{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:KXVMMX6JFPXPWZC5QEACPKN6JT","short_pith_number":"pith:KXVMMX6J","canonical_record":{"source":{"id":"1705.08488","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-23T19:12:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2f09bb730b5cc8f1628c227557dab5b87755eb525e3cc3aae58c9b6fe985f212","abstract_canon_sha256":"19c31477deca1ee16e6dd30d95803a605f000bb99655088f096b9f5fe0c273ab"},"schema_version":"1.0"},"canonical_sha256":"55eac65fc92beefb645d810027a9be4cfcdeb1c13d48e2fcff5cd8f3ca51ef0b","source":{"kind":"arxiv","id":"1705.08488","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08488","created_at":"2026-05-18T00:43:45Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08488v1","created_at":"2026-05-18T00:43:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08488","created_at":"2026-05-18T00:43:45Z"},{"alias_kind":"pith_short_12","alias_value":"KXVMMX6JFPXP","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"KXVMMX6JFPXPWZC5","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"KXVMMX6J","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:KXVMMX6JFPXPWZC5QEACPKN6JT","target":"record","payload":{"canonical_record":{"source":{"id":"1705.08488","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-23T19:12:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2f09bb730b5cc8f1628c227557dab5b87755eb525e3cc3aae58c9b6fe985f212","abstract_canon_sha256":"19c31477deca1ee16e6dd30d95803a605f000bb99655088f096b9f5fe0c273ab"},"schema_version":"1.0"},"canonical_sha256":"55eac65fc92beefb645d810027a9be4cfcdeb1c13d48e2fcff5cd8f3ca51ef0b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:45.978512Z","signature_b64":"X+l1e64exsyVCtYmn58zUomsX9rhTV+nM7iTgaDergCkrouJym7orDRwfAtHmtgilEXf2RwkwPSwYZGY//1nCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55eac65fc92beefb645d810027a9be4cfcdeb1c13d48e2fcff5cd8f3ca51ef0b","last_reissued_at":"2026-05-18T00:43:45.977891Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:45.977891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.08488","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":"2026-05-18T00:43:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pqTsjfNUCfz8cY03i7TM/x3Qw5f58hxYu32oP365XbMtzZyDSn+3QosckoI4elnAeGWLrAoySW94AKlS3Ab/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:00:28.331573Z"},"content_sha256":"052e4daacaa9c2b0907b6e9f1a0419bf0694c3d8286611b6fa382f703485a57f","schema_version":"1.0","event_id":"sha256:052e4daacaa9c2b0907b6e9f1a0419bf0694c3d8286611b6fa382f703485a57f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:KXVMMX6JFPXPWZC5QEACPKN6JT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Second-Order Word Embeddings from Nearest Neighbor Topological Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Denis Newman-Griffis, Eric Fosler-Lussier","submitted_at":"2017-05-23T19:12:05Z","abstract_excerpt":"We introduce second-order vector representations of words, induced from nearest neighborhood topological features in pre-trained contextual word embeddings. We then analyze the effects of using second-order embeddings as input features in two deep natural language processing models, for named entity recognition and recognizing textual entailment, as well as a linear model for paraphrase recognition. Surprisingly, we find that nearest neighbor information alone is sufficient to capture most of the performance benefits derived from using pre-trained word embeddings. Furthermore, second-order emb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08488","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":"2026-05-18T00:43:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TneJEZPe0QKq8dkBq2+jKh+zDXRdP2z455H+pnGq2KZ4QDq+JHkXfkS7EHNB8tt0JWxdNPk+iL9pEEBEGPfqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:00:28.332177Z"},"content_sha256":"6895f6379cd9775e47c517030329ef8adf27bc0b4d5637c4fff73769d98c1e0c","schema_version":"1.0","event_id":"sha256:6895f6379cd9775e47c517030329ef8adf27bc0b4d5637c4fff73769d98c1e0c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KXVMMX6JFPXPWZC5QEACPKN6JT/bundle.json","state_url":"https://pith.science/pith/KXVMMX6JFPXPWZC5QEACPKN6JT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KXVMMX6JFPXPWZC5QEACPKN6JT/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":"2026-05-27T13:00:28Z","links":{"resolver":"https://pith.science/pith/KXVMMX6JFPXPWZC5QEACPKN6JT","bundle":"https://pith.science/pith/KXVMMX6JFPXPWZC5QEACPKN6JT/bundle.json","state":"https://pith.science/pith/KXVMMX6JFPXPWZC5QEACPKN6JT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KXVMMX6JFPXPWZC5QEACPKN6JT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:KXVMMX6JFPXPWZC5QEACPKN6JT","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":"19c31477deca1ee16e6dd30d95803a605f000bb99655088f096b9f5fe0c273ab","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-23T19:12:05Z","title_canon_sha256":"2f09bb730b5cc8f1628c227557dab5b87755eb525e3cc3aae58c9b6fe985f212"},"schema_version":"1.0","source":{"id":"1705.08488","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08488","created_at":"2026-05-18T00:43:45Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08488v1","created_at":"2026-05-18T00:43:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08488","created_at":"2026-05-18T00:43:45Z"},{"alias_kind":"pith_short_12","alias_value":"KXVMMX6JFPXP","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"KXVMMX6JFPXPWZC5","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"KXVMMX6J","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:6895f6379cd9775e47c517030329ef8adf27bc0b4d5637c4fff73769d98c1e0c","target":"graph","created_at":"2026-05-18T00:43:45Z","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":"We introduce second-order vector representations of words, induced from nearest neighborhood topological features in pre-trained contextual word embeddings. We then analyze the effects of using second-order embeddings as input features in two deep natural language processing models, for named entity recognition and recognizing textual entailment, as well as a linear model for paraphrase recognition. Surprisingly, we find that nearest neighbor information alone is sufficient to capture most of the performance benefits derived from using pre-trained word embeddings. Furthermore, second-order emb","authors_text":"Denis Newman-Griffis, Eric Fosler-Lussier","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-23T19:12:05Z","title":"Second-Order Word Embeddings from Nearest Neighbor Topological Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08488","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":"sha256:052e4daacaa9c2b0907b6e9f1a0419bf0694c3d8286611b6fa382f703485a57f","target":"record","created_at":"2026-05-18T00:43:45Z","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":"19c31477deca1ee16e6dd30d95803a605f000bb99655088f096b9f5fe0c273ab","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-23T19:12:05Z","title_canon_sha256":"2f09bb730b5cc8f1628c227557dab5b87755eb525e3cc3aae58c9b6fe985f212"},"schema_version":"1.0","source":{"id":"1705.08488","kind":"arxiv","version":1}},"canonical_sha256":"55eac65fc92beefb645d810027a9be4cfcdeb1c13d48e2fcff5cd8f3ca51ef0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55eac65fc92beefb645d810027a9be4cfcdeb1c13d48e2fcff5cd8f3ca51ef0b","first_computed_at":"2026-05-18T00:43:45.977891Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:45.977891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X+l1e64exsyVCtYmn58zUomsX9rhTV+nM7iTgaDergCkrouJym7orDRwfAtHmtgilEXf2RwkwPSwYZGY//1nCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:45.978512Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.08488","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:052e4daacaa9c2b0907b6e9f1a0419bf0694c3d8286611b6fa382f703485a57f","sha256:6895f6379cd9775e47c517030329ef8adf27bc0b4d5637c4fff73769d98c1e0c"],"state_sha256":"b7ad46028b73e97d50759975f454ea76b2cf0f2c9fbe92321548b82c53122dc7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P6RiBTZJ76mzn1T7QIVIXseUUk1hhq8p0roGC+EFicq8MhaPsZZslKcAEdJlIlTKtXSjKb4Cb6UMoMrckJMsDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T13:00:28.335387Z","bundle_sha256":"44f705dde81f26cbb54b7b80861a60d1d6b5f570d271811854b54b07dc67dee0"}}