{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:TX3DXCX4SV5AROCCJ6EBTTUU33","short_pith_number":"pith:TX3DXCX4","canonical_record":{"source":{"id":"1604.00734","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-04T03:58:31Z","cross_cats_sorted":[],"title_canon_sha256":"0d0ddd94ee21add4bb618906c63ecc804783719df3f21ef551b806173dd2c0f0","abstract_canon_sha256":"dc74323707edd1025178b6089c174da8c3184062b2965a669b499d6d687bf7cd"},"schema_version":"1.0"},"canonical_sha256":"9df63b8afc957a08b8424f8819ce94defa3bf1f3eb1b8f859891cab1824060fb","source":{"kind":"arxiv","id":"1604.00734","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.00734","created_at":"2026-05-18T01:17:48Z"},{"alias_kind":"arxiv_version","alias_value":"1604.00734v1","created_at":"2026-05-18T01:17:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.00734","created_at":"2026-05-18T01:17:48Z"},{"alias_kind":"pith_short_12","alias_value":"TX3DXCX4SV5A","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"TX3DXCX4SV5AROCC","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"TX3DXCX4","created_at":"2026-05-18T12:30:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:TX3DXCX4SV5AROCCJ6EBTTUU33","target":"record","payload":{"canonical_record":{"source":{"id":"1604.00734","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-04T03:58:31Z","cross_cats_sorted":[],"title_canon_sha256":"0d0ddd94ee21add4bb618906c63ecc804783719df3f21ef551b806173dd2c0f0","abstract_canon_sha256":"dc74323707edd1025178b6089c174da8c3184062b2965a669b499d6d687bf7cd"},"schema_version":"1.0"},"canonical_sha256":"9df63b8afc957a08b8424f8819ce94defa3bf1f3eb1b8f859891cab1824060fb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:48.462935Z","signature_b64":"zvUXdMfM6NprelJes+7gLHag93dQdr7QtlhEwkr6Px/lGYwdTA6A9yLX34hh9P937VUmWslJcnSPKz145Ce+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9df63b8afc957a08b8424f8819ce94defa3bf1f3eb1b8f859891cab1824060fb","last_reissued_at":"2026-05-18T01:17:48.462184Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:48.462184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1604.00734","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":"2026-05-18T01:17:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xr3FyjK//QzaHHVX1kJjzOMRB+LoXXfzPFfDPp/Kcng6IaaI9G6qcCIq+oKq//GJ9cu1/sla5NnpAJ7vGiVADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:14:10.225921Z"},"content_sha256":"d557a8125549e0247b7575e5dc3e42be509dad8d6036bf6dc7c16d288b7a4b82","schema_version":"1.0","event_id":"sha256:d557a8125549e0247b7575e5dc3e42be509dad8d6036bf6dc7c16d288b7a4b82"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:TX3DXCX4SV5AROCCJ6EBTTUU33","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Klein, Greg Durrett, Matthew Francis-Landau","submitted_at":"2016-04-04T03:58:31Z","abstract_excerpt":"A key challenge in entity linking is making effective use of contextual information to disambiguate mentions that might refer to different entities in different contexts. We present a model that uses convolutional neural networks to capture semantic correspondence between a mention's context and a proposed target entity. These convolutional networks operate at multiple granularities to exploit various kinds of topic information, and their rich parameterization gives them the capacity to learn which n-grams characterize different topics. We combine these networks with a sparse linear model to a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.00734","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":""},"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":"2026-05-18T01:17:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3PDQ6RCbazqwP3KC0JEzvozPjSFAKmQY2FLsT6o7BI2HAmLCwWrNjOMzTC2vANvirErly52Txk9i0/UMRtrtBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:14:10.226653Z"},"content_sha256":"8f4e863077ab487c5382f4ae109a097cd562dc318d3ea3446824541017a1356e","schema_version":"1.0","event_id":"sha256:8f4e863077ab487c5382f4ae109a097cd562dc318d3ea3446824541017a1356e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TX3DXCX4SV5AROCCJ6EBTTUU33/bundle.json","state_url":"https://pith.science/pith/TX3DXCX4SV5AROCCJ6EBTTUU33/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TX3DXCX4SV5AROCCJ6EBTTUU33/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":"2026-05-25T17:14:10Z","links":{"resolver":"https://pith.science/pith/TX3DXCX4SV5AROCCJ6EBTTUU33","bundle":"https://pith.science/pith/TX3DXCX4SV5AROCCJ6EBTTUU33/bundle.json","state":"https://pith.science/pith/TX3DXCX4SV5AROCCJ6EBTTUU33/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TX3DXCX4SV5AROCCJ6EBTTUU33/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:TX3DXCX4SV5AROCCJ6EBTTUU33","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":"dc74323707edd1025178b6089c174da8c3184062b2965a669b499d6d687bf7cd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-04T03:58:31Z","title_canon_sha256":"0d0ddd94ee21add4bb618906c63ecc804783719df3f21ef551b806173dd2c0f0"},"schema_version":"1.0","source":{"id":"1604.00734","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.00734","created_at":"2026-05-18T01:17:48Z"},{"alias_kind":"arxiv_version","alias_value":"1604.00734v1","created_at":"2026-05-18T01:17:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.00734","created_at":"2026-05-18T01:17:48Z"},{"alias_kind":"pith_short_12","alias_value":"TX3DXCX4SV5A","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"TX3DXCX4SV5AROCC","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"TX3DXCX4","created_at":"2026-05-18T12:30:46Z"}],"graph_snapshots":[{"event_id":"sha256:8f4e863077ab487c5382f4ae109a097cd562dc318d3ea3446824541017a1356e","target":"graph","created_at":"2026-05-18T01:17:48Z","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"},"paper":{"abstract_excerpt":"A key challenge in entity linking is making effective use of contextual information to disambiguate mentions that might refer to different entities in different contexts. We present a model that uses convolutional neural networks to capture semantic correspondence between a mention's context and a proposed target entity. These convolutional networks operate at multiple granularities to exploit various kinds of topic information, and their rich parameterization gives them the capacity to learn which n-grams characterize different topics. We combine these networks with a sparse linear model to a","authors_text":"Dan Klein, Greg Durrett, Matthew Francis-Landau","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-04T03:58:31Z","title":"Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.00734","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:d557a8125549e0247b7575e5dc3e42be509dad8d6036bf6dc7c16d288b7a4b82","target":"record","created_at":"2026-05-18T01:17:48Z","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":"dc74323707edd1025178b6089c174da8c3184062b2965a669b499d6d687bf7cd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-04T03:58:31Z","title_canon_sha256":"0d0ddd94ee21add4bb618906c63ecc804783719df3f21ef551b806173dd2c0f0"},"schema_version":"1.0","source":{"id":"1604.00734","kind":"arxiv","version":1}},"canonical_sha256":"9df63b8afc957a08b8424f8819ce94defa3bf1f3eb1b8f859891cab1824060fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9df63b8afc957a08b8424f8819ce94defa3bf1f3eb1b8f859891cab1824060fb","first_computed_at":"2026-05-18T01:17:48.462184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:17:48.462184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zvUXdMfM6NprelJes+7gLHag93dQdr7QtlhEwkr6Px/lGYwdTA6A9yLX34hh9P937VUmWslJcnSPKz145Ce+Bg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:17:48.462935Z","signed_message":"canonical_sha256_bytes"},"source_id":"1604.00734","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d557a8125549e0247b7575e5dc3e42be509dad8d6036bf6dc7c16d288b7a4b82","sha256:8f4e863077ab487c5382f4ae109a097cd562dc318d3ea3446824541017a1356e"],"state_sha256":"520ea4ffd11de7ac85f755a70fe54f95355274247d38e88842be695ca3765d95"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y9GtDtn2b/G61amOf2BmcnLcPlhH/UwuQaX3NJqwMAJK7PORQQKks1TjbUYAMpvE/AQeU6cuZ2R5DBJJWtHEBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T17:14:10.230691Z","bundle_sha256":"dc34b4fd3b1f084a5287fac60bf925ea7e743a03c397c61cebba729d4d2a4490"}}