{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:63HFLUWRAQ7HDKG5YAU7JMYUIU","short_pith_number":"pith:63HFLUWR","schema_version":"1.0","canonical_sha256":"f6ce55d2d1043e71a8ddc029f4b3144525e21ea93c791ff690de91050c2c143a","source":{"kind":"arxiv","id":"2105.00695","version":2},"attestation_state":"computed","paper":{"title":"ResVGAE: Going Deeper with Residual Modules for Link Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Aydin Ayanzadeh, Beh\\c{c}et U\\u{g}ur T\\\"oreyin, Indrit Nallbani, Nurullah \\c{C}al{\\i}k, Reyhan Kevser Keser","submitted_at":"2021-05-03T09:05:46Z","abstract_excerpt":"Graph autoencoders are efficient at embedding graph-based data sets. Most graph autoencoder architectures have shallow depths which limits their ability to capture meaningful relations between nodes separated by multi-hops. In this paper, we propose Residual Variational Graph Autoencoder, ResVGAE, a deep variational graph autoencoder model with multiple residual modules. We show that our multiple residual modules, a convolutional layer with residual connection, improve the average precision of the graph autoencoders. Experimental results suggest that our proposed model with residual modules ou"},"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":"2105.00695","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-03T09:05:46Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"0d4c1bcdc9cd61f129461c51c432b85ff4abd40550f2f70500bbe99f6e0b3daf","abstract_canon_sha256":"511b753cddb0f1e35460095e915bc139fdb20b878f8829dc815aa1eff8e1700c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:11.057814Z","signature_b64":"tdHyG5GDzIi6RE+5QqEgw3h93ZbIPcDKOw6Wlwc3fwuK4iXD8WGBsskwx8JQPRIvOzYPerloGUFIAspli8dDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6ce55d2d1043e71a8ddc029f4b3144525e21ea93c791ff690de91050c2c143a","last_reissued_at":"2026-07-05T04:46:11.057337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:11.057337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ResVGAE: Going Deeper with Residual Modules for Link Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Aydin Ayanzadeh, Beh\\c{c}et U\\u{g}ur T\\\"oreyin, Indrit Nallbani, Nurullah \\c{C}al{\\i}k, Reyhan Kevser Keser","submitted_at":"2021-05-03T09:05:46Z","abstract_excerpt":"Graph autoencoders are efficient at embedding graph-based data sets. Most graph autoencoder architectures have shallow depths which limits their ability to capture meaningful relations between nodes separated by multi-hops. In this paper, we propose Residual Variational Graph Autoencoder, ResVGAE, a deep variational graph autoencoder model with multiple residual modules. We show that our multiple residual modules, a convolutional layer with residual connection, improve the average precision of the graph autoencoders. Experimental results suggest that our proposed model with residual modules ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.00695","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/2105.00695/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":"2105.00695","created_at":"2026-07-05T04:46:11.057387+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.00695v2","created_at":"2026-07-05T04:46:11.057387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.00695","created_at":"2026-07-05T04:46:11.057387+00:00"},{"alias_kind":"pith_short_12","alias_value":"63HFLUWRAQ7H","created_at":"2026-07-05T04:46:11.057387+00:00"},{"alias_kind":"pith_short_16","alias_value":"63HFLUWRAQ7HDKG5","created_at":"2026-07-05T04:46:11.057387+00:00"},{"alias_kind":"pith_short_8","alias_value":"63HFLUWR","created_at":"2026-07-05T04:46:11.057387+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.12177","citing_title":"Floorplan2Guide: LLM-Guided Floorplan Parsing for BLV Indoor Navigation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23970","citing_title":"LLM-Guided Agentic Floor Plan Parsing for Accessible Indoor Navigation of Blind and Low-Vision People","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/63HFLUWRAQ7HDKG5YAU7JMYUIU","json":"https://pith.science/pith/63HFLUWRAQ7HDKG5YAU7JMYUIU.json","graph_json":"https://pith.science/api/pith-number/63HFLUWRAQ7HDKG5YAU7JMYUIU/graph.json","events_json":"https://pith.science/api/pith-number/63HFLUWRAQ7HDKG5YAU7JMYUIU/events.json","paper":"https://pith.science/paper/63HFLUWR"},"agent_actions":{"view_html":"https://pith.science/pith/63HFLUWRAQ7HDKG5YAU7JMYUIU","download_json":"https://pith.science/pith/63HFLUWRAQ7HDKG5YAU7JMYUIU.json","view_paper":"https://pith.science/paper/63HFLUWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.00695&json=true","fetch_graph":"https://pith.science/api/pith-number/63HFLUWRAQ7HDKG5YAU7JMYUIU/graph.json","fetch_events":"https://pith.science/api/pith-number/63HFLUWRAQ7HDKG5YAU7JMYUIU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/63HFLUWRAQ7HDKG5YAU7JMYUIU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/63HFLUWRAQ7HDKG5YAU7JMYUIU/action/storage_attestation","attest_author":"https://pith.science/pith/63HFLUWRAQ7HDKG5YAU7JMYUIU/action/author_attestation","sign_citation":"https://pith.science/pith/63HFLUWRAQ7HDKG5YAU7JMYUIU/action/citation_signature","submit_replication":"https://pith.science/pith/63HFLUWRAQ7HDKG5YAU7JMYUIU/action/replication_record"}},"created_at":"2026-07-05T04:46:11.057387+00:00","updated_at":"2026-07-05T04:46:11.057387+00:00"}