{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CVVYJATEYKKOT6HC5NNVCNYOFM","short_pith_number":"pith:CVVYJATE","schema_version":"1.0","canonical_sha256":"156b848264c294e9f8e2eb5b51370e2b17ede9bfa86567bc6fdc83208f555fb7","source":{"kind":"arxiv","id":"2412.15396","version":2},"attestation_state":"computed","paper":{"title":"Learning Visual Composition through Improved Semantic Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Abhijit Ogale, Austin Stone, Bingyi Cao, Hagen Soltau, Jonathon Shlens, Kaifeng Chen, Robert Geirhos, Xi Yi, Ye Xia","submitted_at":"2024-12-19T20:58:26Z","abstract_excerpt":"Visual imagery does not consist of solitary objects, but instead reflects the composition of a multitude of fluid concepts. While there have been great advances in visual representation learning, such advances have focused on building better representations for a small number of discrete objects bereft of an understanding of how these objects are interacting. One can observe this limitation in representations learned through captions or contrastive learning -- where the learned model treats an image essentially as a bag of words. Several works have attempted to address this limitation through "},"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":"2412.15396","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T20:58:26Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"title_canon_sha256":"95b15bd72345de541994cace0723310b55e79acefde2cfa9a823418e7fa75e51","abstract_canon_sha256":"0f15a9ace5618d830fd2d4792dbcdcb9f85545366b92342e2f733e1c6cae3948"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:21.026011Z","signature_b64":"oZVrDhiisOwLQ7mFuVy3QQIXb/LBUXeTDKpuO76ccWyPd20yBY4FWNNjaPcLQOqBtMpKIVFV3jNnBzqK7tzeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"156b848264c294e9f8e2eb5b51370e2b17ede9bfa86567bc6fdc83208f555fb7","last_reissued_at":"2026-07-05T10:44:21.025522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:21.025522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Visual Composition through Improved Semantic Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Abhijit Ogale, Austin Stone, Bingyi Cao, Hagen Soltau, Jonathon Shlens, Kaifeng Chen, Robert Geirhos, Xi Yi, Ye Xia","submitted_at":"2024-12-19T20:58:26Z","abstract_excerpt":"Visual imagery does not consist of solitary objects, but instead reflects the composition of a multitude of fluid concepts. While there have been great advances in visual representation learning, such advances have focused on building better representations for a small number of discrete objects bereft of an understanding of how these objects are interacting. One can observe this limitation in representations learned through captions or contrastive learning -- where the learned model treats an image essentially as a bag of words. Several works have attempted to address this limitation through "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15396","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/2412.15396/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":"2412.15396","created_at":"2026-07-05T10:44:21.025584+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.15396v2","created_at":"2026-07-05T10:44:21.025584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15396","created_at":"2026-07-05T10:44:21.025584+00:00"},{"alias_kind":"pith_short_12","alias_value":"CVVYJATEYKKO","created_at":"2026-07-05T10:44:21.025584+00:00"},{"alias_kind":"pith_short_16","alias_value":"CVVYJATEYKKOT6HC","created_at":"2026-07-05T10:44:21.025584+00:00"},{"alias_kind":"pith_short_8","alias_value":"CVVYJATE","created_at":"2026-07-05T10:44:21.025584+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/CVVYJATEYKKOT6HC5NNVCNYOFM","json":"https://pith.science/pith/CVVYJATEYKKOT6HC5NNVCNYOFM.json","graph_json":"https://pith.science/api/pith-number/CVVYJATEYKKOT6HC5NNVCNYOFM/graph.json","events_json":"https://pith.science/api/pith-number/CVVYJATEYKKOT6HC5NNVCNYOFM/events.json","paper":"https://pith.science/paper/CVVYJATE"},"agent_actions":{"view_html":"https://pith.science/pith/CVVYJATEYKKOT6HC5NNVCNYOFM","download_json":"https://pith.science/pith/CVVYJATEYKKOT6HC5NNVCNYOFM.json","view_paper":"https://pith.science/paper/CVVYJATE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.15396&json=true","fetch_graph":"https://pith.science/api/pith-number/CVVYJATEYKKOT6HC5NNVCNYOFM/graph.json","fetch_events":"https://pith.science/api/pith-number/CVVYJATEYKKOT6HC5NNVCNYOFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CVVYJATEYKKOT6HC5NNVCNYOFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CVVYJATEYKKOT6HC5NNVCNYOFM/action/storage_attestation","attest_author":"https://pith.science/pith/CVVYJATEYKKOT6HC5NNVCNYOFM/action/author_attestation","sign_citation":"https://pith.science/pith/CVVYJATEYKKOT6HC5NNVCNYOFM/action/citation_signature","submit_replication":"https://pith.science/pith/CVVYJATEYKKOT6HC5NNVCNYOFM/action/replication_record"}},"created_at":"2026-07-05T10:44:21.025584+00:00","updated_at":"2026-07-05T10:44:21.025584+00:00"}