{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:F2MPIVR66GU6DZPUPC6EGJN3VB","short_pith_number":"pith:F2MPIVR6","schema_version":"1.0","canonical_sha256":"2e98f4563ef1a9e1e5f478bc4325bba85314dcf5becf062be9638ddc099da93d","source":{"kind":"arxiv","id":"2305.06343","version":2},"attestation_state":"computed","paper":{"title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alon Mendelson, Amir Globerson, Assaf Arbelle, Leonid Karlinsky, Roei Herzig, Rogerio Feris, Trevor Darrell","submitted_at":"2023-05-10T17:52:26Z","abstract_excerpt":"Vision and language models (VLMs) have demonstrated remarkable zero-shot (ZS) performance in a variety of tasks. However, recent works have shown that even the best VLMs struggle to capture aspects of compositional scene understanding, such as object attributes, relations, and action states. In contrast, obtaining structured annotations, such as scene graphs (SGs), that could improve these models is time-consuming and costly, and thus cannot be used on a large scale. Here we ask whether small SG datasets can provide sufficient information for enhancing structured understanding of pretrained VL"},"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":"2305.06343","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-10T17:52:26Z","cross_cats_sorted":[],"title_canon_sha256":"b6d81da13313ca8ef1d9c4f3af0204a41ba5a3c58596ace7a0094ebe869ff8cf","abstract_canon_sha256":"7a0a4e23780fdaec8d97ab2df509b01ff54831977cc281c42eb998c27e7dd7e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:46.904488Z","signature_b64":"CVx4b9jbjG6nTDxN8wwpuPWI+LzcB8UGgyyD6CoEhLjxX1zHLvl++hqRCsTvinEaurvWxd18n1o5F2fGZ23CCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e98f4563ef1a9e1e5f478bc4325bba85314dcf5becf062be9638ddc099da93d","last_reissued_at":"2026-07-05T07:04:46.904038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:46.904038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alon Mendelson, Amir Globerson, Assaf Arbelle, Leonid Karlinsky, Roei Herzig, Rogerio Feris, Trevor Darrell","submitted_at":"2023-05-10T17:52:26Z","abstract_excerpt":"Vision and language models (VLMs) have demonstrated remarkable zero-shot (ZS) performance in a variety of tasks. However, recent works have shown that even the best VLMs struggle to capture aspects of compositional scene understanding, such as object attributes, relations, and action states. In contrast, obtaining structured annotations, such as scene graphs (SGs), that could improve these models is time-consuming and costly, and thus cannot be used on a large scale. Here we ask whether small SG datasets can provide sufficient information for enhancing structured understanding of pretrained VL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06343","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/2305.06343/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":"2305.06343","created_at":"2026-07-05T07:04:46.904101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.06343v2","created_at":"2026-07-05T07:04:46.904101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06343","created_at":"2026-07-05T07:04:46.904101+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2MPIVR66GU6","created_at":"2026-07-05T07:04:46.904101+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2MPIVR66GU6DZPU","created_at":"2026-07-05T07:04:46.904101+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2MPIVR6","created_at":"2026-07-05T07:04:46.904101+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/F2MPIVR66GU6DZPUPC6EGJN3VB","json":"https://pith.science/pith/F2MPIVR66GU6DZPUPC6EGJN3VB.json","graph_json":"https://pith.science/api/pith-number/F2MPIVR66GU6DZPUPC6EGJN3VB/graph.json","events_json":"https://pith.science/api/pith-number/F2MPIVR66GU6DZPUPC6EGJN3VB/events.json","paper":"https://pith.science/paper/F2MPIVR6"},"agent_actions":{"view_html":"https://pith.science/pith/F2MPIVR66GU6DZPUPC6EGJN3VB","download_json":"https://pith.science/pith/F2MPIVR66GU6DZPUPC6EGJN3VB.json","view_paper":"https://pith.science/paper/F2MPIVR6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.06343&json=true","fetch_graph":"https://pith.science/api/pith-number/F2MPIVR66GU6DZPUPC6EGJN3VB/graph.json","fetch_events":"https://pith.science/api/pith-number/F2MPIVR66GU6DZPUPC6EGJN3VB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2MPIVR66GU6DZPUPC6EGJN3VB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2MPIVR66GU6DZPUPC6EGJN3VB/action/storage_attestation","attest_author":"https://pith.science/pith/F2MPIVR66GU6DZPUPC6EGJN3VB/action/author_attestation","sign_citation":"https://pith.science/pith/F2MPIVR66GU6DZPUPC6EGJN3VB/action/citation_signature","submit_replication":"https://pith.science/pith/F2MPIVR66GU6DZPUPC6EGJN3VB/action/replication_record"}},"created_at":"2026-07-05T07:04:46.904101+00:00","updated_at":"2026-07-05T07:04:46.904101+00:00"}