{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:22GDY7QWIHFZP4MNGIM4YWTBXL","short_pith_number":"pith:22GDY7QW","schema_version":"1.0","canonical_sha256":"d68c3c7e1641cb97f18d3219cc5a61bac06180333a622551b4dd0f2967568311","source":{"kind":"arxiv","id":"2410.16512","version":2},"attestation_state":"computed","paper":{"title":"TIPS: Text-Image Pretraining with Spatial awareness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andre Araujo, Arjun Karpur, Bingyi Cao, Dan Gnanapragasam, Daniel Salz, Guangxing Han, Howard Zhou, Jan Dlabal, Kaifeng Chen, Kevis-Kokitsi Maninis, Koert Chen, Mojtaba Seyedhosseini, Soham Ghosh, Ye Xia","submitted_at":"2024-10-21T21:05:04Z","abstract_excerpt":"While image-text representation learning has become very popular in recent years, existing models tend to lack spatial awareness and have limited direct applicability for dense understanding tasks. For this reason, self-supervised image-only pretraining is still the go-to method for many dense vision applications (e.g. depth estimation, semantic segmentation), despite the lack of explicit supervisory signals. In this paper, we close this gap between image-text and self-supervised learning, by proposing a novel general-purpose image-text model, which can be effectively used off the shelf for de"},"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":"2410.16512","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T21:05:04Z","cross_cats_sorted":[],"title_canon_sha256":"3eb29dbe71ceabe82107bec305370681153557b51fe1548bbf183180392da1ef","abstract_canon_sha256":"b428e492997c0eb9ca21c0202403b64103369e1e253a8fe080c99495713eaefb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:41.071723Z","signature_b64":"EPKm1Fje91MRN4JYwnbLCslFzCCDJIPd8UJf+8lzbyI8oVj+iHuYEav2bBm7Bx/1U1WVN86ciIiXBVuX9Q5pBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d68c3c7e1641cb97f18d3219cc5a61bac06180333a622551b4dd0f2967568311","last_reissued_at":"2026-07-05T10:26:41.071071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:41.071071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TIPS: Text-Image Pretraining with Spatial awareness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andre Araujo, Arjun Karpur, Bingyi Cao, Dan Gnanapragasam, Daniel Salz, Guangxing Han, Howard Zhou, Jan Dlabal, Kaifeng Chen, Kevis-Kokitsi Maninis, Koert Chen, Mojtaba Seyedhosseini, Soham Ghosh, Ye Xia","submitted_at":"2024-10-21T21:05:04Z","abstract_excerpt":"While image-text representation learning has become very popular in recent years, existing models tend to lack spatial awareness and have limited direct applicability for dense understanding tasks. For this reason, self-supervised image-only pretraining is still the go-to method for many dense vision applications (e.g. depth estimation, semantic segmentation), despite the lack of explicit supervisory signals. In this paper, we close this gap between image-text and self-supervised learning, by proposing a novel general-purpose image-text model, which can be effectively used off the shelf for de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16512","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/2410.16512/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":"2410.16512","created_at":"2026-07-05T10:26:41.071146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16512v2","created_at":"2026-07-05T10:26:41.071146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16512","created_at":"2026-07-05T10:26:41.071146+00:00"},{"alias_kind":"pith_short_12","alias_value":"22GDY7QWIHFZ","created_at":"2026-07-05T10:26:41.071146+00:00"},{"alias_kind":"pith_short_16","alias_value":"22GDY7QWIHFZP4MN","created_at":"2026-07-05T10:26:41.071146+00:00"},{"alias_kind":"pith_short_8","alias_value":"22GDY7QW","created_at":"2026-07-05T10:26:41.071146+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27295","citing_title":"Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21906","citing_title":"Universal CT Representations from Anatomy to Disease Phenotype through Agglomerative Pretraining","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21906","citing_title":"Universal CT Representations from Anatomy to Disease Phenotype through Agglomerative Pretraining","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19622","citing_title":"UniRefiner: Teaching Pre-trained ViTs to Self-Dispose Dross via Contrastive Register","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22123","citing_title":"Multilingual Vision-Language Models, A Survey","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00937","citing_title":"CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2504.13181","citing_title":"Perception Encoder: The best visual embeddings are not at the output of the network","ref_index":90,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/22GDY7QWIHFZP4MNGIM4YWTBXL","json":"https://pith.science/pith/22GDY7QWIHFZP4MNGIM4YWTBXL.json","graph_json":"https://pith.science/api/pith-number/22GDY7QWIHFZP4MNGIM4YWTBXL/graph.json","events_json":"https://pith.science/api/pith-number/22GDY7QWIHFZP4MNGIM4YWTBXL/events.json","paper":"https://pith.science/paper/22GDY7QW"},"agent_actions":{"view_html":"https://pith.science/pith/22GDY7QWIHFZP4MNGIM4YWTBXL","download_json":"https://pith.science/pith/22GDY7QWIHFZP4MNGIM4YWTBXL.json","view_paper":"https://pith.science/paper/22GDY7QW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16512&json=true","fetch_graph":"https://pith.science/api/pith-number/22GDY7QWIHFZP4MNGIM4YWTBXL/graph.json","fetch_events":"https://pith.science/api/pith-number/22GDY7QWIHFZP4MNGIM4YWTBXL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/22GDY7QWIHFZP4MNGIM4YWTBXL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/22GDY7QWIHFZP4MNGIM4YWTBXL/action/storage_attestation","attest_author":"https://pith.science/pith/22GDY7QWIHFZP4MNGIM4YWTBXL/action/author_attestation","sign_citation":"https://pith.science/pith/22GDY7QWIHFZP4MNGIM4YWTBXL/action/citation_signature","submit_replication":"https://pith.science/pith/22GDY7QWIHFZP4MNGIM4YWTBXL/action/replication_record"}},"created_at":"2026-07-05T10:26:41.071146+00:00","updated_at":"2026-07-05T10:26:41.071146+00:00"}