{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JWHNTNTIYEFUC57S6R7ZWGR52Z","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":"6f3fc84d44be1968ffe2d8c34ad1f3e65bd39a40a53f4e9177ea7a732773a47e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-12T17:19:05Z","title_canon_sha256":"30c24b7653add93fb2de1922175fed8df64cb93d86c0fc1c1b8d04379f25df5e"},"schema_version":"1.0","source":{"id":"2110.06176","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.06176","created_at":"2026-07-05T04:16:15Z"},{"alias_kind":"arxiv_version","alias_value":"2110.06176v2","created_at":"2026-07-05T04:16:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06176","created_at":"2026-07-05T04:16:15Z"},{"alias_kind":"pith_short_12","alias_value":"JWHNTNTIYEFU","created_at":"2026-07-05T04:16:15Z"},{"alias_kind":"pith_short_16","alias_value":"JWHNTNTIYEFUC57S","created_at":"2026-07-05T04:16:15Z"},{"alias_kind":"pith_short_8","alias_value":"JWHNTNTI","created_at":"2026-07-05T04:16:15Z"}],"graph_snapshots":[{"event_id":"sha256:fcb14d939b83443012084a8f631dfbb5f6e48e6e62f4663cd0b18cedae91f7f7","target":"graph","created_at":"2026-07-05T04:16:15Z","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/2110.06176/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural language understanding tasks such as open-domain question answering often require retrieving and assimilating factual information from multiple sources. We propose to address this problem by integrating a semi-parametric representation of a large text corpus into a Transformer model as a source of factual knowledge. Specifically, our method represents knowledge with `mention memory', a table of dense vector representations of every entity mention in a corpus. The proposed model - TOME - is a Transformer that accesses the information through internal memory layers in which each entity m","authors_text":"Fei Sha, Michiel de Jong, Nicholas FitzGerald, William Cohen, Yury Zemlyanskiy","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-12T17:19:05Z","title":"Mention Memory: incorporating textual knowledge into Transformers through entity mention attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06176","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":"sha256:49a5e627ee40aec608491db551df158010c40ae79b9551775cd9b993d6ae3a78","target":"record","created_at":"2026-07-05T04:16:15Z","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":"6f3fc84d44be1968ffe2d8c34ad1f3e65bd39a40a53f4e9177ea7a732773a47e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-12T17:19:05Z","title_canon_sha256":"30c24b7653add93fb2de1922175fed8df64cb93d86c0fc1c1b8d04379f25df5e"},"schema_version":"1.0","source":{"id":"2110.06176","kind":"arxiv","version":2}},"canonical_sha256":"4d8ed9b668c10b4177f2f47f9b1a3dd64936a763e591f51ef6241a2c8681e432","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d8ed9b668c10b4177f2f47f9b1a3dd64936a763e591f51ef6241a2c8681e432","first_computed_at":"2026-07-05T04:16:15.523775Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:16:15.523775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ojded6ZQvulCf8ncYfSMPkTL25P/mkAwI73kbwbifL/V+ApTcxbgQNYj0ekUu+NvrMxDb4vhYmaFd1RElpn+CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:16:15.524301Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.06176","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49a5e627ee40aec608491db551df158010c40ae79b9551775cd9b993d6ae3a78","sha256:fcb14d939b83443012084a8f631dfbb5f6e48e6e62f4663cd0b18cedae91f7f7"],"state_sha256":"62f5be8316c5a1a595add9ab695b8f8a818e8a0996d91443188bf86e78a86a17"}