-8f56-ebb9b91ff1c2","year":1999},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Austin R Benson, David F Gleich, and Jure Leskovec. 2016. Higher-order organi- zation of complex networks.Science353, 6295 (2016), 163–166","work_id":"b790660d-e4b4-474c-b1f2-78dfa0943aba","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Dimitri P. Bertsekas. 1999.Nonlinear Programming(2 ed.). Athena Scientific","work_id":"d7bd4363-7c65-40e8-bc19-3d169066edd6","year":1999}],"snapshot_sha256":"816ae73e29e2a2e4796f237e4892cb03cfaa62e789ceb3da8e225f4b24fd12b1"},"source":{"id":"2605.15460","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T14:51:28.525043Z","id":"84827b2f-a438-493b-8e96-805084abf309","model_set":{"reader":"grok-4.3"},"one_line_summary":"DMP-MH clips degrees to control triangle sensitivity, synthesizes an edge-DP graph with Noisy Mirror Descent, and distills it into dual-stream hash networks, beating private baselines by up to 11.4 mAP on MIRFlickr-25K and NUS-WIDE while keeping 92.5% of non-private performance.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Degree clipping before noisy synthesis lets differentially private multi-modal hashing retain up to 92.5 percent of non-private retrieval accuracy.","strongest_claim":"DMP-MH outperforms private baselines by up to 11.4 mAP points while retaining up to 92.5% of non-private performance on MIRFlickr-25K and NUS-WIDE under a strict inductive protocol.","weakest_assumption":"That deterministically clipping node degrees to a fixed threshold caps the L2-sensitivity of triangle motifs independently of dataset size and still leaves enough structural signal for the downstream hashing loss to recover useful cross-modal alignments."}},"verdict_id":"84827b2f-a438-493b-8e96-805084abf309"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f7cbe9d60d54b208fb1030f234cbbf6d80f6e145d65a52668f7f07ef82155785","target":"record","created_at":"2026-05-20T00:00:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"62263ae63dafad58291d982776f6e1a16bea20e2c13717e7f870bce567e892be","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-14T22:43:30Z","title_canon_sha256":"4a18356291197261c8689a35ef5c251e3318b10835fcc221d96182ce65e48f61"},"schema_version":"1.0","source":{"id":"2605.15460","kind":"arxiv","version":1}},"canonical_sha256":"c123cedde10c0ae068d2449e60e105e7558572c75a73cc6201f3b070a37e64eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c123cedde10c0ae068d2449e60e105e7558572c75a73cc6201f3b070a37e64eb","first_computed_at":"2026-05-20T00:00:59.720643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:59.720643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yhYfNKem1pHc7EZ2pcQFHMsfhcFuaHgCnYOmpUjRxWIpyO3L80jv97ww3pkE6aosqszxHGCjB3xbtI6AwpsiDA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:59.721475Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15460","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7cbe9d60d54b208fb1030f234cbbf6d80f6e145d65a52668f7f07ef82155785","sha256:a0f75dd6059fce34f925e7840ac563017aea52d6856d35376d9185588a3e775e"],"state_sha256":"1cd488f7a081eb072e9c75b1431f81e30047b946fb8a1d8eab2a303ab37e4f66"}