{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:XHE3LQZBEFUHSPXFTYZO5PLYYM","short_pith_number":"pith:XHE3LQZB","canonical_record":{"source":{"id":"1502.03520","kind":"arxiv","version":8},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-12T02:50:08Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"d098ab0355f6afbf5d29d9e7610d0633dc2a7261e55aa45f2a569ef7a035b50c","abstract_canon_sha256":"0c9b84c6e7ffc607aa48983213e1d6e6147240923e16f3a65d1c3a9eb1bbf69a"},"schema_version":"1.0"},"canonical_sha256":"b9c9b5c3212168793ee59e32eebd78c30f11d9c6afdc390697374f5f5930386a","source":{"kind":"arxiv","id":"1502.03520","version":8},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.03520","created_at":"2026-05-17T23:42:54Z"},{"alias_kind":"arxiv_version","alias_value":"1502.03520v8","created_at":"2026-05-17T23:42:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.03520","created_at":"2026-05-17T23:42:54Z"},{"alias_kind":"pith_short_12","alias_value":"XHE3LQZBEFUH","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"XHE3LQZBEFUHSPXF","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"XHE3LQZB","created_at":"2026-05-18T12:29:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:XHE3LQZBEFUHSPXFTYZO5PLYYM","target":"record","payload":{"canonical_record":{"source":{"id":"1502.03520","kind":"arxiv","version":8},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-12T02:50:08Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"d098ab0355f6afbf5d29d9e7610d0633dc2a7261e55aa45f2a569ef7a035b50c","abstract_canon_sha256":"0c9b84c6e7ffc607aa48983213e1d6e6147240923e16f3a65d1c3a9eb1bbf69a"},"schema_version":"1.0"},"canonical_sha256":"b9c9b5c3212168793ee59e32eebd78c30f11d9c6afdc390697374f5f5930386a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:54.135356Z","signature_b64":"LAfRZjdzpBBMwT7S4MgN5imliBqYuQXwYklx/pZf+ZM2k0u2gVtmrLs7cwOzo1WGNv4TatwjuyCRgFXvLos0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9c9b5c3212168793ee59e32eebd78c30f11d9c6afdc390697374f5f5930386a","last_reissued_at":"2026-05-17T23:42:54.134775Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:54.134775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1502.03520","source_version":8,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7a+h+8pDq8DUHu0G3WwdTSLZuWUl7TdBgJIGaFQL1RrgMzLPQa/JMTWm2hwW1kfi1rfZAdIS9UKL98sSUJj0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T17:19:14.483835Z"},"content_sha256":"f45f862b0474ad1ea122eb4d539e07d726b1c11336c01cac77905ff5b6cd902c","schema_version":"1.0","event_id":"sha256:f45f862b0474ad1ea122eb4d539e07d726b1c11336c01cac77905ff5b6cd902c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:XHE3LQZBEFUHSPXFTYZO5PLYYM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Latent Variable Model Approach to PMI-based Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrej Risteski, Sanjeev Arora, Tengyu Ma, Yingyu Liang, Yuanzhi Li","submitted_at":"2015-02-12T02:50:08Z","abstract_excerpt":"Semantic word embeddings represent the meaning of a word via a vector, and are created by diverse methods. Many use nonlinear operations on co-occurrence statistics, and have hand-tuned hyperparameters and reweighting methods.\n  This paper proposes a new generative model, a dynamic version of the log-linear topic model of~\\citet{mnih2007three}. The methodological novelty is to use the prior to compute closed form expressions for word statistics. This provides a theoretical justification for nonlinear models like PMI, word2vec, and GloVe, as well as some hyperparameter choices. It also helps ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.03520","kind":"arxiv","version":8},"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":"2026-05-17T23:42:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N6N3ECgRce+XdNdUWEM0H0Y3cMjBhmnhjOrbLw5JlpFH8VieJIGTIPCwWTBNXSzyVIfody9disaVPyY8F/fjCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T17:19:14.484190Z"},"content_sha256":"74462ac671aeb53ff7ca02526761d4f0ec746e8ab4d936912af8dd4e63e60f50","schema_version":"1.0","event_id":"sha256:74462ac671aeb53ff7ca02526761d4f0ec746e8ab4d936912af8dd4e63e60f50"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XHE3LQZBEFUHSPXFTYZO5PLYYM/bundle.json","state_url":"https://pith.science/pith/XHE3LQZBEFUHSPXFTYZO5PLYYM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XHE3LQZBEFUHSPXFTYZO5PLYYM/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":"2026-06-03T17:19:14Z","links":{"resolver":"https://pith.science/pith/XHE3LQZBEFUHSPXFTYZO5PLYYM","bundle":"https://pith.science/pith/XHE3LQZBEFUHSPXFTYZO5PLYYM/bundle.json","state":"https://pith.science/pith/XHE3LQZBEFUHSPXFTYZO5PLYYM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XHE3LQZBEFUHSPXFTYZO5PLYYM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:XHE3LQZBEFUHSPXFTYZO5PLYYM","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":"0c9b84c6e7ffc607aa48983213e1d6e6147240923e16f3a65d1c3a9eb1bbf69a","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-12T02:50:08Z","title_canon_sha256":"d098ab0355f6afbf5d29d9e7610d0633dc2a7261e55aa45f2a569ef7a035b50c"},"schema_version":"1.0","source":{"id":"1502.03520","kind":"arxiv","version":8}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.03520","created_at":"2026-05-17T23:42:54Z"},{"alias_kind":"arxiv_version","alias_value":"1502.03520v8","created_at":"2026-05-17T23:42:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.03520","created_at":"2026-05-17T23:42:54Z"},{"alias_kind":"pith_short_12","alias_value":"XHE3LQZBEFUH","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"XHE3LQZBEFUHSPXF","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"XHE3LQZB","created_at":"2026-05-18T12:29:50Z"}],"graph_snapshots":[{"event_id":"sha256:74462ac671aeb53ff7ca02526761d4f0ec746e8ab4d936912af8dd4e63e60f50","target":"graph","created_at":"2026-05-17T23:42:54Z","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":"Semantic word embeddings represent the meaning of a word via a vector, and are created by diverse methods. Many use nonlinear operations on co-occurrence statistics, and have hand-tuned hyperparameters and reweighting methods.\n  This paper proposes a new generative model, a dynamic version of the log-linear topic model of~\\citet{mnih2007three}. The methodological novelty is to use the prior to compute closed form expressions for word statistics. This provides a theoretical justification for nonlinear models like PMI, word2vec, and GloVe, as well as some hyperparameter choices. It also helps ex","authors_text":"Andrej Risteski, Sanjeev Arora, Tengyu Ma, Yingyu Liang, Yuanzhi Li","cross_cats":["cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-12T02:50:08Z","title":"A Latent Variable Model Approach to PMI-based Word Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.03520","kind":"arxiv","version":8},"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:f45f862b0474ad1ea122eb4d539e07d726b1c11336c01cac77905ff5b6cd902c","target":"record","created_at":"2026-05-17T23:42:54Z","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":"0c9b84c6e7ffc607aa48983213e1d6e6147240923e16f3a65d1c3a9eb1bbf69a","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-12T02:50:08Z","title_canon_sha256":"d098ab0355f6afbf5d29d9e7610d0633dc2a7261e55aa45f2a569ef7a035b50c"},"schema_version":"1.0","source":{"id":"1502.03520","kind":"arxiv","version":8}},"canonical_sha256":"b9c9b5c3212168793ee59e32eebd78c30f11d9c6afdc390697374f5f5930386a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9c9b5c3212168793ee59e32eebd78c30f11d9c6afdc390697374f5f5930386a","first_computed_at":"2026-05-17T23:42:54.134775Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:54.134775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LAfRZjdzpBBMwT7S4MgN5imliBqYuQXwYklx/pZf+ZM2k0u2gVtmrLs7cwOzo1WGNv4TatwjuyCRgFXvLos0Aw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:54.135356Z","signed_message":"canonical_sha256_bytes"},"source_id":"1502.03520","source_kind":"arxiv","source_version":8}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f45f862b0474ad1ea122eb4d539e07d726b1c11336c01cac77905ff5b6cd902c","sha256:74462ac671aeb53ff7ca02526761d4f0ec746e8ab4d936912af8dd4e63e60f50"],"state_sha256":"9420efe4b8e77c8ada256dc4bfe4aecabf1ca328072e3039cf52c1c3edf372c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EjW4f77aE3F9x2cDVDn8NdfoE+vRmINJVRag5i4FzBT4hhLZiWapa2cGJ5BcwCWOOokY/5fM+IAagyC2b2mVAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T17:19:14.486413Z","bundle_sha256":"925b0b15e9c5914e619ede4cbe51a8912b4576b1431d8244a4dd557be7554b15"}}