{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SX2DONPT7BC4AVTZV7ZMOF6KU6","short_pith_number":"pith:SX2DONPT","schema_version":"1.0","canonical_sha256":"95f43735f3f845c05679aff2c717caa7acdde3f4249249d0982c062a8ac70120","source":{"kind":"arxiv","id":"2607.27178","version":1},"attestation_state":"computed","paper":{"title":"DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Am\\'elie Chatelain, Antoine Chaffin, Paulo Roberto Moura Junior, Rapha\\\"el Sourty","submitted_at":"2026-07-29T17:50:51Z","abstract_excerpt":"State-of-the-art retrieval models increasingly rely on closed training data, creating a reproducibility gap. We present an open end-to-end recipe for training retrieval models and study how English supervision transfers to multilingual retrieval through translate-train. We first reconstruct and curate 665M English contrastive pre-training pairs from 1.4B pairs across 34 public sources and build 1.88M supervised fine-tuning pairs with mined hard negatives. Training yields two 149M-parameter models: DenseOn, a single-vector dense model, and LateOn, a ColBERT-style late-interaction model. They ac"},"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":"2607.27178","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-29T17:50:51Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"b4af44bcfa4d5be02956979d1516566d727856bdffdf1664ae70ae804595c293","abstract_canon_sha256":"a95705fd65be424beddc12666cb3ea1a705c2e56b1b9287572ca7143627e4569"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95f43735f3f845c05679aff2c717caa7acdde3f4249249d0982c062a8ac70120","last_reissued_at":"2026-07-30T01:23:57.983325Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:23:57.983325Z"},"graph_snapshot":{"paper":{"title":"DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Am\\'elie Chatelain, Antoine Chaffin, Paulo Roberto Moura Junior, Rapha\\\"el Sourty","submitted_at":"2026-07-29T17:50:51Z","abstract_excerpt":"State-of-the-art retrieval models increasingly rely on closed training data, creating a reproducibility gap. We present an open end-to-end recipe for training retrieval models and study how English supervision transfers to multilingual retrieval through translate-train. We first reconstruct and curate 665M English contrastive pre-training pairs from 1.4B pairs across 34 public sources and build 1.88M supervised fine-tuning pairs with mined hard negatives. Training yields two 149M-parameter models: DenseOn, a single-vector dense model, and LateOn, a ColBERT-style late-interaction model. They ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27178","kind":"arxiv","version":1},"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/2607.27178/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":"2607.27178","created_at":"2026-07-30T01:23:57.988219+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27178v1","created_at":"2026-07-30T01:23:57.988219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27178","created_at":"2026-07-30T01:23:57.988219+00:00"},{"alias_kind":"pith_short_12","alias_value":"SX2DONPT7BC4","created_at":"2026-07-30T01:23:57.988219+00:00"},{"alias_kind":"pith_short_16","alias_value":"SX2DONPT7BC4AVTZ","created_at":"2026-07-30T01:23:57.988219+00:00"},{"alias_kind":"pith_short_8","alias_value":"SX2DONPT","created_at":"2026-07-30T01:23:57.988219+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SX2DONPT7BC4AVTZV7ZMOF6KU6","json":"https://pith.science/pith/SX2DONPT7BC4AVTZV7ZMOF6KU6.json","graph_json":"https://pith.science/api/pith-number/SX2DONPT7BC4AVTZV7ZMOF6KU6/graph.json","events_json":"https://pith.science/api/pith-number/SX2DONPT7BC4AVTZV7ZMOF6KU6/events.json","paper":"https://pith.science/paper/SX2DONPT"},"agent_actions":{"view_html":"https://pith.science/pith/SX2DONPT7BC4AVTZV7ZMOF6KU6","download_json":"https://pith.science/pith/SX2DONPT7BC4AVTZV7ZMOF6KU6.json","view_paper":"https://pith.science/paper/SX2DONPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27178&json=true","fetch_graph":"https://pith.science/api/pith-number/SX2DONPT7BC4AVTZV7ZMOF6KU6/graph.json","fetch_events":"https://pith.science/api/pith-number/SX2DONPT7BC4AVTZV7ZMOF6KU6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SX2DONPT7BC4AVTZV7ZMOF6KU6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SX2DONPT7BC4AVTZV7ZMOF6KU6/action/storage_attestation","attest_author":"https://pith.science/pith/SX2DONPT7BC4AVTZV7ZMOF6KU6/action/author_attestation","sign_citation":"https://pith.science/pith/SX2DONPT7BC4AVTZV7ZMOF6KU6/action/citation_signature","submit_replication":"https://pith.science/pith/SX2DONPT7BC4AVTZV7ZMOF6KU6/action/replication_record"}},"created_at":"2026-07-30T01:23:57.988219+00:00","updated_at":"2026-07-30T01:23:57.988219+00:00"}