{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3QVKD4DIGARKC234OSBDBY3QTP","short_pith_number":"pith:3QVKD4DI","schema_version":"1.0","canonical_sha256":"dc2aa1f0683022a16b7c748230e3709bc7bbe02d591dacc946848f317acbdc79","source":{"kind":"arxiv","id":"2311.13258","version":1},"attestation_state":"computed","paper":{"title":"ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Derek Hoiem, Heng Ji, Manling Li, Xingyao Wang, Yangyi Chen","submitted_at":"2023-11-22T09:23:34Z","abstract_excerpt":"State-of-the-art vision-language models (VLMs) still have limited performance in structural knowledge extraction, such as relations between objects. In this work, we present ViStruct, a training framework to learn VLMs for effective visual structural knowledge extraction. Two novel designs are incorporated. First, we propose to leverage the inherent structure of programming language to depict visual structural information. This approach enables explicit and consistent representation of visual structural information of multiple granularities, such as concepts, relations, and events, in a well-o"},"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":"2311.13258","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-22T09:23:34Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"d1aa14025df0bedda7aeb2ba1c2a91fb910bd05895b23035d6224b4c05428c58","abstract_canon_sha256":"785dedc309034a3d76d22250afa0bc0021a362985fddc32f7736a745bf0fc06e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:15:26.797109Z","signature_b64":"YidYpnnSMWnIK77tzASknVt9FBofGToBXBSsO6lmUODrW+wS10JVi8LP1ZRpxGMNCF50+E/Yi4ZKzUJ7DkhHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc2aa1f0683022a16b7c748230e3709bc7bbe02d591dacc946848f317acbdc79","last_reissued_at":"2026-07-05T07:15:26.796611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:15:26.796611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Derek Hoiem, Heng Ji, Manling Li, Xingyao Wang, Yangyi Chen","submitted_at":"2023-11-22T09:23:34Z","abstract_excerpt":"State-of-the-art vision-language models (VLMs) still have limited performance in structural knowledge extraction, such as relations between objects. In this work, we present ViStruct, a training framework to learn VLMs for effective visual structural knowledge extraction. Two novel designs are incorporated. First, we propose to leverage the inherent structure of programming language to depict visual structural information. This approach enables explicit and consistent representation of visual structural information of multiple granularities, such as concepts, relations, and events, in a well-o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13258","kind":"arxiv","version":1},"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/2311.13258/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":"2311.13258","created_at":"2026-07-05T07:15:26.796678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.13258v1","created_at":"2026-07-05T07:15:26.796678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13258","created_at":"2026-07-05T07:15:26.796678+00:00"},{"alias_kind":"pith_short_12","alias_value":"3QVKD4DIGARK","created_at":"2026-07-05T07:15:26.796678+00:00"},{"alias_kind":"pith_short_16","alias_value":"3QVKD4DIGARKC234","created_at":"2026-07-05T07:15:26.796678+00:00"},{"alias_kind":"pith_short_8","alias_value":"3QVKD4DI","created_at":"2026-07-05T07:15:26.796678+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.08971","citing_title":"Prioritizing Image-Related Tokens Enhances Vision-Language Pre-Training","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3QVKD4DIGARKC234OSBDBY3QTP","json":"https://pith.science/pith/3QVKD4DIGARKC234OSBDBY3QTP.json","graph_json":"https://pith.science/api/pith-number/3QVKD4DIGARKC234OSBDBY3QTP/graph.json","events_json":"https://pith.science/api/pith-number/3QVKD4DIGARKC234OSBDBY3QTP/events.json","paper":"https://pith.science/paper/3QVKD4DI"},"agent_actions":{"view_html":"https://pith.science/pith/3QVKD4DIGARKC234OSBDBY3QTP","download_json":"https://pith.science/pith/3QVKD4DIGARKC234OSBDBY3QTP.json","view_paper":"https://pith.science/paper/3QVKD4DI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.13258&json=true","fetch_graph":"https://pith.science/api/pith-number/3QVKD4DIGARKC234OSBDBY3QTP/graph.json","fetch_events":"https://pith.science/api/pith-number/3QVKD4DIGARKC234OSBDBY3QTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3QVKD4DIGARKC234OSBDBY3QTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3QVKD4DIGARKC234OSBDBY3QTP/action/storage_attestation","attest_author":"https://pith.science/pith/3QVKD4DIGARKC234OSBDBY3QTP/action/author_attestation","sign_citation":"https://pith.science/pith/3QVKD4DIGARKC234OSBDBY3QTP/action/citation_signature","submit_replication":"https://pith.science/pith/3QVKD4DIGARKC234OSBDBY3QTP/action/replication_record"}},"created_at":"2026-07-05T07:15:26.796678+00:00","updated_at":"2026-07-05T07:15:26.796678+00:00"}