{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:3XPPVFXKJ2572SEOHZUJZQUXMI","short_pith_number":"pith:3XPPVFXK","canonical_record":{"source":{"id":"1705.00441","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-01T08:16:56Z","cross_cats_sorted":[],"title_canon_sha256":"6d8dbb1b0962661b10ab41b32d194505f48ea071e658f12e79d282a8f15da094","abstract_canon_sha256":"e4b5129ab6936e57dda2e36d4497f323c8a7efdcd118582f9d4d107a00e9dbc6"},"schema_version":"1.0"},"canonical_sha256":"dddefa96ea4ebbfd488e3e689cc297620837c246f041c4237533d713812d84a0","source":{"kind":"arxiv","id":"1705.00441","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.00441","created_at":"2026-05-18T00:23:45Z"},{"alias_kind":"arxiv_version","alias_value":"1705.00441v1","created_at":"2026-05-18T00:23:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.00441","created_at":"2026-05-18T00:23:45Z"},{"alias_kind":"pith_short_12","alias_value":"3XPPVFXKJ257","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3XPPVFXKJ2572SEO","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3XPPVFXK","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:3XPPVFXKJ2572SEOHZUJZQUXMI","target":"record","payload":{"canonical_record":{"source":{"id":"1705.00441","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-01T08:16:56Z","cross_cats_sorted":[],"title_canon_sha256":"6d8dbb1b0962661b10ab41b32d194505f48ea071e658f12e79d282a8f15da094","abstract_canon_sha256":"e4b5129ab6936e57dda2e36d4497f323c8a7efdcd118582f9d4d107a00e9dbc6"},"schema_version":"1.0"},"canonical_sha256":"dddefa96ea4ebbfd488e3e689cc297620837c246f041c4237533d713812d84a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:45.690972Z","signature_b64":"JVsShvyLwaUzlm6YCTKmm40OHxoW2Kj3WjhX7b0kfFZ0P0KaWcRoP0hLUNlhP2Wgh9SqDjIt9Sva8V7WT8WqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dddefa96ea4ebbfd488e3e689cc297620837c246f041c4237533d713812d84a0","last_reissued_at":"2026-05-18T00:23:45.690518Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:45.690518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.00441","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":"2026-05-18T00:23:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0myrCL60gkZDvlIcU1PGPqOHX8V0iv8BAlv80462KSSMii6hBX7iPhblTpj2c+sRDy5GXXGCwhCOdMTTbTkmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T22:18:15.168108Z"},"content_sha256":"e3e76698c48c3af216c2f668b57a031ab8863773b4a416552aa7900e4197b1f9","schema_version":"1.0","event_id":"sha256:e3e76698c48c3af216c2f668b57a031ab8863773b4a416552aa7900e4197b1f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:3XPPVFXKJ2572SEOHZUJZQUXMI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Topic-Sensitive Word Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arianna Bisazza, Christof Monz, Marzieh Fadaee","submitted_at":"2017-05-01T08:16:56Z","abstract_excerpt":"Distributed word representations are widely used for modeling words in NLP tasks. Most of the existing models generate one representation per word and do not consider different meanings of a word. We present two approaches to learn multiple topic-sensitive representations per word by using Hierarchical Dirichlet Process. We observe that by modeling topics and integrating topic distributions for each document we obtain representations that are able to distinguish between different meanings of a given word. Our models yield statistically significant improvements for the lexical substitution task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.00441","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":"2026-05-18T00:23:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x0dfrjf9F313rd7fTSXXJ2iX5n+mHDEJMINSks/5+l5KBIZntlvI89JRG9LrXIqJLV6xKps/Ec2YnVMDjhBjCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T22:18:15.168852Z"},"content_sha256":"dd5963afc033081d987f6905ba36eb1d41f7ab6a0d7ee829f5e2068d6e10e6e4","schema_version":"1.0","event_id":"sha256:dd5963afc033081d987f6905ba36eb1d41f7ab6a0d7ee829f5e2068d6e10e6e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3XPPVFXKJ2572SEOHZUJZQUXMI/bundle.json","state_url":"https://pith.science/pith/3XPPVFXKJ2572SEOHZUJZQUXMI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3XPPVFXKJ2572SEOHZUJZQUXMI/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":"2026-06-05T22:18:15Z","links":{"resolver":"https://pith.science/pith/3XPPVFXKJ2572SEOHZUJZQUXMI","bundle":"https://pith.science/pith/3XPPVFXKJ2572SEOHZUJZQUXMI/bundle.json","state":"https://pith.science/pith/3XPPVFXKJ2572SEOHZUJZQUXMI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3XPPVFXKJ2572SEOHZUJZQUXMI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:3XPPVFXKJ2572SEOHZUJZQUXMI","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":"e4b5129ab6936e57dda2e36d4497f323c8a7efdcd118582f9d4d107a00e9dbc6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-01T08:16:56Z","title_canon_sha256":"6d8dbb1b0962661b10ab41b32d194505f48ea071e658f12e79d282a8f15da094"},"schema_version":"1.0","source":{"id":"1705.00441","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.00441","created_at":"2026-05-18T00:23:45Z"},{"alias_kind":"arxiv_version","alias_value":"1705.00441v1","created_at":"2026-05-18T00:23:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.00441","created_at":"2026-05-18T00:23:45Z"},{"alias_kind":"pith_short_12","alias_value":"3XPPVFXKJ257","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3XPPVFXKJ2572SEO","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3XPPVFXK","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:dd5963afc033081d987f6905ba36eb1d41f7ab6a0d7ee829f5e2068d6e10e6e4","target":"graph","created_at":"2026-05-18T00:23:45Z","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":"Distributed word representations are widely used for modeling words in NLP tasks. Most of the existing models generate one representation per word and do not consider different meanings of a word. We present two approaches to learn multiple topic-sensitive representations per word by using Hierarchical Dirichlet Process. We observe that by modeling topics and integrating topic distributions for each document we obtain representations that are able to distinguish between different meanings of a given word. Our models yield statistically significant improvements for the lexical substitution task","authors_text":"Arianna Bisazza, Christof Monz, Marzieh Fadaee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-01T08:16:56Z","title":"Learning Topic-Sensitive Word Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.00441","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:e3e76698c48c3af216c2f668b57a031ab8863773b4a416552aa7900e4197b1f9","target":"record","created_at":"2026-05-18T00:23:45Z","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":"e4b5129ab6936e57dda2e36d4497f323c8a7efdcd118582f9d4d107a00e9dbc6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-01T08:16:56Z","title_canon_sha256":"6d8dbb1b0962661b10ab41b32d194505f48ea071e658f12e79d282a8f15da094"},"schema_version":"1.0","source":{"id":"1705.00441","kind":"arxiv","version":1}},"canonical_sha256":"dddefa96ea4ebbfd488e3e689cc297620837c246f041c4237533d713812d84a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dddefa96ea4ebbfd488e3e689cc297620837c246f041c4237533d713812d84a0","first_computed_at":"2026-05-18T00:23:45.690518Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:23:45.690518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JVsShvyLwaUzlm6YCTKmm40OHxoW2Kj3WjhX7b0kfFZ0P0KaWcRoP0hLUNlhP2Wgh9SqDjIt9Sva8V7WT8WqDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:23:45.690972Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.00441","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3e76698c48c3af216c2f668b57a031ab8863773b4a416552aa7900e4197b1f9","sha256:dd5963afc033081d987f6905ba36eb1d41f7ab6a0d7ee829f5e2068d6e10e6e4"],"state_sha256":"afbaee83376d9a2c4f167becac4dfd11454bc54a702154ad37c79018b9575bb0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qlF3BeMQOm15OKsUt7cTVaBJpOQTJczToTfjzes41ZjOm/z2QZjohYFKafGd2CeWreoBb2T0v5mIgjArJA4xBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T22:18:15.172443Z","bundle_sha256":"62e331dad455eb192f49ad414a33a1eeab8fdcfaf2ac7b0c75b458351b3ae633"}}