{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UGY6RNCB67KA55ZA3VYYVLBMYW","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":"120193e188e461f536c9ced7d0d41aca2eac17419a917cd34149323fc9b03a26","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T22:20:04Z","title_canon_sha256":"34fb3b669afda398e1066accb189ea44419fdef4439c042eb6b7bad893902927"},"schema_version":"1.0","source":{"id":"2507.05513","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05513","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05513v1","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05513","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"pith_short_12","alias_value":"UGY6RNCB67KA","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"pith_short_16","alias_value":"UGY6RNCB67KA55ZA","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"pith_short_8","alias_value":"UGY6RNCB","created_at":"2026-07-05T11:33:31Z"}],"graph_snapshots":[{"event_id":"sha256:0004ceabb6d16350538731759213b1d377dd378870fab5dec1861d9b6088cf6b","target":"graph","created_at":"2026-07-05T11:33:31Z","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/2507.05513/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Motivated by the growing demand for retrieval systems that operate across modalities, we introduce llama-nemoretriever-colembed, a unified text-image retrieval model that delivers state-of-the-art performance across multiple benchmarks. We release two model variants, 1B and 3B. The 3B model achieves state of the art performance, scoring NDCG@5 91.0 on ViDoRe V1 and 63.5 on ViDoRe V2, placing first on both leaderboards as of June 27, 2025.\n  Our approach leverages the NVIDIA Eagle2 Vision-Language model (VLM), modifies its architecture by replacing causal attention with bidirectional attention,","authors_text":"Benedikt Schifferer, Even Oldridge, Gabriel Moreira, Mengyao Xu, Radek Osmulski, Ronay Ak, Yauhen Babakhin, Zhiding Yu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T22:20:04Z","title":"Llama Nemoretriever Colembed: Top-Performing Text-Image Retrieval Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05513","kind":"arxiv","version":1},"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:ea020e508fd13c7a5e6d7ae6c4efee5dd7b29d4511b56bffd9b94bdcb2f23187","target":"record","created_at":"2026-07-05T11:33:31Z","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":"120193e188e461f536c9ced7d0d41aca2eac17419a917cd34149323fc9b03a26","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T22:20:04Z","title_canon_sha256":"34fb3b669afda398e1066accb189ea44419fdef4439c042eb6b7bad893902927"},"schema_version":"1.0","source":{"id":"2507.05513","kind":"arxiv","version":1}},"canonical_sha256":"a1b1e8b441f7d40ef720dd718aac2cc5b82302c63fc3c8ba8a6a93e8e03f1183","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1b1e8b441f7d40ef720dd718aac2cc5b82302c63fc3c8ba8a6a93e8e03f1183","first_computed_at":"2026-07-05T11:33:31.672129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:31.672129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4A3T8j1vPWTItTn/kJowtWceAANBwYvU4wtMl9HBs/l/vt7CsLQRk6A1nrCweptPWk/PcpPLDcark6MPtvapAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:31.672561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05513","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea020e508fd13c7a5e6d7ae6c4efee5dd7b29d4511b56bffd9b94bdcb2f23187","sha256:0004ceabb6d16350538731759213b1d377dd378870fab5dec1861d9b6088cf6b"],"state_sha256":"6264d82d94c47b902074c27dca8c3c27f5f9a1114f1b92a5efa6031e7ed3d239"}