{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:HTTB7VTQJC4ALZS4FCM5QXK5M7","short_pith_number":"pith:HTTB7VTQ","canonical_record":{"source":{"id":"1506.01070","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-02T21:30:21Z","cross_cats_sorted":[],"title_canon_sha256":"111caef91fc195da8bcc6697cfadbb56f64f8008f22815462fd363f45ee3ee0a","abstract_canon_sha256":"98dced653976469c631f8d47f0a0f0bce92fa0bbc3842f08478f378a335995a9"},"schema_version":"1.0"},"canonical_sha256":"3ce61fd67048b805e65c2899d85d5d67d704cee976e7f7e0c97f49cccbaaf244","source":{"kind":"arxiv","id":"1506.01070","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.01070","created_at":"2026-05-18T01:26:10Z"},{"alias_kind":"arxiv_version","alias_value":"1506.01070v3","created_at":"2026-05-18T01:26:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.01070","created_at":"2026-05-18T01:26:10Z"},{"alias_kind":"pith_short_12","alias_value":"HTTB7VTQJC4A","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"HTTB7VTQJC4ALZS4","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"HTTB7VTQ","created_at":"2026-05-18T12:29:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:HTTB7VTQJC4ALZS4FCM5QXK5M7","target":"record","payload":{"canonical_record":{"source":{"id":"1506.01070","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-02T21:30:21Z","cross_cats_sorted":[],"title_canon_sha256":"111caef91fc195da8bcc6697cfadbb56f64f8008f22815462fd363f45ee3ee0a","abstract_canon_sha256":"98dced653976469c631f8d47f0a0f0bce92fa0bbc3842f08478f378a335995a9"},"schema_version":"1.0"},"canonical_sha256":"3ce61fd67048b805e65c2899d85d5d67d704cee976e7f7e0c97f49cccbaaf244","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:26:10.168047Z","signature_b64":"EmCDHyi3cJCal5k/guj/zhFdTT85lCFJt+8Bjh1R9I42nZVO7ckMAsXbnJDFUu001/p/f75JWBkMdgAP+SQyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ce61fd67048b805e65c2899d85d5d67d704cee976e7f7e0c97f49cccbaaf244","last_reissued_at":"2026-05-18T01:26:10.167446Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:26:10.167446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.01070","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:26:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hodmy/fVXfa5uWjYZtmPLoN5RLhqam9HmcOMwK4hU1XrDBxiWFOXW0wUNLiLJy5Qe3lSO23qJMqy/J/3WouZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T01:18:28.050565Z"},"content_sha256":"51b88286bf0dffd94c84fd31791a435260f5f3357d03b1940b3818512589b893","schema_version":"1.0","event_id":"sha256:51b88286bf0dffd94c84fd31791a435260f5f3357d03b1940b3818512589b893"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:HTTB7VTQJC4ALZS4FCM5QXK5M7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do Multi-Sense Embeddings Improve Natural Language Understanding?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Jurafsky, Jiwei Li","submitted_at":"2015-06-02T21:30:21Z","abstract_excerpt":"Learning a distinct representation for each sense of an ambiguous word could lead to more powerful and fine-grained models of vector-space representations. Yet while `multi-sense' methods have been proposed and tested on artificial word-similarity tasks, we don't know if they improve real natural language understanding tasks. In this paper we introduce a multi-sense embedding model based on Chinese Restaurant Processes that achieves state of the art performance on matching human word similarity judgments, and propose a pipelined architecture for incorporating multi-sense embeddings into langua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.01070","kind":"arxiv","version":3},"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":"2026-05-18T01:26:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P2QCHkttOK6pUjeXXglSc7WyuuHYQtE61xGbroFLKb3M9kZEFUSmMRrhuXJJexJGwHMLr/8cOqSCaflORGWlDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T01:18:28.051185Z"},"content_sha256":"5fe117f8bba8c3b7aba2b817eb258eb985edc37a20a1b9fe2b1d161679429415","schema_version":"1.0","event_id":"sha256:5fe117f8bba8c3b7aba2b817eb258eb985edc37a20a1b9fe2b1d161679429415"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HTTB7VTQJC4ALZS4FCM5QXK5M7/bundle.json","state_url":"https://pith.science/pith/HTTB7VTQJC4ALZS4FCM5QXK5M7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HTTB7VTQJC4ALZS4FCM5QXK5M7/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":"2026-06-05T01:18:28Z","links":{"resolver":"https://pith.science/pith/HTTB7VTQJC4ALZS4FCM5QXK5M7","bundle":"https://pith.science/pith/HTTB7VTQJC4ALZS4FCM5QXK5M7/bundle.json","state":"https://pith.science/pith/HTTB7VTQJC4ALZS4FCM5QXK5M7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HTTB7VTQJC4ALZS4FCM5QXK5M7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:HTTB7VTQJC4ALZS4FCM5QXK5M7","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":"98dced653976469c631f8d47f0a0f0bce92fa0bbc3842f08478f378a335995a9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-02T21:30:21Z","title_canon_sha256":"111caef91fc195da8bcc6697cfadbb56f64f8008f22815462fd363f45ee3ee0a"},"schema_version":"1.0","source":{"id":"1506.01070","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.01070","created_at":"2026-05-18T01:26:10Z"},{"alias_kind":"arxiv_version","alias_value":"1506.01070v3","created_at":"2026-05-18T01:26:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.01070","created_at":"2026-05-18T01:26:10Z"},{"alias_kind":"pith_short_12","alias_value":"HTTB7VTQJC4A","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"HTTB7VTQJC4ALZS4","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"HTTB7VTQ","created_at":"2026-05-18T12:29:25Z"}],"graph_snapshots":[{"event_id":"sha256:5fe117f8bba8c3b7aba2b817eb258eb985edc37a20a1b9fe2b1d161679429415","target":"graph","created_at":"2026-05-18T01:26:10Z","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":"Learning a distinct representation for each sense of an ambiguous word could lead to more powerful and fine-grained models of vector-space representations. Yet while `multi-sense' methods have been proposed and tested on artificial word-similarity tasks, we don't know if they improve real natural language understanding tasks. In this paper we introduce a multi-sense embedding model based on Chinese Restaurant Processes that achieves state of the art performance on matching human word similarity judgments, and propose a pipelined architecture for incorporating multi-sense embeddings into langua","authors_text":"Dan Jurafsky, Jiwei Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-02T21:30:21Z","title":"Do Multi-Sense Embeddings Improve Natural Language Understanding?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.01070","kind":"arxiv","version":3},"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":"sha256:51b88286bf0dffd94c84fd31791a435260f5f3357d03b1940b3818512589b893","target":"record","created_at":"2026-05-18T01:26:10Z","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":"98dced653976469c631f8d47f0a0f0bce92fa0bbc3842f08478f378a335995a9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-02T21:30:21Z","title_canon_sha256":"111caef91fc195da8bcc6697cfadbb56f64f8008f22815462fd363f45ee3ee0a"},"schema_version":"1.0","source":{"id":"1506.01070","kind":"arxiv","version":3}},"canonical_sha256":"3ce61fd67048b805e65c2899d85d5d67d704cee976e7f7e0c97f49cccbaaf244","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ce61fd67048b805e65c2899d85d5d67d704cee976e7f7e0c97f49cccbaaf244","first_computed_at":"2026-05-18T01:26:10.167446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:26:10.167446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EmCDHyi3cJCal5k/guj/zhFdTT85lCFJt+8Bjh1R9I42nZVO7ckMAsXbnJDFUu001/p/f75JWBkMdgAP+SQyDw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:26:10.168047Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.01070","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51b88286bf0dffd94c84fd31791a435260f5f3357d03b1940b3818512589b893","sha256:5fe117f8bba8c3b7aba2b817eb258eb985edc37a20a1b9fe2b1d161679429415"],"state_sha256":"76f529ef9373a198bc190287a443c1a91dc366a902a11badff9349647272ff07"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ef6NglyTLPCdzcYyaJ9W6y49jG5+LCggrfXRUmdWXlpcpULVLmfE377Bv4GgvxB7lN3WvIHUmCoDmmpsuLrHDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T01:18:28.055103Z","bundle_sha256":"7877c5e92218721084b280a3e49f50e418d197d1df3d549f68d5f90c04d05c65"}}