{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:XZ6EE57CPSY6IQT2SYCMFCNS2K","short_pith_number":"pith:XZ6EE57C","canonical_record":{"source":{"id":"1609.08293","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-27T07:38:29Z","cross_cats_sorted":[],"title_canon_sha256":"5d231d454ba57210e833fb5929e9b1f955bc7d4d5076bdef12af142df6b9bb22","abstract_canon_sha256":"15b1a47eae1b6827bbbb29e73420a68cf85c02c5c62fd281623b4bcc16fd266f"},"schema_version":"1.0"},"canonical_sha256":"be7c4277e27cb1e4427a9604c289b2d285915c1b44e7f2d2e8c84fd7913f4f87","source":{"kind":"arxiv","id":"1609.08293","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.08293","created_at":"2026-05-18T01:03:46Z"},{"alias_kind":"arxiv_version","alias_value":"1609.08293v1","created_at":"2026-05-18T01:03:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.08293","created_at":"2026-05-18T01:03:46Z"},{"alias_kind":"pith_short_12","alias_value":"XZ6EE57CPSY6","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"XZ6EE57CPSY6IQT2","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"XZ6EE57C","created_at":"2026-05-18T12:30:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:XZ6EE57CPSY6IQT2SYCMFCNS2K","target":"record","payload":{"canonical_record":{"source":{"id":"1609.08293","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-27T07:38:29Z","cross_cats_sorted":[],"title_canon_sha256":"5d231d454ba57210e833fb5929e9b1f955bc7d4d5076bdef12af142df6b9bb22","abstract_canon_sha256":"15b1a47eae1b6827bbbb29e73420a68cf85c02c5c62fd281623b4bcc16fd266f"},"schema_version":"1.0"},"canonical_sha256":"be7c4277e27cb1e4427a9604c289b2d285915c1b44e7f2d2e8c84fd7913f4f87","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:46.203456Z","signature_b64":"VwAFGlCIzyV5wC9yXM5yl1H6/YGJcK+4HuRxPR9ScHgNlU0mjcOr/XmKATlC8AF/sSKIpLJolMCL1uRVDqPCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be7c4277e27cb1e4427a9604c289b2d285915c1b44e7f2d2e8c84fd7913f4f87","last_reissued_at":"2026-05-18T01:03:46.203051Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:46.203051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.08293","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":"2026-05-18T01:03:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2/mo5i9b2okpgzXdaOkhvibtsV0xq4+Xof2j5wWC3oaryhlp5OvlZgWWEhcShPYsazlHnaj/v8wqDyI4Ib43Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T07:15:06.905462Z"},"content_sha256":"b01d058ce4161076d5ad02c3192112d55af65de2116570091126dad7590a57a9","schema_version":"1.0","event_id":"sha256:b01d058ce4161076d5ad02c3192112d55af65de2116570091126dad7590a57a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:XZ6EE57CPSY6IQT2SYCMFCNS2K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Effects of Data Size and Frequency Range on Distributional Semantic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alessandro Lenci, Magnus Sahlgren","submitted_at":"2016-09-27T07:38:29Z","abstract_excerpt":"This paper investigates the effects of data size and frequency range on distributional semantic models. We compare the performance of a number of representative models for several test settings over data of varying sizes, and over test items of various frequency. Our results show that neural network-based models underperform when the data is small, and that the most reliable model over data of varying sizes and frequency ranges is the inverted factorized model."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.08293","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":"2026-05-18T01:03:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JWdkEELGg+HPv4CsTIqQCrBrvxdjbxMHqXQi61SDA+JjyzVBhq3CPB4hSzMgzN89vwPLGcsyDcxhXXcl+YGuDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T07:15:06.905812Z"},"content_sha256":"c3f0f735cdfb08eab1dfb18ad487f2822ba44b5582a678538b840b3b9617624c","schema_version":"1.0","event_id":"sha256:c3f0f735cdfb08eab1dfb18ad487f2822ba44b5582a678538b840b3b9617624c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XZ6EE57CPSY6IQT2SYCMFCNS2K/bundle.json","state_url":"https://pith.science/pith/XZ6EE57CPSY6IQT2SYCMFCNS2K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XZ6EE57CPSY6IQT2SYCMFCNS2K/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":"2026-05-31T07:15:06Z","links":{"resolver":"https://pith.science/pith/XZ6EE57CPSY6IQT2SYCMFCNS2K","bundle":"https://pith.science/pith/XZ6EE57CPSY6IQT2SYCMFCNS2K/bundle.json","state":"https://pith.science/pith/XZ6EE57CPSY6IQT2SYCMFCNS2K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XZ6EE57CPSY6IQT2SYCMFCNS2K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:XZ6EE57CPSY6IQT2SYCMFCNS2K","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":"15b1a47eae1b6827bbbb29e73420a68cf85c02c5c62fd281623b4bcc16fd266f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-27T07:38:29Z","title_canon_sha256":"5d231d454ba57210e833fb5929e9b1f955bc7d4d5076bdef12af142df6b9bb22"},"schema_version":"1.0","source":{"id":"1609.08293","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.08293","created_at":"2026-05-18T01:03:46Z"},{"alias_kind":"arxiv_version","alias_value":"1609.08293v1","created_at":"2026-05-18T01:03:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.08293","created_at":"2026-05-18T01:03:46Z"},{"alias_kind":"pith_short_12","alias_value":"XZ6EE57CPSY6","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"XZ6EE57CPSY6IQT2","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"XZ6EE57C","created_at":"2026-05-18T12:30:51Z"}],"graph_snapshots":[{"event_id":"sha256:c3f0f735cdfb08eab1dfb18ad487f2822ba44b5582a678538b840b3b9617624c","target":"graph","created_at":"2026-05-18T01:03:46Z","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":"This paper investigates the effects of data size and frequency range on distributional semantic models. We compare the performance of a number of representative models for several test settings over data of varying sizes, and over test items of various frequency. Our results show that neural network-based models underperform when the data is small, and that the most reliable model over data of varying sizes and frequency ranges is the inverted factorized model.","authors_text":"Alessandro Lenci, Magnus Sahlgren","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-27T07:38:29Z","title":"The Effects of Data Size and Frequency Range on Distributional Semantic Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.08293","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:b01d058ce4161076d5ad02c3192112d55af65de2116570091126dad7590a57a9","target":"record","created_at":"2026-05-18T01:03:46Z","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":"15b1a47eae1b6827bbbb29e73420a68cf85c02c5c62fd281623b4bcc16fd266f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-27T07:38:29Z","title_canon_sha256":"5d231d454ba57210e833fb5929e9b1f955bc7d4d5076bdef12af142df6b9bb22"},"schema_version":"1.0","source":{"id":"1609.08293","kind":"arxiv","version":1}},"canonical_sha256":"be7c4277e27cb1e4427a9604c289b2d285915c1b44e7f2d2e8c84fd7913f4f87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be7c4277e27cb1e4427a9604c289b2d285915c1b44e7f2d2e8c84fd7913f4f87","first_computed_at":"2026-05-18T01:03:46.203051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:03:46.203051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VwAFGlCIzyV5wC9yXM5yl1H6/YGJcK+4HuRxPR9ScHgNlU0mjcOr/XmKATlC8AF/sSKIpLJolMCL1uRVDqPCBw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:03:46.203456Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.08293","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b01d058ce4161076d5ad02c3192112d55af65de2116570091126dad7590a57a9","sha256:c3f0f735cdfb08eab1dfb18ad487f2822ba44b5582a678538b840b3b9617624c"],"state_sha256":"b015326ad47f40daa9af92dd24fc6e5e7c18a74a0516c5f28ea5d644ffb96da4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QoiTrp8dOzOEGD++OpcaY6cLNuhrKvkb+Mj+KAu97/P0xAOVPOk1ZALqbcllj3Q7JGEbSwgxg6ZjoZpuIN3OAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T07:15:06.907852Z","bundle_sha256":"6e046223907a02d1ad5ebb662f88211bd706f9db334496cc3e02215842b7cc31"}}