{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:22GDY7QWIHFZP4MNGIM4YWTBXL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b428e492997c0eb9ca21c0202403b64103369e1e253a8fe080c99495713eaefb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T21:05:04Z","title_canon_sha256":"3eb29dbe71ceabe82107bec305370681153557b51fe1548bbf183180392da1ef"},"schema_version":"1.0","source":{"id":"2410.16512","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16512","created_at":"2026-07-05T10:26:41Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16512v2","created_at":"2026-07-05T10:26:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16512","created_at":"2026-07-05T10:26:41Z"},{"alias_kind":"pith_short_12","alias_value":"22GDY7QWIHFZ","created_at":"2026-07-05T10:26:41Z"},{"alias_kind":"pith_short_16","alias_value":"22GDY7QWIHFZP4MN","created_at":"2026-07-05T10:26:41Z"},{"alias_kind":"pith_short_8","alias_value":"22GDY7QW","created_at":"2026-07-05T10:26:41Z"}],"graph_snapshots":[{"event_id":"sha256:c00c554340d8fc26fb870570bc14d16f2fa4d9f69c92dbff537adcee85ce2edf","target":"graph","created_at":"2026-07-05T10:26:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.16512/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T21:05:04Z","title":"TIPS: Text-Image Pretraining with Spatial awareness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16512","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b5170f6cfe3f3dd2f7dbcc778d31928a0c4a81f53b2124d421eeb95dae79f002","target":"record","created_at":"2026-07-05T10:26:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b428e492997c0eb9ca21c0202403b64103369e1e253a8fe080c99495713eaefb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T21:05:04Z","title_canon_sha256":"3eb29dbe71ceabe82107bec305370681153557b51fe1548bbf183180392da1ef"},"schema_version":"1.0","source":{"id":"2410.16512","kind":"arxiv","version":2}},"canonical_sha256":"d68c3c7e1641cb97f18d3219cc5a61bac06180333a622551b4dd0f2967568311","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d68c3c7e1641cb97f18d3219cc5a61bac06180333a622551b4dd0f2967568311","first_computed_at":"2026-07-05T10:26:41.071071Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:26:41.071071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EPKm1Fje91MRN4JYwnbLCslFzCCDJIPd8UJf+8lzbyI8oVj+iHuYEav2bBm7Bx/1U1WVN86ciIiXBVuX9Q5pBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:26:41.071723Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16512","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5170f6cfe3f3dd2f7dbcc778d31928a0c4a81f53b2124d421eeb95dae79f002","sha256:c00c554340d8fc26fb870570bc14d16f2fa4d9f69c92dbff537adcee85ce2edf"],"state_sha256":"697718b11a33121064a949c3ee9da3f54cc330ee0add96f5c2f6fcf09870b044"}