{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SISRTRARXFOBG4BL4RN3DSUF7V","short_pith_number":"pith:SISRTRAR","canonical_record":{"source":{"id":"2401.11248","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-01-20T15:02:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"086370da7bcbe27d2ee64473b4da0b6db0dd690e456cf5c7b3fedd11e345c180","abstract_canon_sha256":"3919d7ad82fef5f99c52085c958ab768dfc10c3988576c17da7cd2f1e2db798c"},"schema_version":"1.0"},"canonical_sha256":"922519c411b95c13702be45bb1ca85fd4f7a5174bddadfe34a13c72d20da3fa9","source":{"kind":"arxiv","id":"2401.11248","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.11248","created_at":"2026-07-05T08:10:22Z"},{"alias_kind":"arxiv_version","alias_value":"2401.11248v2","created_at":"2026-07-05T08:10:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11248","created_at":"2026-07-05T08:10:22Z"},{"alias_kind":"pith_short_12","alias_value":"SISRTRARXFOB","created_at":"2026-07-05T08:10:22Z"},{"alias_kind":"pith_short_16","alias_value":"SISRTRARXFOBG4BL","created_at":"2026-07-05T08:10:22Z"},{"alias_kind":"pith_short_8","alias_value":"SISRTRAR","created_at":"2026-07-05T08:10:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SISRTRARXFOBG4BL4RN3DSUF7V","target":"record","payload":{"canonical_record":{"source":{"id":"2401.11248","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-01-20T15:02:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"086370da7bcbe27d2ee64473b4da0b6db0dd690e456cf5c7b3fedd11e345c180","abstract_canon_sha256":"3919d7ad82fef5f99c52085c958ab768dfc10c3988576c17da7cd2f1e2db798c"},"schema_version":"1.0"},"canonical_sha256":"922519c411b95c13702be45bb1ca85fd4f7a5174bddadfe34a13c72d20da3fa9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:22.330039Z","signature_b64":"REaeTRn24klFE1dnRchSLZeBdpa0iITGqV5E7k4ynL+AfXTQmbti53h7rdXprKk09tP095Yb+K+HaFWT9uhOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"922519c411b95c13702be45bb1ca85fd4f7a5174bddadfe34a13c72d20da3fa9","last_reissued_at":"2026-07-05T08:10:22.329566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:22.329566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.11248","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:10:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NRbyVLLm3S+GkBaWptzwcUBvfDDtIrmgY75+VBrxDixFhXsuh5drVoQLEcjXN2gISzRntWM87rvGwpIlpdIBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:53:17.259330Z"},"content_sha256":"a00199f1ab4a0da40ef0647ed9c0f02031c22f168a65f05d02b067dd0b246c9d","schema_version":"1.0","event_id":"sha256:a00199f1ab4a0da40ef0647ed9c0f02031c22f168a65f05d02b067dd0b246c9d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SISRTRARXFOBG4BL4RN3DSUF7V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Guangyuan Ma, Songlin Hu, Xing Wu, Zijia Lin","submitted_at":"2024-01-20T15:02:33Z","abstract_excerpt":"Masked auto-encoder pre-training has emerged as a prevalent technique for initializing and enhancing dense retrieval systems. It generally utilizes additional Transformer decoder blocks to provide sustainable supervision signals and compress contextual information into dense representations. However, the underlying reasons for the effectiveness of such a pre-training technique remain unclear. The usage of additional Transformer-based decoders also incurs significant computational costs. In this study, we aim to shed light on this issue by revealing that masked auto-encoder (MAE) pre-training w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11248","kind":"arxiv","version":2},"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/2401.11248/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":"2026-07-05T08:10:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SUUaYc0exSNID2Z9s9TuBw8KMAPBeNP5XxSIN5UKcUtDIp8ayGGBpgy3xgYTjGZ/FGzmi/3OhR9HCIDRZR2sAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:53:17.259841Z"},"content_sha256":"f3d28c1361a3d39e5255177d7ec635a22f1b202fad1b638743e70bfcf3cbb41c","schema_version":"1.0","event_id":"sha256:f3d28c1361a3d39e5255177d7ec635a22f1b202fad1b638743e70bfcf3cbb41c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SISRTRARXFOBG4BL4RN3DSUF7V/bundle.json","state_url":"https://pith.science/pith/SISRTRARXFOBG4BL4RN3DSUF7V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SISRTRARXFOBG4BL4RN3DSUF7V/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":"2026-08-09T18:53:17Z","links":{"resolver":"https://pith.science/pith/SISRTRARXFOBG4BL4RN3DSUF7V","bundle":"https://pith.science/pith/SISRTRARXFOBG4BL4RN3DSUF7V/bundle.json","state":"https://pith.science/pith/SISRTRARXFOBG4BL4RN3DSUF7V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SISRTRARXFOBG4BL4RN3DSUF7V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SISRTRARXFOBG4BL4RN3DSUF7V","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":"3919d7ad82fef5f99c52085c958ab768dfc10c3988576c17da7cd2f1e2db798c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-01-20T15:02:33Z","title_canon_sha256":"086370da7bcbe27d2ee64473b4da0b6db0dd690e456cf5c7b3fedd11e345c180"},"schema_version":"1.0","source":{"id":"2401.11248","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.11248","created_at":"2026-07-05T08:10:22Z"},{"alias_kind":"arxiv_version","alias_value":"2401.11248v2","created_at":"2026-07-05T08:10:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11248","created_at":"2026-07-05T08:10:22Z"},{"alias_kind":"pith_short_12","alias_value":"SISRTRARXFOB","created_at":"2026-07-05T08:10:22Z"},{"alias_kind":"pith_short_16","alias_value":"SISRTRARXFOBG4BL","created_at":"2026-07-05T08:10:22Z"},{"alias_kind":"pith_short_8","alias_value":"SISRTRAR","created_at":"2026-07-05T08:10:22Z"}],"graph_snapshots":[{"event_id":"sha256:f3d28c1361a3d39e5255177d7ec635a22f1b202fad1b638743e70bfcf3cbb41c","target":"graph","created_at":"2026-07-05T08:10:22Z","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/2401.11248/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Masked auto-encoder pre-training has emerged as a prevalent technique for initializing and enhancing dense retrieval systems. It generally utilizes additional Transformer decoder blocks to provide sustainable supervision signals and compress contextual information into dense representations. However, the underlying reasons for the effectiveness of such a pre-training technique remain unclear. The usage of additional Transformer-based decoders also incurs significant computational costs. In this study, we aim to shed light on this issue by revealing that masked auto-encoder (MAE) pre-training w","authors_text":"Guangyuan Ma, Songlin Hu, Xing Wu, Zijia Lin","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-01-20T15:02:33Z","title":"Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11248","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:a00199f1ab4a0da40ef0647ed9c0f02031c22f168a65f05d02b067dd0b246c9d","target":"record","created_at":"2026-07-05T08:10:22Z","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":"3919d7ad82fef5f99c52085c958ab768dfc10c3988576c17da7cd2f1e2db798c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-01-20T15:02:33Z","title_canon_sha256":"086370da7bcbe27d2ee64473b4da0b6db0dd690e456cf5c7b3fedd11e345c180"},"schema_version":"1.0","source":{"id":"2401.11248","kind":"arxiv","version":2}},"canonical_sha256":"922519c411b95c13702be45bb1ca85fd4f7a5174bddadfe34a13c72d20da3fa9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"922519c411b95c13702be45bb1ca85fd4f7a5174bddadfe34a13c72d20da3fa9","first_computed_at":"2026-07-05T08:10:22.329566Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:10:22.329566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"REaeTRn24klFE1dnRchSLZeBdpa0iITGqV5E7k4ynL+AfXTQmbti53h7rdXprKk09tP095Yb+K+HaFWT9uhOBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:10:22.330039Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.11248","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a00199f1ab4a0da40ef0647ed9c0f02031c22f168a65f05d02b067dd0b246c9d","sha256:f3d28c1361a3d39e5255177d7ec635a22f1b202fad1b638743e70bfcf3cbb41c"],"state_sha256":"863dd608e62a52b7a73aca48492bf6af96601bf5ff907b6de806546b5751b003"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vdmAyDOLBK3E007vhWLeUwvXwKUXULzzpCfPsglV/rbeeXyXTv0eRocJl1hHHL+8dTRYRu1o7Fu05u4aoETRCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:53:17.263158Z","bundle_sha256":"882d7fc1aa4ba311b2fc605a1fc34c812fde312cfe64246a6f59239ad4f0ebe2"}}