{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:22XYNIO66U7NYBV6RFLIXRFHXV","short_pith_number":"pith:22XYNIO6","canonical_record":{"source":{"id":"2401.04055","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-01-08T17:53:06Z","cross_cats_sorted":[],"title_canon_sha256":"cc57b8132677bcac54ef72b5ffbe8119e13da889cfb1364dfc07b74ea83a6ef4","abstract_canon_sha256":"391251c80d8c434e0ddb39d0a1f0be5867f98148f07bee97e1f08fd8f4885bc5"},"schema_version":"1.0"},"canonical_sha256":"d6af86a1def53edc06be89568bc4a7bd4bc02b7842b5ab198e825934c87cdbc4","source":{"kind":"arxiv","id":"2401.04055","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.04055","created_at":"2026-07-05T07:31:23Z"},{"alias_kind":"arxiv_version","alias_value":"2401.04055v1","created_at":"2026-07-05T07:31:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04055","created_at":"2026-07-05T07:31:23Z"},{"alias_kind":"pith_short_12","alias_value":"22XYNIO66U7N","created_at":"2026-07-05T07:31:23Z"},{"alias_kind":"pith_short_16","alias_value":"22XYNIO66U7NYBV6","created_at":"2026-07-05T07:31:23Z"},{"alias_kind":"pith_short_8","alias_value":"22XYNIO6","created_at":"2026-07-05T07:31:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:22XYNIO66U7NYBV6RFLIXRFHXV","target":"record","payload":{"canonical_record":{"source":{"id":"2401.04055","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-01-08T17:53:06Z","cross_cats_sorted":[],"title_canon_sha256":"cc57b8132677bcac54ef72b5ffbe8119e13da889cfb1364dfc07b74ea83a6ef4","abstract_canon_sha256":"391251c80d8c434e0ddb39d0a1f0be5867f98148f07bee97e1f08fd8f4885bc5"},"schema_version":"1.0"},"canonical_sha256":"d6af86a1def53edc06be89568bc4a7bd4bc02b7842b5ab198e825934c87cdbc4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:23.357253Z","signature_b64":"4ErORBE3kBicff0WfKfG57RyrBP0jy6SThf+fNfQzyay3xveTKUeJrODZVLn7+lmqe/HD109pSdQ1ecrSApuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6af86a1def53edc06be89568bc4a7bd4bc02b7842b5ab198e825934c87cdbc4","last_reissued_at":"2026-07-05T07:31:23.356719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:23.356719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.04055","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":"2026-07-05T07:31:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w8D4cKxbdaIxJ5nd5px+7f1mTKZSk6NL3q0kHvAq8211RjXL0gxOMOGHHjDKpPh4q2hqbq+dF2rWBzvI+BEVCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:02:50.551684Z"},"content_sha256":"d9812375f1a24faeb73636816cb22aa9317bbf59a628f9c99eb3b2c9ec954beb","schema_version":"1.0","event_id":"sha256:d9812375f1a24faeb73636816cb22aa9317bbf59a628f9c99eb3b2c9ec954beb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:22XYNIO66U7NYBV6RFLIXRFHXV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sparse Meets Dense: A Hybrid Approach to Enhance Scientific Document Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Priyanka Mandikal, Raymond Mooney","submitted_at":"2024-01-08T17:53:06Z","abstract_excerpt":"Traditional information retrieval is based on sparse bag-of-words vector representations of documents and queries. More recent deep-learning approaches have used dense embeddings learned using a transformer-based large language model. We show that on a classic benchmark on scientific document retrieval in the medical domain of cystic fibrosis, that both of these models perform roughly equivalently. Notably, dense vectors from the state-of-the-art SPECTER2 model do not significantly enhance performance. However, a hybrid model that we propose combining these methods yields significantly better "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04055","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/2401.04055/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":"2026-07-05T07:31:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gOZSvLOfr/Tc+8H+d733ydfMB+BNlCU2jhNWzhR06exDXqXDIpIbjX6N3wHZYXyaQqHmPkVZqyrQw7EgValGDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:02:50.552188Z"},"content_sha256":"60d968d8d92a738583f8945534da0209efcd3e417f5241d352954378f0a33514","schema_version":"1.0","event_id":"sha256:60d968d8d92a738583f8945534da0209efcd3e417f5241d352954378f0a33514"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/22XYNIO66U7NYBV6RFLIXRFHXV/bundle.json","state_url":"https://pith.science/pith/22XYNIO66U7NYBV6RFLIXRFHXV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/22XYNIO66U7NYBV6RFLIXRFHXV/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":"2026-08-07T01:02:50Z","links":{"resolver":"https://pith.science/pith/22XYNIO66U7NYBV6RFLIXRFHXV","bundle":"https://pith.science/pith/22XYNIO66U7NYBV6RFLIXRFHXV/bundle.json","state":"https://pith.science/pith/22XYNIO66U7NYBV6RFLIXRFHXV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/22XYNIO66U7NYBV6RFLIXRFHXV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:22XYNIO66U7NYBV6RFLIXRFHXV","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":"391251c80d8c434e0ddb39d0a1f0be5867f98148f07bee97e1f08fd8f4885bc5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-01-08T17:53:06Z","title_canon_sha256":"cc57b8132677bcac54ef72b5ffbe8119e13da889cfb1364dfc07b74ea83a6ef4"},"schema_version":"1.0","source":{"id":"2401.04055","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.04055","created_at":"2026-07-05T07:31:23Z"},{"alias_kind":"arxiv_version","alias_value":"2401.04055v1","created_at":"2026-07-05T07:31:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04055","created_at":"2026-07-05T07:31:23Z"},{"alias_kind":"pith_short_12","alias_value":"22XYNIO66U7N","created_at":"2026-07-05T07:31:23Z"},{"alias_kind":"pith_short_16","alias_value":"22XYNIO66U7NYBV6","created_at":"2026-07-05T07:31:23Z"},{"alias_kind":"pith_short_8","alias_value":"22XYNIO6","created_at":"2026-07-05T07:31:23Z"}],"graph_snapshots":[{"event_id":"sha256:60d968d8d92a738583f8945534da0209efcd3e417f5241d352954378f0a33514","target":"graph","created_at":"2026-07-05T07:31:23Z","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/2401.04055/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional information retrieval is based on sparse bag-of-words vector representations of documents and queries. More recent deep-learning approaches have used dense embeddings learned using a transformer-based large language model. We show that on a classic benchmark on scientific document retrieval in the medical domain of cystic fibrosis, that both of these models perform roughly equivalently. Notably, dense vectors from the state-of-the-art SPECTER2 model do not significantly enhance performance. However, a hybrid model that we propose combining these methods yields significantly better ","authors_text":"Priyanka Mandikal, Raymond Mooney","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-01-08T17:53:06Z","title":"Sparse Meets Dense: A Hybrid Approach to Enhance Scientific Document Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04055","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:d9812375f1a24faeb73636816cb22aa9317bbf59a628f9c99eb3b2c9ec954beb","target":"record","created_at":"2026-07-05T07:31:23Z","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":"391251c80d8c434e0ddb39d0a1f0be5867f98148f07bee97e1f08fd8f4885bc5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-01-08T17:53:06Z","title_canon_sha256":"cc57b8132677bcac54ef72b5ffbe8119e13da889cfb1364dfc07b74ea83a6ef4"},"schema_version":"1.0","source":{"id":"2401.04055","kind":"arxiv","version":1}},"canonical_sha256":"d6af86a1def53edc06be89568bc4a7bd4bc02b7842b5ab198e825934c87cdbc4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6af86a1def53edc06be89568bc4a7bd4bc02b7842b5ab198e825934c87cdbc4","first_computed_at":"2026-07-05T07:31:23.356719Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:31:23.356719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4ErORBE3kBicff0WfKfG57RyrBP0jy6SThf+fNfQzyay3xveTKUeJrODZVLn7+lmqe/HD109pSdQ1ecrSApuCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:31:23.357253Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.04055","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9812375f1a24faeb73636816cb22aa9317bbf59a628f9c99eb3b2c9ec954beb","sha256:60d968d8d92a738583f8945534da0209efcd3e417f5241d352954378f0a33514"],"state_sha256":"0fcea2b55215786222e2e8251314923d181a663c6fb41b586403f0077f38beb4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qv+f9JDJyN3gEuPBcdk8HbLGpCiileWeaPXrzkj95ZxFo3WgxI04vpu5Y316naMr5OPVFLtqdUJ5M/depvAMBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:02:50.556030Z","bundle_sha256":"818f2f8e1e035583abdff9f0a00c88ce9cbe64104917be891c90adceac878e6f"}}