{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XLPKTF4WLNJ3YPOYOQKKH4UR6V","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":"78a9f88056bbe0b1cb2c802b7154e7892be3c957f4a4220a5ac236baee7eb138","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T16:48:01Z","title_canon_sha256":"39be0f5add8f32a57727f0d07c716ba10f00e259c629e356a3ee4ff06d3930ad"},"schema_version":"1.0","source":{"id":"2211.12402","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.12402","created_at":"2026-07-05T06:35:46Z"},{"alias_kind":"arxiv_version","alias_value":"2211.12402v2","created_at":"2026-07-05T06:35:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12402","created_at":"2026-07-05T06:35:46Z"},{"alias_kind":"pith_short_12","alias_value":"XLPKTF4WLNJ3","created_at":"2026-07-05T06:35:46Z"},{"alias_kind":"pith_short_16","alias_value":"XLPKTF4WLNJ3YPOY","created_at":"2026-07-05T06:35:46Z"},{"alias_kind":"pith_short_8","alias_value":"XLPKTF4W","created_at":"2026-07-05T06:35:46Z"}],"graph_snapshots":[{"event_id":"sha256:60355647583ad7f7f284e3b7e65ea670a3ac11742cb91fbd0111c3131a3a20dd","target":"graph","created_at":"2026-07-05T06:35:46Z","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/2211.12402/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision language pre-training aims to learn alignments between vision and language from a large amount of data. Most existing methods only learn image-text alignments. Some others utilize pre-trained object detectors to leverage vision language alignments at the object level. In this paper, we propose to learn multi-grained vision language alignments by a unified pre-training framework that learns multi-grained aligning and multi-grained localization simultaneously. Based on it, we present X$^2$-VLM, an all-in-one model with a flexible modular architecture, in which we further unify image-text ","authors_text":"Hang Li, Jiawei Wang, Jipeng Zhang, Wangchunshu Zhou, Xinsong Zhang, Yan Zeng","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T16:48:01Z","title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12402","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:fdc5c49ded97eb8fe26110b3995df93150129e8cc54d9dd2f6172153bdc4a8a9","target":"record","created_at":"2026-07-05T06:35:46Z","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":"78a9f88056bbe0b1cb2c802b7154e7892be3c957f4a4220a5ac236baee7eb138","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T16:48:01Z","title_canon_sha256":"39be0f5add8f32a57727f0d07c716ba10f00e259c629e356a3ee4ff06d3930ad"},"schema_version":"1.0","source":{"id":"2211.12402","kind":"arxiv","version":2}},"canonical_sha256":"badea997965b53bc3dd87414a3f291f5525e2295988d2a3ed90107f8be279c19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"badea997965b53bc3dd87414a3f291f5525e2295988d2a3ed90107f8be279c19","first_computed_at":"2026-07-05T06:35:46.425728Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:35:46.425728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vKugHxgXyykMTKNmWWbwKy3d8gwnA3V9bJ/JKUs/eQslzq3066H2XAqFRJ5ra7SulxMFKZPtn81wb3cNyVugCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:35:46.427119Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.12402","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fdc5c49ded97eb8fe26110b3995df93150129e8cc54d9dd2f6172153bdc4a8a9","sha256:60355647583ad7f7f284e3b7e65ea670a3ac11742cb91fbd0111c3131a3a20dd"],"state_sha256":"7e0c67b0e1482dcf4121fc80ede9157022f6f142b97e8a4024be63dd4fb8abad"}