{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3XUV3JVKEN4M6BBI64SZIPOCKX","short_pith_number":"pith:3XUV3JVK","schema_version":"1.0","canonical_sha256":"dde95da6aa2378cf0428f725943dc255c9285c5c9910ea8178ac848606624e08","source":{"kind":"arxiv","id":"1807.08692","version":2},"attestation_state":"computed","paper":{"title":"Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahmet Iscen, Giorgos Tolias, Ondrej Chum, Teddy Furon, Yannis Avrithis","submitted_at":"2018-07-23T16:07:29Z","abstract_excerpt":"State of the art image retrieval performance is achieved with CNN features and manifold ranking using a k-NN similarity graph that is pre-computed off-line. The two most successful existing approaches are temporal filtering, where manifold ranking amounts to solving a sparse linear system online, and spectral filtering, where eigen-decomposition of the adjacency matrix is performed off-line and then manifold ranking amounts to dot-product search online. The former suffers from expensive queries and the latter from significant space overhead. Here we introduce a novel, theoretically well-founde"},"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":"1807.08692","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-23T16:07:29Z","cross_cats_sorted":[],"title_canon_sha256":"0b2af4cf2185c9755e21e5174b1ab5828654a0aa57be13bdeacd9a54225e664d","abstract_canon_sha256":"184c97def97f5a88cdc442274d73fae835866a3096ac9b088ea9fc6319488d4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:08.275185Z","signature_b64":"zDjjqld5miqg+FeuaV40TYJYKSOwyks2ON6P0dTPKJnrXdd6j1EkNFVAbU5/X14ndCaLiHgXOE/OATXPs4NWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dde95da6aa2378cf0428f725943dc255c9285c5c9910ea8178ac848606624e08","last_reissued_at":"2026-05-18T00:00:08.274746Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:08.274746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahmet Iscen, Giorgos Tolias, Ondrej Chum, Teddy Furon, Yannis Avrithis","submitted_at":"2018-07-23T16:07:29Z","abstract_excerpt":"State of the art image retrieval performance is achieved with CNN features and manifold ranking using a k-NN similarity graph that is pre-computed off-line. The two most successful existing approaches are temporal filtering, where manifold ranking amounts to solving a sparse linear system online, and spectral filtering, where eigen-decomposition of the adjacency matrix is performed off-line and then manifold ranking amounts to dot-product search online. The former suffers from expensive queries and the latter from significant space overhead. Here we introduce a novel, theoretically well-founde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.08692","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":""},"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":"1807.08692","created_at":"2026-05-18T00:00:08.274809+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.08692v2","created_at":"2026-05-18T00:00:08.274809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.08692","created_at":"2026-05-18T00:00:08.274809+00:00"},{"alias_kind":"pith_short_12","alias_value":"3XUV3JVKEN4M","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"3XUV3JVKEN4M6BBI","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"3XUV3JVK","created_at":"2026-05-18T12:32:05.422762+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/3XUV3JVKEN4M6BBI64SZIPOCKX","json":"https://pith.science/pith/3XUV3JVKEN4M6BBI64SZIPOCKX.json","graph_json":"https://pith.science/api/pith-number/3XUV3JVKEN4M6BBI64SZIPOCKX/graph.json","events_json":"https://pith.science/api/pith-number/3XUV3JVKEN4M6BBI64SZIPOCKX/events.json","paper":"https://pith.science/paper/3XUV3JVK"},"agent_actions":{"view_html":"https://pith.science/pith/3XUV3JVKEN4M6BBI64SZIPOCKX","download_json":"https://pith.science/pith/3XUV3JVKEN4M6BBI64SZIPOCKX.json","view_paper":"https://pith.science/paper/3XUV3JVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.08692&json=true","fetch_graph":"https://pith.science/api/pith-number/3XUV3JVKEN4M6BBI64SZIPOCKX/graph.json","fetch_events":"https://pith.science/api/pith-number/3XUV3JVKEN4M6BBI64SZIPOCKX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3XUV3JVKEN4M6BBI64SZIPOCKX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3XUV3JVKEN4M6BBI64SZIPOCKX/action/storage_attestation","attest_author":"https://pith.science/pith/3XUV3JVKEN4M6BBI64SZIPOCKX/action/author_attestation","sign_citation":"https://pith.science/pith/3XUV3JVKEN4M6BBI64SZIPOCKX/action/citation_signature","submit_replication":"https://pith.science/pith/3XUV3JVKEN4M6BBI64SZIPOCKX/action/replication_record"}},"created_at":"2026-05-18T00:00:08.274809+00:00","updated_at":"2026-05-18T00:00:08.274809+00:00"}