{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3BJTNXC7VA3RSH7OX4ZZ5TB5P3","short_pith_number":"pith:3BJTNXC7","canonical_record":{"source":{"id":"2106.06830","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-12T18:27:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"06f56123ef212e8790837fed47aaff3f38f63833f97b9b72dd867e691a26637b","abstract_canon_sha256":"8d8cc76959a56e6c927bc4743e2229d3d8466fcd87d3272b22d6855f723abd4a"},"schema_version":"1.0"},"canonical_sha256":"d85336dc5fa837191feebf339ecc3d7ef3e70a6c7fb37514ce42b4d5b4bdd490","source":{"kind":"arxiv","id":"2106.06830","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.06830","created_at":"2026-07-05T02:48:41Z"},{"alias_kind":"arxiv_version","alias_value":"2106.06830v1","created_at":"2026-07-05T02:48:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06830","created_at":"2026-07-05T02:48:41Z"},{"alias_kind":"pith_short_12","alias_value":"3BJTNXC7VA3R","created_at":"2026-07-05T02:48:41Z"},{"alias_kind":"pith_short_16","alias_value":"3BJTNXC7VA3RSH7O","created_at":"2026-07-05T02:48:41Z"},{"alias_kind":"pith_short_8","alias_value":"3BJTNXC7","created_at":"2026-07-05T02:48:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3BJTNXC7VA3RSH7OX4ZZ5TB5P3","target":"record","payload":{"canonical_record":{"source":{"id":"2106.06830","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-12T18:27:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"06f56123ef212e8790837fed47aaff3f38f63833f97b9b72dd867e691a26637b","abstract_canon_sha256":"8d8cc76959a56e6c927bc4743e2229d3d8466fcd87d3272b22d6855f723abd4a"},"schema_version":"1.0"},"canonical_sha256":"d85336dc5fa837191feebf339ecc3d7ef3e70a6c7fb37514ce42b4d5b4bdd490","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:41.634107Z","signature_b64":"7euW8qyP7M/x6jC7NQtmvbH4VsHZl9fi4g/q0hk/XmdbEXQ58I3RLsNPRygDeYAp1YavQ7Kw4D5fisAnAuF/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d85336dc5fa837191feebf339ecc3d7ef3e70a6c7fb37514ce42b4d5b4bdd490","last_reissued_at":"2026-07-05T02:48:41.633701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:41.633701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.06830","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":"2026-07-05T02:48:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YVUkTmHZ39Pq6t1SR5sFyxoaz1t8o2Ky4zuCw8kCpQ5yoViNOo8VGfB3w9TrQFSRfHytrjaSiwnkCF7N9S6ODQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T10:40:47.055219Z"},"content_sha256":"4f3ba5f23d237cb8cd323871d2314044d149b746f27eabb2c825d164ec2f088e","schema_version":"1.0","event_id":"sha256:4f3ba5f23d237cb8cd323871d2314044d149b746f27eabb2c825d164ec2f088e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3BJTNXC7VA3RSH7OX4ZZ5TB5P3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Entity Disambiguation and the Role of Popularity in Retrieval-Based NLP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anthony Chen, Pallavi Gudipati, Sameer Singh, Shayne Longpre, Xiao Ling","submitted_at":"2021-06-12T18:27:18Z","abstract_excerpt":"Retrieval is a core component for open-domain NLP tasks. In open-domain tasks, multiple entities can share a name, making disambiguation an inherent yet under-explored problem. We propose an evaluation benchmark for assessing the entity disambiguation capabilities of these retrievers, which we call Ambiguous Entity Retrieval (AmbER) sets. We define an AmbER set as a collection of entities that share a name along with queries about those entities. By covering the set of entities for polysemous names, AmbER sets act as a challenging test of entity disambiguation. We create AmbER sets for three p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06830","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/2106.06830/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":"2026-07-05T02:48:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LcPkAFc7MCvNYhcmWiVzXfMxxWez3IbnNYYZND6PdvgNwBrFOQBFcFSCPEgtX5pH4avEAucK0xS9wuqCdhM7AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T10:40:47.055785Z"},"content_sha256":"14f771e4ea6bf38bfc1708c051ecf6d354a4e7e0bfffdfa2a1a4ce48af08fa73","schema_version":"1.0","event_id":"sha256:14f771e4ea6bf38bfc1708c051ecf6d354a4e7e0bfffdfa2a1a4ce48af08fa73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3BJTNXC7VA3RSH7OX4ZZ5TB5P3/bundle.json","state_url":"https://pith.science/pith/3BJTNXC7VA3RSH7OX4ZZ5TB5P3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3BJTNXC7VA3RSH7OX4ZZ5TB5P3/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":"2026-08-20T10:40:47Z","links":{"resolver":"https://pith.science/pith/3BJTNXC7VA3RSH7OX4ZZ5TB5P3","bundle":"https://pith.science/pith/3BJTNXC7VA3RSH7OX4ZZ5TB5P3/bundle.json","state":"https://pith.science/pith/3BJTNXC7VA3RSH7OX4ZZ5TB5P3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3BJTNXC7VA3RSH7OX4ZZ5TB5P3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3BJTNXC7VA3RSH7OX4ZZ5TB5P3","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":"8d8cc76959a56e6c927bc4743e2229d3d8466fcd87d3272b22d6855f723abd4a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-12T18:27:18Z","title_canon_sha256":"06f56123ef212e8790837fed47aaff3f38f63833f97b9b72dd867e691a26637b"},"schema_version":"1.0","source":{"id":"2106.06830","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.06830","created_at":"2026-07-05T02:48:41Z"},{"alias_kind":"arxiv_version","alias_value":"2106.06830v1","created_at":"2026-07-05T02:48:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06830","created_at":"2026-07-05T02:48:41Z"},{"alias_kind":"pith_short_12","alias_value":"3BJTNXC7VA3R","created_at":"2026-07-05T02:48:41Z"},{"alias_kind":"pith_short_16","alias_value":"3BJTNXC7VA3RSH7O","created_at":"2026-07-05T02:48:41Z"},{"alias_kind":"pith_short_8","alias_value":"3BJTNXC7","created_at":"2026-07-05T02:48:41Z"}],"graph_snapshots":[{"event_id":"sha256:14f771e4ea6bf38bfc1708c051ecf6d354a4e7e0bfffdfa2a1a4ce48af08fa73","target":"graph","created_at":"2026-07-05T02:48:41Z","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/2106.06830/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval is a core component for open-domain NLP tasks. In open-domain tasks, multiple entities can share a name, making disambiguation an inherent yet under-explored problem. We propose an evaluation benchmark for assessing the entity disambiguation capabilities of these retrievers, which we call Ambiguous Entity Retrieval (AmbER) sets. We define an AmbER set as a collection of entities that share a name along with queries about those entities. By covering the set of entities for polysemous names, AmbER sets act as a challenging test of entity disambiguation. We create AmbER sets for three p","authors_text":"Anthony Chen, Pallavi Gudipati, Sameer Singh, Shayne Longpre, Xiao Ling","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-12T18:27:18Z","title":"Evaluating Entity Disambiguation and the Role of Popularity in Retrieval-Based NLP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06830","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":"sha256:4f3ba5f23d237cb8cd323871d2314044d149b746f27eabb2c825d164ec2f088e","target":"record","created_at":"2026-07-05T02:48:41Z","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":"8d8cc76959a56e6c927bc4743e2229d3d8466fcd87d3272b22d6855f723abd4a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-12T18:27:18Z","title_canon_sha256":"06f56123ef212e8790837fed47aaff3f38f63833f97b9b72dd867e691a26637b"},"schema_version":"1.0","source":{"id":"2106.06830","kind":"arxiv","version":1}},"canonical_sha256":"d85336dc5fa837191feebf339ecc3d7ef3e70a6c7fb37514ce42b4d5b4bdd490","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d85336dc5fa837191feebf339ecc3d7ef3e70a6c7fb37514ce42b4d5b4bdd490","first_computed_at":"2026-07-05T02:48:41.633701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:41.633701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7euW8qyP7M/x6jC7NQtmvbH4VsHZl9fi4g/q0hk/XmdbEXQ58I3RLsNPRygDeYAp1YavQ7Kw4D5fisAnAuF/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:41.634107Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.06830","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f3ba5f23d237cb8cd323871d2314044d149b746f27eabb2c825d164ec2f088e","sha256:14f771e4ea6bf38bfc1708c051ecf6d354a4e7e0bfffdfa2a1a4ce48af08fa73"],"state_sha256":"b20bac8af3d4f0ca006c0cbb813a1aa0f6d676c2d46c954afe65dc5af1df37d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8YtCbncUZ2Z30t8yW3z/77VzW5PoBPUKZJcQu4xe3ZT51ljE3JFmc7kO8LhKKIy0+KwDoY+FghFGyyhKZpdQCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T10:40:47.059976Z","bundle_sha256":"971b5f942c9481aad1eeaf46f7cf7dce9da7ddbda5b57d0042ed718ec12aa207"}}