{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AMNCMNMEJBMQALEGQDOOL7VG47","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":"f4def17e77296114da1ee32521b30e2d190993127f596b5d9675593d6cd2d233","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-29T16:21:00Z","title_canon_sha256":"6bec2ef547dff4a8a4fb7ac575a0fdf705bd80f4141ddf3c0a4d176da209ede1"},"schema_version":"1.0","source":{"id":"2408.16672","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.16672","created_at":"2026-07-05T09:07:02Z"},{"alias_kind":"arxiv_version","alias_value":"2408.16672v4","created_at":"2026-07-05T09:07:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16672","created_at":"2026-07-05T09:07:02Z"},{"alias_kind":"pith_short_12","alias_value":"AMNCMNMEJBMQ","created_at":"2026-07-05T09:07:02Z"},{"alias_kind":"pith_short_16","alias_value":"AMNCMNMEJBMQALEG","created_at":"2026-07-05T09:07:02Z"},{"alias_kind":"pith_short_8","alias_value":"AMNCMNME","created_at":"2026-07-05T09:07:02Z"}],"graph_snapshots":[{"event_id":"sha256:4b5e15c8e0eec0f6d7b747abf25d97c01672f079baa6bf7384fab5427dc21a60","target":"graph","created_at":"2026-07-05T09:07:02Z","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/2408.16672/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-vector dense models, such as ColBERT, have proven highly effective in information retrieval. ColBERT's late interaction scoring approximates the joint query-document attention seen in cross-encoders while maintaining inference efficiency closer to traditional dense retrieval models, thanks to its bi-encoder architecture and recent optimizations in indexing and search. In this work we propose a number of incremental improvements to the ColBERT model architecture and training pipeline, using methods shown to work in the more mature single-vector embedding model training paradigm, particula","authors_text":"Andreas Koukounas, Bo Wang, Georgios Mastrapas, Han Xiao, Isabelle Mohr, Michael G\\\"unther, Mohammad Kalim Akram, Nan Wang, Rohan Jha, Saba Sturua","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-29T16:21:00Z","title":"Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16672","kind":"arxiv","version":4},"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":"sha256:3beb57c042edbde8e33b2c09fa11578136e80082cf49d22190d09458f566f1a3","target":"record","created_at":"2026-07-05T09:07:02Z","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":"f4def17e77296114da1ee32521b30e2d190993127f596b5d9675593d6cd2d233","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-29T16:21:00Z","title_canon_sha256":"6bec2ef547dff4a8a4fb7ac575a0fdf705bd80f4141ddf3c0a4d176da209ede1"},"schema_version":"1.0","source":{"id":"2408.16672","kind":"arxiv","version":4}},"canonical_sha256":"031a2635844859002c8680dce5fea6e7e96234b9aff063310194a3cdc38ad1b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"031a2635844859002c8680dce5fea6e7e96234b9aff063310194a3cdc38ad1b9","first_computed_at":"2026-07-05T09:07:02.602730Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:07:02.602730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"244Rxy7LF68e8Pz2IbH05LCuJ7hBs0aBiW2nWoLjDK+AZFbJ5OGl9GHqkMwv1E/FAAtGJksnb6qfVAUVKpRLBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:07:02.603194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.16672","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3beb57c042edbde8e33b2c09fa11578136e80082cf49d22190d09458f566f1a3","sha256:4b5e15c8e0eec0f6d7b747abf25d97c01672f079baa6bf7384fab5427dc21a60"],"state_sha256":"ae2cc7e87645301486e800d3d028792f8e7592fef08525c5e651c80f0579d38a"}