{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:LXY3YQJGS3MN5SEC52Q7YFHV3E","short_pith_number":"pith:LXY3YQJG","canonical_record":{"source":{"id":"1506.04488","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-15T06:30:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"903478352178a7e52a7bbf781ff12130f5c524b1e46a198255e30d57f63c852f","abstract_canon_sha256":"69aa38f4c6f176c15794770c104addc16a855a5b986354f92ac29909e99eb86d"},"schema_version":"1.0"},"canonical_sha256":"5df1bc412696d8dec882eea1fc14f5d921cc70667627173d311cc3fd42c07511","source":{"kind":"arxiv","id":"1506.04488","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.04488","created_at":"2026-05-18T01:10:38Z"},{"alias_kind":"arxiv_version","alias_value":"1506.04488v2","created_at":"2026-05-18T01:10:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.04488","created_at":"2026-05-18T01:10:38Z"},{"alias_kind":"pith_short_12","alias_value":"LXY3YQJGS3MN","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_16","alias_value":"LXY3YQJGS3MN5SEC","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_8","alias_value":"LXY3YQJG","created_at":"2026-05-18T12:29:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:LXY3YQJGS3MN5SEC52Q7YFHV3E","target":"record","payload":{"canonical_record":{"source":{"id":"1506.04488","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-15T06:30:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"903478352178a7e52a7bbf781ff12130f5c524b1e46a198255e30d57f63c852f","abstract_canon_sha256":"69aa38f4c6f176c15794770c104addc16a855a5b986354f92ac29909e99eb86d"},"schema_version":"1.0"},"canonical_sha256":"5df1bc412696d8dec882eea1fc14f5d921cc70667627173d311cc3fd42c07511","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:10:38.567311Z","signature_b64":"cP+4GW7H6KHhW2jAkmpj/pTX/pxxOVMTqi1z0PoDq6oYHnua3bz/75ELFbFt3XnF5chW2Xj78TDKmdneMbl7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5df1bc412696d8dec882eea1fc14f5d921cc70667627173d311cc3fd42c07511","last_reissued_at":"2026-05-18T01:10:38.566718Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:10:38.566718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.04488","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:10:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c6Xsp31GksZBbd41N91u39Jtb9ds+l6FACkan6uzyOkRxZFilzyke1FrPh8WbWcZ2msxbb79FRoBjjw1jufLBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T07:25:39.888132Z"},"content_sha256":"5215a1a5a917e3c7715b31cc2fdbf75a3518c1c51bab5bd10db8cb3dbc586eff","schema_version":"1.0","event_id":"sha256:5215a1a5a917e3c7715b31cc2fdbf75a3518c1c51bab5bd10db8cb3dbc586eff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:LXY3YQJGS3MN5SEC52Q7YFHV3E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distilling Word Embeddings: An Encoding Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ge Li, Lili Mou, Lu Zhang, Ran Jia, Yan Xu, Zhi Jin","submitted_at":"2015-06-15T06:30:36Z","abstract_excerpt":"Distilling knowledge from a well-trained cumbersome network to a small one has recently become a new research topic, as lightweight neural networks with high performance are particularly in need in various resource-restricted systems. This paper addresses the problem of distilling word embeddings for NLP tasks. We propose an encoding approach to distill task-specific knowledge from a set of high-dimensional embeddings, which can reduce model complexity by a large margin as well as retain high accuracy, showing a good compromise between efficiency and performance. Experiments in two tasks revea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.04488","kind":"arxiv","version":2},"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":"2026-05-18T01:10:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qqqLk7fm3ZLIlAEW4sfbRvza3TGCUda8gYc1deSnAE/Du1VGBsC+eV+lc0j6j0v30p5r2NhY92t3WNsNJyatDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T07:25:39.888495Z"},"content_sha256":"9be087fccd5166b1799c75c9d861517c07c59c230c1ab52f6713b4dac63317fc","schema_version":"1.0","event_id":"sha256:9be087fccd5166b1799c75c9d861517c07c59c230c1ab52f6713b4dac63317fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LXY3YQJGS3MN5SEC52Q7YFHV3E/bundle.json","state_url":"https://pith.science/pith/LXY3YQJGS3MN5SEC52Q7YFHV3E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LXY3YQJGS3MN5SEC52Q7YFHV3E/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":"2026-07-02T07:25:39Z","links":{"resolver":"https://pith.science/pith/LXY3YQJGS3MN5SEC52Q7YFHV3E","bundle":"https://pith.science/pith/LXY3YQJGS3MN5SEC52Q7YFHV3E/bundle.json","state":"https://pith.science/pith/LXY3YQJGS3MN5SEC52Q7YFHV3E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LXY3YQJGS3MN5SEC52Q7YFHV3E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:LXY3YQJGS3MN5SEC52Q7YFHV3E","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":"69aa38f4c6f176c15794770c104addc16a855a5b986354f92ac29909e99eb86d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-15T06:30:36Z","title_canon_sha256":"903478352178a7e52a7bbf781ff12130f5c524b1e46a198255e30d57f63c852f"},"schema_version":"1.0","source":{"id":"1506.04488","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.04488","created_at":"2026-05-18T01:10:38Z"},{"alias_kind":"arxiv_version","alias_value":"1506.04488v2","created_at":"2026-05-18T01:10:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.04488","created_at":"2026-05-18T01:10:38Z"},{"alias_kind":"pith_short_12","alias_value":"LXY3YQJGS3MN","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_16","alias_value":"LXY3YQJGS3MN5SEC","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_8","alias_value":"LXY3YQJG","created_at":"2026-05-18T12:29:29Z"}],"graph_snapshots":[{"event_id":"sha256:9be087fccd5166b1799c75c9d861517c07c59c230c1ab52f6713b4dac63317fc","target":"graph","created_at":"2026-05-18T01:10:38Z","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":"Distilling knowledge from a well-trained cumbersome network to a small one has recently become a new research topic, as lightweight neural networks with high performance are particularly in need in various resource-restricted systems. This paper addresses the problem of distilling word embeddings for NLP tasks. We propose an encoding approach to distill task-specific knowledge from a set of high-dimensional embeddings, which can reduce model complexity by a large margin as well as retain high accuracy, showing a good compromise between efficiency and performance. Experiments in two tasks revea","authors_text":"Ge Li, Lili Mou, Lu Zhang, Ran Jia, Yan Xu, Zhi Jin","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-15T06:30:36Z","title":"Distilling Word Embeddings: An Encoding Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.04488","kind":"arxiv","version":2},"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":"sha256:5215a1a5a917e3c7715b31cc2fdbf75a3518c1c51bab5bd10db8cb3dbc586eff","target":"record","created_at":"2026-05-18T01:10:38Z","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":"69aa38f4c6f176c15794770c104addc16a855a5b986354f92ac29909e99eb86d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-15T06:30:36Z","title_canon_sha256":"903478352178a7e52a7bbf781ff12130f5c524b1e46a198255e30d57f63c852f"},"schema_version":"1.0","source":{"id":"1506.04488","kind":"arxiv","version":2}},"canonical_sha256":"5df1bc412696d8dec882eea1fc14f5d921cc70667627173d311cc3fd42c07511","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5df1bc412696d8dec882eea1fc14f5d921cc70667627173d311cc3fd42c07511","first_computed_at":"2026-05-18T01:10:38.566718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:10:38.566718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cP+4GW7H6KHhW2jAkmpj/pTX/pxxOVMTqi1z0PoDq6oYHnua3bz/75ELFbFt3XnF5chW2Xj78TDKmdneMbl7Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:10:38.567311Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.04488","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5215a1a5a917e3c7715b31cc2fdbf75a3518c1c51bab5bd10db8cb3dbc586eff","sha256:9be087fccd5166b1799c75c9d861517c07c59c230c1ab52f6713b4dac63317fc"],"state_sha256":"c4d1ed481914748a85fbab1e22480fb13078aa69e25405f0e5e7fe5cca8dca68"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HyrQgj5sQNcZu6TkLZPiVWLyyaEcb5lDelgUpGS3jiBDW7YRhCmop59c4P9UTjMc6kVo6JnsiWgdsLvAkWKJDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T07:25:39.890434Z","bundle_sha256":"8fd8132f440cadb119c15471b2e50a9a4b3f4454d93e939fe15ee51ec3570270"}}