{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZLYNCD5KRTPRA67JOLONFR67BM","short_pith_number":"pith:ZLYNCD5K","canonical_record":{"source":{"id":"2410.07722","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-10-10T08:41:34Z","cross_cats_sorted":[],"title_canon_sha256":"37228f01ef4c406cec4b6b684c75f9f03711aaf89ebc45383b1d5139b3c45015","abstract_canon_sha256":"5ee017304c16c4e2a4e88e2034e73ae199771b40860059a8afcfa5fdc4866525"},"schema_version":"1.0"},"canonical_sha256":"caf0d10faa8cdf107be972dcd2c7df0b2142b6eb9959837415565fd5c0484e84","source":{"kind":"arxiv","id":"2410.07722","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07722","created_at":"2026-07-05T09:21:08Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07722v2","created_at":"2026-07-05T09:21:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07722","created_at":"2026-07-05T09:21:08Z"},{"alias_kind":"pith_short_12","alias_value":"ZLYNCD5KRTPR","created_at":"2026-07-05T09:21:08Z"},{"alias_kind":"pith_short_16","alias_value":"ZLYNCD5KRTPRA67J","created_at":"2026-07-05T09:21:08Z"},{"alias_kind":"pith_short_8","alias_value":"ZLYNCD5K","created_at":"2026-07-05T09:21:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZLYNCD5KRTPRA67JOLONFR67BM","target":"record","payload":{"canonical_record":{"source":{"id":"2410.07722","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-10-10T08:41:34Z","cross_cats_sorted":[],"title_canon_sha256":"37228f01ef4c406cec4b6b684c75f9f03711aaf89ebc45383b1d5139b3c45015","abstract_canon_sha256":"5ee017304c16c4e2a4e88e2034e73ae199771b40860059a8afcfa5fdc4866525"},"schema_version":"1.0"},"canonical_sha256":"caf0d10faa8cdf107be972dcd2c7df0b2142b6eb9959837415565fd5c0484e84","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:08.184637Z","signature_b64":"ZYUEpJtKej5hauyr6l3SeyPm3r91JTjo7LYF9Gus5HmgozPPktT7I32OxDoVtsjPvg7pqO+7SiRtCYUl+etqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"caf0d10faa8cdf107be972dcd2c7df0b2142b6eb9959837415565fd5c0484e84","last_reissued_at":"2026-07-05T09:21:08.184226Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:08.184226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.07722","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":"2026-07-05T09:21:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wPRRI8NDMYyqHSq53nNiPHedwykXKWsClJfavVgDIKUeEZMz4S0ds8npqtRdFjRs+Tj9FjkcbDUJhYCGaZlfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T15:56:16.094173Z"},"content_sha256":"60b0036f5c02b82b5e0216c85719255d431394887a9c33f6da731bb8b7a3c438","schema_version":"1.0","event_id":"sha256:60b0036f5c02b82b5e0216c85719255d431394887a9c33f6da731bb8b7a3c438"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZLYNCD5KRTPRA67JOLONFR67BM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DyVo: Dynamic Vocabularies for Learned Sparse Retrieval with Entities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andrew Yates, Iain Mackie, Jeff Dalton, Sean MacAvaney, Shubham Chatterjee, Thong Nguyen","submitted_at":"2024-10-10T08:41:34Z","abstract_excerpt":"Learned Sparse Retrieval (LSR) models use vocabularies from pre-trained transformers, which often split entities into nonsensical fragments. Splitting entities can reduce retrieval accuracy and limits the model's ability to incorporate up-to-date world knowledge not included in the training data. In this work, we enhance the LSR vocabulary with Wikipedia concepts and entities, enabling the model to resolve ambiguities more effectively and stay current with evolving knowledge. Central to our approach is a Dynamic Vocabulary (DyVo) head, which leverages existing entity embeddings and an entity r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07722","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/2410.07722/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":"2026-07-05T09:21:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s+Yt0RtKCCNQATENNc3ree0+sQGiOanJMHTItU6+drL87bBEwBrU5ClL871viE1Qakoh9vNs8G19F611zafADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T15:56:16.094534Z"},"content_sha256":"efc4ca0adf3992f961ec95bc4463d00b1efabda25f44ade624699e9584121089","schema_version":"1.0","event_id":"sha256:efc4ca0adf3992f961ec95bc4463d00b1efabda25f44ade624699e9584121089"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZLYNCD5KRTPRA67JOLONFR67BM/bundle.json","state_url":"https://pith.science/pith/ZLYNCD5KRTPRA67JOLONFR67BM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZLYNCD5KRTPRA67JOLONFR67BM/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":"2026-08-22T15:56:16Z","links":{"resolver":"https://pith.science/pith/ZLYNCD5KRTPRA67JOLONFR67BM","bundle":"https://pith.science/pith/ZLYNCD5KRTPRA67JOLONFR67BM/bundle.json","state":"https://pith.science/pith/ZLYNCD5KRTPRA67JOLONFR67BM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZLYNCD5KRTPRA67JOLONFR67BM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZLYNCD5KRTPRA67JOLONFR67BM","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":"5ee017304c16c4e2a4e88e2034e73ae199771b40860059a8afcfa5fdc4866525","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-10-10T08:41:34Z","title_canon_sha256":"37228f01ef4c406cec4b6b684c75f9f03711aaf89ebc45383b1d5139b3c45015"},"schema_version":"1.0","source":{"id":"2410.07722","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07722","created_at":"2026-07-05T09:21:08Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07722v2","created_at":"2026-07-05T09:21:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07722","created_at":"2026-07-05T09:21:08Z"},{"alias_kind":"pith_short_12","alias_value":"ZLYNCD5KRTPR","created_at":"2026-07-05T09:21:08Z"},{"alias_kind":"pith_short_16","alias_value":"ZLYNCD5KRTPRA67J","created_at":"2026-07-05T09:21:08Z"},{"alias_kind":"pith_short_8","alias_value":"ZLYNCD5K","created_at":"2026-07-05T09:21:08Z"}],"graph_snapshots":[{"event_id":"sha256:efc4ca0adf3992f961ec95bc4463d00b1efabda25f44ade624699e9584121089","target":"graph","created_at":"2026-07-05T09:21:08Z","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/2410.07722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learned Sparse Retrieval (LSR) models use vocabularies from pre-trained transformers, which often split entities into nonsensical fragments. Splitting entities can reduce retrieval accuracy and limits the model's ability to incorporate up-to-date world knowledge not included in the training data. In this work, we enhance the LSR vocabulary with Wikipedia concepts and entities, enabling the model to resolve ambiguities more effectively and stay current with evolving knowledge. Central to our approach is a Dynamic Vocabulary (DyVo) head, which leverages existing entity embeddings and an entity r","authors_text":"Andrew Yates, Iain Mackie, Jeff Dalton, Sean MacAvaney, Shubham Chatterjee, Thong Nguyen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-10-10T08:41:34Z","title":"DyVo: Dynamic Vocabularies for Learned Sparse Retrieval with Entities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07722","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":"sha256:60b0036f5c02b82b5e0216c85719255d431394887a9c33f6da731bb8b7a3c438","target":"record","created_at":"2026-07-05T09:21:08Z","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":"5ee017304c16c4e2a4e88e2034e73ae199771b40860059a8afcfa5fdc4866525","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-10-10T08:41:34Z","title_canon_sha256":"37228f01ef4c406cec4b6b684c75f9f03711aaf89ebc45383b1d5139b3c45015"},"schema_version":"1.0","source":{"id":"2410.07722","kind":"arxiv","version":2}},"canonical_sha256":"caf0d10faa8cdf107be972dcd2c7df0b2142b6eb9959837415565fd5c0484e84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"caf0d10faa8cdf107be972dcd2c7df0b2142b6eb9959837415565fd5c0484e84","first_computed_at":"2026-07-05T09:21:08.184226Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:08.184226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZYUEpJtKej5hauyr6l3SeyPm3r91JTjo7LYF9Gus5HmgozPPktT7I32OxDoVtsjPvg7pqO+7SiRtCYUl+etqBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:08.184637Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.07722","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60b0036f5c02b82b5e0216c85719255d431394887a9c33f6da731bb8b7a3c438","sha256:efc4ca0adf3992f961ec95bc4463d00b1efabda25f44ade624699e9584121089"],"state_sha256":"9411fc69b79ac84398a50920c29615b53716103424a26cc9de12499e1de41dd1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GHmzWVn3LJP1WK6IstPQmUJOyyoeKw8NT2aKcCmBDlWMvMLiRWGcWRfKRDdtf3NTLFkzGAMUPxSL7hk/o7xRCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T15:56:16.097652Z","bundle_sha256":"6823175c23b0e6ad3e16df3386ac76c153df68862f42cf7ba6d661b52f143252"}}