{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HH45WWRETMULOIIBEYGKQW4E53","short_pith_number":"pith:HH45WWRE","schema_version":"1.0","canonical_sha256":"39f9db5a249b28b72101260ca85b84eeca29cf1099742811f2daf2ee905b1fb8","source":{"kind":"arxiv","id":"2305.18171","version":5},"attestation_state":"computed","paper":{"title":"Improved Probabilistic Image-Text Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Sanghyuk Chun","submitted_at":"2023-05-29T16:02:09Z","abstract_excerpt":"Image-Text Matching (ITM) task, a fundamental vision-language (VL) task, suffers from the inherent ambiguity arising from multiplicity and imperfect annotations. Deterministic functions are not sufficiently powerful to capture ambiguity, prompting the exploration of probabilistic embeddings to tackle the challenge. However, the existing probabilistic ITM approach encounters two key shortcomings; the burden of heavy computations due to the Monte Carlo approximation, and the loss saturation issue in the face of abundant false negatives. To overcome the issues, this paper presents an improved Pro"},"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":"2305.18171","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-29T16:02:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cb6c15ece3acee48629afb355d9f5a9d18e13df95821f86ac83fb168330f173b","abstract_canon_sha256":"17e00fa59b1d897df0605481c76d58a2abd3ac868121f399f871ab30071d0350"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:48.916735Z","signature_b64":"tVHHJjqBLnVEbjDzUnK+Fc+/B+MqmHm8PB+L3PVYaZsgz9dMcHP15jiW7uJdhFaxs4LzkOjdWOHZfd7kqVE0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39f9db5a249b28b72101260ca85b84eeca29cf1099742811f2daf2ee905b1fb8","last_reissued_at":"2026-07-05T08:05:48.916303Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:48.916303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Probabilistic Image-Text Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Sanghyuk Chun","submitted_at":"2023-05-29T16:02:09Z","abstract_excerpt":"Image-Text Matching (ITM) task, a fundamental vision-language (VL) task, suffers from the inherent ambiguity arising from multiplicity and imperfect annotations. Deterministic functions are not sufficiently powerful to capture ambiguity, prompting the exploration of probabilistic embeddings to tackle the challenge. However, the existing probabilistic ITM approach encounters two key shortcomings; the burden of heavy computations due to the Monte Carlo approximation, and the loss saturation issue in the face of abundant false negatives. To overcome the issues, this paper presents an improved Pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18171","kind":"arxiv","version":5},"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/2305.18171/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":"2305.18171","created_at":"2026-07-05T08:05:48.916371+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18171v5","created_at":"2026-07-05T08:05:48.916371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18171","created_at":"2026-07-05T08:05:48.916371+00:00"},{"alias_kind":"pith_short_12","alias_value":"HH45WWRETMUL","created_at":"2026-07-05T08:05:48.916371+00:00"},{"alias_kind":"pith_short_16","alias_value":"HH45WWRETMULOIIB","created_at":"2026-07-05T08:05:48.916371+00:00"},{"alias_kind":"pith_short_8","alias_value":"HH45WWRE","created_at":"2026-07-05T08:05:48.916371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04061","citing_title":"Intra-Modal Neighbors Never Lie: Rectifying Inter-Modal Noisy Correspondence via Graph-Based Intra-Modal Reasoning","ref_index":163,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HH45WWRETMULOIIBEYGKQW4E53","json":"https://pith.science/pith/HH45WWRETMULOIIBEYGKQW4E53.json","graph_json":"https://pith.science/api/pith-number/HH45WWRETMULOIIBEYGKQW4E53/graph.json","events_json":"https://pith.science/api/pith-number/HH45WWRETMULOIIBEYGKQW4E53/events.json","paper":"https://pith.science/paper/HH45WWRE"},"agent_actions":{"view_html":"https://pith.science/pith/HH45WWRETMULOIIBEYGKQW4E53","download_json":"https://pith.science/pith/HH45WWRETMULOIIBEYGKQW4E53.json","view_paper":"https://pith.science/paper/HH45WWRE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18171&json=true","fetch_graph":"https://pith.science/api/pith-number/HH45WWRETMULOIIBEYGKQW4E53/graph.json","fetch_events":"https://pith.science/api/pith-number/HH45WWRETMULOIIBEYGKQW4E53/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HH45WWRETMULOIIBEYGKQW4E53/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HH45WWRETMULOIIBEYGKQW4E53/action/storage_attestation","attest_author":"https://pith.science/pith/HH45WWRETMULOIIBEYGKQW4E53/action/author_attestation","sign_citation":"https://pith.science/pith/HH45WWRETMULOIIBEYGKQW4E53/action/citation_signature","submit_replication":"https://pith.science/pith/HH45WWRETMULOIIBEYGKQW4E53/action/replication_record"}},"created_at":"2026-07-05T08:05:48.916371+00:00","updated_at":"2026-07-05T08:05:48.916371+00:00"}