{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:PKZYPYKWOQWLLNFOH5S5P3GKYC","short_pith_number":"pith:PKZYPYKW","canonical_record":{"source":{"id":"1602.03483","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-02-10T18:49:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"15616cef402aaaf9f1491c58b438e741b56d3cb1b15b4778b8018a028224b6d0","abstract_canon_sha256":"72a7d4adf858472fef468473f6b4c24364eea6c9b1f98324f0d8bad98cb37d75"},"schema_version":"1.0"},"canonical_sha256":"7ab387e156742cb5b4ae3f65d7eccac0bda9fe991eb839245cf33dcb339d058e","source":{"kind":"arxiv","id":"1602.03483","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.03483","created_at":"2026-05-18T01:20:59Z"},{"alias_kind":"arxiv_version","alias_value":"1602.03483v1","created_at":"2026-05-18T01:20:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.03483","created_at":"2026-05-18T01:20:59Z"},{"alias_kind":"pith_short_12","alias_value":"PKZYPYKWOQWL","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"PKZYPYKWOQWLLNFO","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"PKZYPYKW","created_at":"2026-05-18T12:30:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:PKZYPYKWOQWLLNFOH5S5P3GKYC","target":"record","payload":{"canonical_record":{"source":{"id":"1602.03483","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-02-10T18:49:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"15616cef402aaaf9f1491c58b438e741b56d3cb1b15b4778b8018a028224b6d0","abstract_canon_sha256":"72a7d4adf858472fef468473f6b4c24364eea6c9b1f98324f0d8bad98cb37d75"},"schema_version":"1.0"},"canonical_sha256":"7ab387e156742cb5b4ae3f65d7eccac0bda9fe991eb839245cf33dcb339d058e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:59.824931Z","signature_b64":"O3hisvZ8zF/x67/L4eqFhYixJFttNo4JvnURd1UA64XWSz4CDRgX/yb+ECL8LKkXCIHIac1GcXJ/5vdmeltVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ab387e156742cb5b4ae3f65d7eccac0bda9fe991eb839245cf33dcb339d058e","last_reissued_at":"2026-05-18T01:20:59.824347Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:59.824347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1602.03483","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":"2026-05-18T01:20:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vx2iaw5jZFcqIuXsYRhI68x8CwFiThM5CfC9/zuRjHXqOGcXMo7gaRFeI5qrXn8DmwUYcA7U8OAbX3BrqtceCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T19:20:59.650878Z"},"content_sha256":"aede14705e790171697006ad0064fe21ca2fe0f49bc5d647269869d0abe37639","schema_version":"1.0","event_id":"sha256:aede14705e790171697006ad0064fe21ca2fe0f49bc5d647269869d0abe37639"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:PKZYPYKWOQWLLNFOH5S5P3GKYC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Distributed Representations of Sentences from Unlabelled Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anna Korhonen, Felix Hill, Kyunghyun Cho","submitted_at":"2016-02-10T18:49:58Z","abstract_excerpt":"Unsupervised methods for learning distributed representations of words are ubiquitous in today's NLP research, but far less is known about the best ways to learn distributed phrase or sentence representations from unlabelled data. This paper is a systematic comparison of models that learn such representations. We find that the optimal approach depends critically on the intended application. Deeper, more complex models are preferable for representations to be used in supervised systems, but shallow log-linear models work best for building representation spaces that can be decoded with simple sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.03483","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":"2026-05-18T01:20:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BVDX2RS0cw4hi/1tKuAIodRJoFZ58TdgI8mWANUTnSMNvwHA0ttycawNG6eZ79VtwSu1g16ipINTuOrGuWScDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T19:20:59.651529Z"},"content_sha256":"b12aded947b1adc8c4eb2959344c9956814e71026e450c897c7ffdd48d96ecb4","schema_version":"1.0","event_id":"sha256:b12aded947b1adc8c4eb2959344c9956814e71026e450c897c7ffdd48d96ecb4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PKZYPYKWOQWLLNFOH5S5P3GKYC/bundle.json","state_url":"https://pith.science/pith/PKZYPYKWOQWLLNFOH5S5P3GKYC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PKZYPYKWOQWLLNFOH5S5P3GKYC/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":"2026-06-06T19:20:59Z","links":{"resolver":"https://pith.science/pith/PKZYPYKWOQWLLNFOH5S5P3GKYC","bundle":"https://pith.science/pith/PKZYPYKWOQWLLNFOH5S5P3GKYC/bundle.json","state":"https://pith.science/pith/PKZYPYKWOQWLLNFOH5S5P3GKYC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PKZYPYKWOQWLLNFOH5S5P3GKYC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:PKZYPYKWOQWLLNFOH5S5P3GKYC","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":"72a7d4adf858472fef468473f6b4c24364eea6c9b1f98324f0d8bad98cb37d75","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-02-10T18:49:58Z","title_canon_sha256":"15616cef402aaaf9f1491c58b438e741b56d3cb1b15b4778b8018a028224b6d0"},"schema_version":"1.0","source":{"id":"1602.03483","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.03483","created_at":"2026-05-18T01:20:59Z"},{"alias_kind":"arxiv_version","alias_value":"1602.03483v1","created_at":"2026-05-18T01:20:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.03483","created_at":"2026-05-18T01:20:59Z"},{"alias_kind":"pith_short_12","alias_value":"PKZYPYKWOQWL","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"PKZYPYKWOQWLLNFO","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"PKZYPYKW","created_at":"2026-05-18T12:30:39Z"}],"graph_snapshots":[{"event_id":"sha256:b12aded947b1adc8c4eb2959344c9956814e71026e450c897c7ffdd48d96ecb4","target":"graph","created_at":"2026-05-18T01:20:59Z","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":"Unsupervised methods for learning distributed representations of words are ubiquitous in today's NLP research, but far less is known about the best ways to learn distributed phrase or sentence representations from unlabelled data. This paper is a systematic comparison of models that learn such representations. We find that the optimal approach depends critically on the intended application. Deeper, more complex models are preferable for representations to be used in supervised systems, but shallow log-linear models work best for building representation spaces that can be decoded with simple sp","authors_text":"Anna Korhonen, Felix Hill, Kyunghyun Cho","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-02-10T18:49:58Z","title":"Learning Distributed Representations of Sentences from Unlabelled Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.03483","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:aede14705e790171697006ad0064fe21ca2fe0f49bc5d647269869d0abe37639","target":"record","created_at":"2026-05-18T01:20:59Z","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":"72a7d4adf858472fef468473f6b4c24364eea6c9b1f98324f0d8bad98cb37d75","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-02-10T18:49:58Z","title_canon_sha256":"15616cef402aaaf9f1491c58b438e741b56d3cb1b15b4778b8018a028224b6d0"},"schema_version":"1.0","source":{"id":"1602.03483","kind":"arxiv","version":1}},"canonical_sha256":"7ab387e156742cb5b4ae3f65d7eccac0bda9fe991eb839245cf33dcb339d058e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ab387e156742cb5b4ae3f65d7eccac0bda9fe991eb839245cf33dcb339d058e","first_computed_at":"2026-05-18T01:20:59.824347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:20:59.824347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O3hisvZ8zF/x67/L4eqFhYixJFttNo4JvnURd1UA64XWSz4CDRgX/yb+ECL8LKkXCIHIac1GcXJ/5vdmeltVBg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:20:59.824931Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.03483","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aede14705e790171697006ad0064fe21ca2fe0f49bc5d647269869d0abe37639","sha256:b12aded947b1adc8c4eb2959344c9956814e71026e450c897c7ffdd48d96ecb4"],"state_sha256":"c305ccec1c779a0053b55533114dd32555954754febf5d03d661f367e9e90bf7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hmI+g2LaoCLMEPlm+djY+GU1DdDMim3Q2QYrF/sCvJYtvfwqTOiaLsx5hzuXYwzpi7orLJ8+2oJdOo+uxNGIAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T19:20:59.656241Z","bundle_sha256":"4c98b59fa28fe9aa35c79397fa8111b25c756c9974591ad67c7351474d7b207a"}}