{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WF6UUVZYCL6AX7UTPCIREMVTW6","short_pith_number":"pith:WF6UUVZY","schema_version":"1.0","canonical_sha256":"b17d4a573812fc0bfe9378911232b3b793affe4b949df28632050f443ed96a97","source":{"kind":"arxiv","id":"2001.02359","version":2},"attestation_state":"computed","paper":{"title":"Weakly Supervised Visual Semantic Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alireza Zareian, Shih-Fu Chang, Svebor Karaman","submitted_at":"2020-01-08T03:46:13Z","abstract_excerpt":"Scene Graph Generation (SGG) aims to extract entities, predicates and their semantic structure from images, enabling deep understanding of visual content, with many applications such as visual reasoning and image retrieval. Nevertheless, existing SGG methods require millions of manually annotated bounding boxes for training, and are computationally inefficient, as they exhaustively process all pairs of object proposals to detect predicates. In this paper, we address those two limitations by first proposing a generalized formulation of SGG, namely Visual Semantic Parsing, which disentangles ent"},"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":"2001.02359","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-08T03:46:13Z","cross_cats_sorted":[],"title_canon_sha256":"71b9d09be945cfc425b273efb80fab18bc75501dfdea732f0128fc8ca800bbb3","abstract_canon_sha256":"ab3dce0836a697c742873a4cce9730b2dcc2ad9a3e4a7cb1fe856c2c17b6f2be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:54.018103Z","signature_b64":"lbbHjtbfzlL1YAq/JhZHo72uIgwAGs9Icb9lytca/8YFC5UmVTKCpzgXu89RNtIYjkqlc2Z+UBuJbbfL+vw/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b17d4a573812fc0bfe9378911232b3b793affe4b949df28632050f443ed96a97","last_reissued_at":"2026-07-05T00:51:54.017633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:54.017633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weakly Supervised Visual Semantic Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alireza Zareian, Shih-Fu Chang, Svebor Karaman","submitted_at":"2020-01-08T03:46:13Z","abstract_excerpt":"Scene Graph Generation (SGG) aims to extract entities, predicates and their semantic structure from images, enabling deep understanding of visual content, with many applications such as visual reasoning and image retrieval. Nevertheless, existing SGG methods require millions of manually annotated bounding boxes for training, and are computationally inefficient, as they exhaustively process all pairs of object proposals to detect predicates. In this paper, we address those two limitations by first proposing a generalized formulation of SGG, namely Visual Semantic Parsing, which disentangles ent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.02359","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/2001.02359/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":"2001.02359","created_at":"2026-07-05T00:51:54.017690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.02359v2","created_at":"2026-07-05T00:51:54.017690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.02359","created_at":"2026-07-05T00:51:54.017690+00:00"},{"alias_kind":"pith_short_12","alias_value":"WF6UUVZYCL6A","created_at":"2026-07-05T00:51:54.017690+00:00"},{"alias_kind":"pith_short_16","alias_value":"WF6UUVZYCL6AX7UT","created_at":"2026-07-05T00:51:54.017690+00:00"},{"alias_kind":"pith_short_8","alias_value":"WF6UUVZY","created_at":"2026-07-05T00:51:54.017690+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/WF6UUVZYCL6AX7UTPCIREMVTW6","json":"https://pith.science/pith/WF6UUVZYCL6AX7UTPCIREMVTW6.json","graph_json":"https://pith.science/api/pith-number/WF6UUVZYCL6AX7UTPCIREMVTW6/graph.json","events_json":"https://pith.science/api/pith-number/WF6UUVZYCL6AX7UTPCIREMVTW6/events.json","paper":"https://pith.science/paper/WF6UUVZY"},"agent_actions":{"view_html":"https://pith.science/pith/WF6UUVZYCL6AX7UTPCIREMVTW6","download_json":"https://pith.science/pith/WF6UUVZYCL6AX7UTPCIREMVTW6.json","view_paper":"https://pith.science/paper/WF6UUVZY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.02359&json=true","fetch_graph":"https://pith.science/api/pith-number/WF6UUVZYCL6AX7UTPCIREMVTW6/graph.json","fetch_events":"https://pith.science/api/pith-number/WF6UUVZYCL6AX7UTPCIREMVTW6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WF6UUVZYCL6AX7UTPCIREMVTW6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WF6UUVZYCL6AX7UTPCIREMVTW6/action/storage_attestation","attest_author":"https://pith.science/pith/WF6UUVZYCL6AX7UTPCIREMVTW6/action/author_attestation","sign_citation":"https://pith.science/pith/WF6UUVZYCL6AX7UTPCIREMVTW6/action/citation_signature","submit_replication":"https://pith.science/pith/WF6UUVZYCL6AX7UTPCIREMVTW6/action/replication_record"}},"created_at":"2026-07-05T00:51:54.017690+00:00","updated_at":"2026-07-05T00:51:54.017690+00:00"}