{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RHGETQJ6AGCYJIDDZ44GOVBMTH","short_pith_number":"pith:RHGETQJ6","schema_version":"1.0","canonical_sha256":"89cc49c13e018584a063cf3867542c99d058daf5d3787915292b25fa3d73d2b3","source":{"kind":"arxiv","id":"2301.13081","version":2},"attestation_state":"computed","paper":{"title":"STAIR: Learning Sparse Text and Image Representation in Grounded Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Albin Madappally Jose, Alexander Toshev, Bowen Zhang, Chen Chen, Jiguang Shen, Jonathon Shlens, Liangliang Cao, Ruoming Pang, Tom Gunter, Yinfei Yang","submitted_at":"2023-01-30T17:21:30Z","abstract_excerpt":"Image and text retrieval is one of the foundational tasks in the vision and language domain with multiple real-world applications. State-of-the-art approaches, e.g. CLIP, ALIGN, represent images and texts as dense embeddings and calculate the similarity in the dense embedding space as the matching score. On the other hand, sparse semantic features like bag-of-words models are more interpretable, but believed to suffer from inferior accuracy than dense representations. In this work, we show that it is possible to build a sparse semantic representation that is as powerful as, or even better than"},"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":"2301.13081","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-30T17:21:30Z","cross_cats_sorted":[],"title_canon_sha256":"545325b75cf41c9fdd1b6747f84142680a179e6f6f4e07fa4319d051c89d55cc","abstract_canon_sha256":"36d6dc5520bbef692b3319ee861268f09be8ab54a90a30f8fc155019d54e5c88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:39:55.921469Z","signature_b64":"WBtxjwrwOnssRA12g7axwFHlKSW+iM/ZP9lE+iNPPjDEOd/g7MSp8DqEnFi2ZzAL1AcVl+6jswdrnPGPJY+jAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89cc49c13e018584a063cf3867542c99d058daf5d3787915292b25fa3d73d2b3","last_reissued_at":"2026-07-05T05:39:55.920965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:39:55.920965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STAIR: Learning Sparse Text and Image Representation in Grounded Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Albin Madappally Jose, Alexander Toshev, Bowen Zhang, Chen Chen, Jiguang Shen, Jonathon Shlens, Liangliang Cao, Ruoming Pang, Tom Gunter, Yinfei Yang","submitted_at":"2023-01-30T17:21:30Z","abstract_excerpt":"Image and text retrieval is one of the foundational tasks in the vision and language domain with multiple real-world applications. State-of-the-art approaches, e.g. CLIP, ALIGN, represent images and texts as dense embeddings and calculate the similarity in the dense embedding space as the matching score. On the other hand, sparse semantic features like bag-of-words models are more interpretable, but believed to suffer from inferior accuracy than dense representations. In this work, we show that it is possible to build a sparse semantic representation that is as powerful as, or even better than"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13081","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/2301.13081/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":"2301.13081","created_at":"2026-07-05T05:39:55.921023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13081v2","created_at":"2026-07-05T05:39:55.921023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13081","created_at":"2026-07-05T05:39:55.921023+00:00"},{"alias_kind":"pith_short_12","alias_value":"RHGETQJ6AGCY","created_at":"2026-07-05T05:39:55.921023+00:00"},{"alias_kind":"pith_short_16","alias_value":"RHGETQJ6AGCYJIDD","created_at":"2026-07-05T05:39:55.921023+00:00"},{"alias_kind":"pith_short_8","alias_value":"RHGETQJ6","created_at":"2026-07-05T05:39:55.921023+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30027","citing_title":"DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RHGETQJ6AGCYJIDDZ44GOVBMTH","json":"https://pith.science/pith/RHGETQJ6AGCYJIDDZ44GOVBMTH.json","graph_json":"https://pith.science/api/pith-number/RHGETQJ6AGCYJIDDZ44GOVBMTH/graph.json","events_json":"https://pith.science/api/pith-number/RHGETQJ6AGCYJIDDZ44GOVBMTH/events.json","paper":"https://pith.science/paper/RHGETQJ6"},"agent_actions":{"view_html":"https://pith.science/pith/RHGETQJ6AGCYJIDDZ44GOVBMTH","download_json":"https://pith.science/pith/RHGETQJ6AGCYJIDDZ44GOVBMTH.json","view_paper":"https://pith.science/paper/RHGETQJ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13081&json=true","fetch_graph":"https://pith.science/api/pith-number/RHGETQJ6AGCYJIDDZ44GOVBMTH/graph.json","fetch_events":"https://pith.science/api/pith-number/RHGETQJ6AGCYJIDDZ44GOVBMTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RHGETQJ6AGCYJIDDZ44GOVBMTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RHGETQJ6AGCYJIDDZ44GOVBMTH/action/storage_attestation","attest_author":"https://pith.science/pith/RHGETQJ6AGCYJIDDZ44GOVBMTH/action/author_attestation","sign_citation":"https://pith.science/pith/RHGETQJ6AGCYJIDDZ44GOVBMTH/action/citation_signature","submit_replication":"https://pith.science/pith/RHGETQJ6AGCYJIDDZ44GOVBMTH/action/replication_record"}},"created_at":"2026-07-05T05:39:55.921023+00:00","updated_at":"2026-07-05T05:39:55.921023+00:00"}