{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7IM5TL5PZQ6PQLGG6DUEC6JXGC","short_pith_number":"pith:7IM5TL5P","canonical_record":{"source":{"id":"2306.02867","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2023-06-05T13:41:10Z","cross_cats_sorted":[],"title_canon_sha256":"29d09f067e889dc2b659f6af223aa4bbf82d2a337293f499db78ffa2ecd4ff22","abstract_canon_sha256":"db1867d8ebf6db75e8282667e87d93977a85cf835dca2d62bd5679ce8fc39b1a"},"schema_version":"1.0"},"canonical_sha256":"fa19d9afafcc3cf82cc6f0e841793730a914c57fe206b8ab2495d6657f385c90","source":{"kind":"arxiv","id":"2306.02867","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02867","created_at":"2026-07-05T06:17:32Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02867v1","created_at":"2026-07-05T06:17:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02867","created_at":"2026-07-05T06:17:32Z"},{"alias_kind":"pith_short_12","alias_value":"7IM5TL5PZQ6P","created_at":"2026-07-05T06:17:32Z"},{"alias_kind":"pith_short_16","alias_value":"7IM5TL5PZQ6PQLGG","created_at":"2026-07-05T06:17:32Z"},{"alias_kind":"pith_short_8","alias_value":"7IM5TL5P","created_at":"2026-07-05T06:17:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7IM5TL5PZQ6PQLGG6DUEC6JXGC","target":"record","payload":{"canonical_record":{"source":{"id":"2306.02867","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2023-06-05T13:41:10Z","cross_cats_sorted":[],"title_canon_sha256":"29d09f067e889dc2b659f6af223aa4bbf82d2a337293f499db78ffa2ecd4ff22","abstract_canon_sha256":"db1867d8ebf6db75e8282667e87d93977a85cf835dca2d62bd5679ce8fc39b1a"},"schema_version":"1.0"},"canonical_sha256":"fa19d9afafcc3cf82cc6f0e841793730a914c57fe206b8ab2495d6657f385c90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:32.218513Z","signature_b64":"Zr+uDHM98z9hY4TOyfMEk2YOUWeUmbUsgggUgGAGNOtfcRlrj2FZGYLuqhUGPNw/lFX8ITdaPNRDa4PcoIpwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa19d9afafcc3cf82cc6f0e841793730a914c57fe206b8ab2495d6657f385c90","last_reissued_at":"2026-07-05T06:17:32.218080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:32.218080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.02867","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:17:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7vsD32dX7dHF8FZzKHaFuJiFcolWws3se8CEJQ0gfMC/S2yBkzbej5Vc+9w8LXNeMXEMqjw2wvKoV3BunI38Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:20:11.571628Z"},"content_sha256":"7eb58cdfb15deb00c08cffcc7d653d1564f476b1d377bd5f6a315bbc672d5841","schema_version":"1.0","event_id":"sha256:7eb58cdfb15deb00c08cffcc7d653d1564f476b1d377bd5f6a315bbc672d5841"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7IM5TL5PZQ6PQLGG6DUEC6JXGC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Middle-Trained Language Models for Neural Search","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Carlos Lassance, Herv\\'e D\\'ejean, Simon Lupart, St\\'ephane Clinchant, Thibault Formal","submitted_at":"2023-06-05T13:41:10Z","abstract_excerpt":"Middle training methods aim to bridge the gap between the Masked Language Model (MLM) pre-training and the final finetuning for retrieval. Recent models such as CoCondenser, RetroMAE, and LexMAE argue that the MLM task is not sufficient enough to pre-train a transformer network for retrieval and hence propose various tasks to do so. Intrigued by those novel methods, we noticed that all these models used different finetuning protocols, making it hard to assess the benefits of middle training. We propose in this paper a benchmark of CoCondenser, RetroMAE, and LexMAE, under the same finetuning co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02867","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/2306.02867/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:17:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eVxOF3PYVW3yCOU8RDDeLg7BThluUvxKp5FlxxuD1HYL7xATpt3ELnmwjrIilVbbvCYl7+Qx8g7rSxvjwkIHDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:20:11.572014Z"},"content_sha256":"50a5f675e5e1720f99dad68b0c4f054dd4a86fddbae04f478569d8cc61f2926d","schema_version":"1.0","event_id":"sha256:50a5f675e5e1720f99dad68b0c4f054dd4a86fddbae04f478569d8cc61f2926d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7IM5TL5PZQ6PQLGG6DUEC6JXGC/bundle.json","state_url":"https://pith.science/pith/7IM5TL5PZQ6PQLGG6DUEC6JXGC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7IM5TL5PZQ6PQLGG6DUEC6JXGC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T04:20:11Z","links":{"resolver":"https://pith.science/pith/7IM5TL5PZQ6PQLGG6DUEC6JXGC","bundle":"https://pith.science/pith/7IM5TL5PZQ6PQLGG6DUEC6JXGC/bundle.json","state":"https://pith.science/pith/7IM5TL5PZQ6PQLGG6DUEC6JXGC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7IM5TL5PZQ6PQLGG6DUEC6JXGC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7IM5TL5PZQ6PQLGG6DUEC6JXGC","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":"db1867d8ebf6db75e8282667e87d93977a85cf835dca2d62bd5679ce8fc39b1a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2023-06-05T13:41:10Z","title_canon_sha256":"29d09f067e889dc2b659f6af223aa4bbf82d2a337293f499db78ffa2ecd4ff22"},"schema_version":"1.0","source":{"id":"2306.02867","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02867","created_at":"2026-07-05T06:17:32Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02867v1","created_at":"2026-07-05T06:17:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02867","created_at":"2026-07-05T06:17:32Z"},{"alias_kind":"pith_short_12","alias_value":"7IM5TL5PZQ6P","created_at":"2026-07-05T06:17:32Z"},{"alias_kind":"pith_short_16","alias_value":"7IM5TL5PZQ6PQLGG","created_at":"2026-07-05T06:17:32Z"},{"alias_kind":"pith_short_8","alias_value":"7IM5TL5P","created_at":"2026-07-05T06:17:32Z"}],"graph_snapshots":[{"event_id":"sha256:50a5f675e5e1720f99dad68b0c4f054dd4a86fddbae04f478569d8cc61f2926d","target":"graph","created_at":"2026-07-05T06:17:32Z","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/2306.02867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Middle training methods aim to bridge the gap between the Masked Language Model (MLM) pre-training and the final finetuning for retrieval. Recent models such as CoCondenser, RetroMAE, and LexMAE argue that the MLM task is not sufficient enough to pre-train a transformer network for retrieval and hence propose various tasks to do so. Intrigued by those novel methods, we noticed that all these models used different finetuning protocols, making it hard to assess the benefits of middle training. We propose in this paper a benchmark of CoCondenser, RetroMAE, and LexMAE, under the same finetuning co","authors_text":"Carlos Lassance, Herv\\'e D\\'ejean, Simon Lupart, St\\'ephane Clinchant, Thibault Formal","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2023-06-05T13:41:10Z","title":"Benchmarking Middle-Trained Language Models for Neural Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02867","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":"sha256:7eb58cdfb15deb00c08cffcc7d653d1564f476b1d377bd5f6a315bbc672d5841","target":"record","created_at":"2026-07-05T06:17:32Z","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":"db1867d8ebf6db75e8282667e87d93977a85cf835dca2d62bd5679ce8fc39b1a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2023-06-05T13:41:10Z","title_canon_sha256":"29d09f067e889dc2b659f6af223aa4bbf82d2a337293f499db78ffa2ecd4ff22"},"schema_version":"1.0","source":{"id":"2306.02867","kind":"arxiv","version":1}},"canonical_sha256":"fa19d9afafcc3cf82cc6f0e841793730a914c57fe206b8ab2495d6657f385c90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa19d9afafcc3cf82cc6f0e841793730a914c57fe206b8ab2495d6657f385c90","first_computed_at":"2026-07-05T06:17:32.218080Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:32.218080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zr+uDHM98z9hY4TOyfMEk2YOUWeUmbUsgggUgGAGNOtfcRlrj2FZGYLuqhUGPNw/lFX8ITdaPNRDa4PcoIpwCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:32.218513Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.02867","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7eb58cdfb15deb00c08cffcc7d653d1564f476b1d377bd5f6a315bbc672d5841","sha256:50a5f675e5e1720f99dad68b0c4f054dd4a86fddbae04f478569d8cc61f2926d"],"state_sha256":"a9e534e7ea3c8b2460f0ce4aecc6031af4ee21ea8888ec91f289f756828c9848"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fVgC7U1YOEFYWzOFxCruPK+o5G1Fy4C50nu9X/ou4CquQlbBtfmWwzJBDEkeTGZH20RwCdcOflWX/9FM0IERBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T04:20:11.574059Z","bundle_sha256":"a9c90dd8ac4ea72c8a249988166a87937194a936912229f14cdd01f14d0dc47f"}}