{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:66TGJGZ5NIL72RT25P3DDKKXTH","short_pith_number":"pith:66TGJGZ5","schema_version":"1.0","canonical_sha256":"f7a6649b3d6a17fd467aebf631a95799f5e49e6d63f62869b7d8262fb4521047","source":{"kind":"arxiv","id":"1912.07506","version":1},"attestation_state":"computed","paper":{"title":"Scale-dependent Relationships in Natural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aakash Sarkar, Marc Howard","submitted_at":"2019-12-16T17:12:00Z","abstract_excerpt":"Natural language exhibits statistical dependencies at a wide range of scales. For instance, the mutual information between words in natural language decays like a power law with the temporal lag between them. However, many statistical learning models applied to language impose a sampling scale while extracting statistical structure. For instance, Word2Vec constructs a vector embedding that maximizes the prediction between a target word and the context words that appear nearby in the corpus. The size of the context is chosen by the user and defines a strong scale; relationships over much larger"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1912.07506","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-16T17:12:00Z","cross_cats_sorted":[],"title_canon_sha256":"36c4c2f339075f5f23afe264f1584cab880ea75c3aa715aad9735681fcea6194","abstract_canon_sha256":"fea7b029d9e2fb0b2be04d61221fa2b57bf5509ae957a6a2c4a6aeedb8102c90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:26:22.238685Z","signature_b64":"yhsvbHLwiX3W8M9CQJAtMdBnyMDtiRX0rHwmzJql6gBnxf0d4dUi18Iiy1Qduq5qjHTNHAJLY53q1VjfQfxvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7a6649b3d6a17fd467aebf631a95799f5e49e6d63f62869b7d8262fb4521047","last_reissued_at":"2026-07-05T00:26:22.238297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:26:22.238297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scale-dependent Relationships in Natural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aakash Sarkar, Marc Howard","submitted_at":"2019-12-16T17:12:00Z","abstract_excerpt":"Natural language exhibits statistical dependencies at a wide range of scales. For instance, the mutual information between words in natural language decays like a power law with the temporal lag between them. However, many statistical learning models applied to language impose a sampling scale while extracting statistical structure. For instance, Word2Vec constructs a vector embedding that maximizes the prediction between a target word and the context words that appear nearby in the corpus. The size of the context is chosen by the user and defines a strong scale; relationships over much larger"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.07506","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.07506/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1912.07506","created_at":"2026-07-05T00:26:22.238366+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.07506v1","created_at":"2026-07-05T00:26:22.238366+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.07506","created_at":"2026-07-05T00:26:22.238366+00:00"},{"alias_kind":"pith_short_12","alias_value":"66TGJGZ5NIL7","created_at":"2026-07-05T00:26:22.238366+00:00"},{"alias_kind":"pith_short_16","alias_value":"66TGJGZ5NIL72RT2","created_at":"2026-07-05T00:26:22.238366+00:00"},{"alias_kind":"pith_short_8","alias_value":"66TGJGZ5","created_at":"2026-07-05T00:26:22.238366+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.09093","citing_title":"The Announcement Carries the Cue: Markup, Boundaries, and the Notation of Pre-Training Corpora","ref_index":68,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/66TGJGZ5NIL72RT25P3DDKKXTH","json":"https://pith.science/pith/66TGJGZ5NIL72RT25P3DDKKXTH.json","graph_json":"https://pith.science/api/pith-number/66TGJGZ5NIL72RT25P3DDKKXTH/graph.json","events_json":"https://pith.science/api/pith-number/66TGJGZ5NIL72RT25P3DDKKXTH/events.json","paper":"https://pith.science/paper/66TGJGZ5"},"agent_actions":{"view_html":"https://pith.science/pith/66TGJGZ5NIL72RT25P3DDKKXTH","download_json":"https://pith.science/pith/66TGJGZ5NIL72RT25P3DDKKXTH.json","view_paper":"https://pith.science/paper/66TGJGZ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.07506&json=true","fetch_graph":"https://pith.science/api/pith-number/66TGJGZ5NIL72RT25P3DDKKXTH/graph.json","fetch_events":"https://pith.science/api/pith-number/66TGJGZ5NIL72RT25P3DDKKXTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66TGJGZ5NIL72RT25P3DDKKXTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66TGJGZ5NIL72RT25P3DDKKXTH/action/storage_attestation","attest_author":"https://pith.science/pith/66TGJGZ5NIL72RT25P3DDKKXTH/action/author_attestation","sign_citation":"https://pith.science/pith/66TGJGZ5NIL72RT25P3DDKKXTH/action/citation_signature","submit_replication":"https://pith.science/pith/66TGJGZ5NIL72RT25P3DDKKXTH/action/replication_record"}},"created_at":"2026-07-05T00:26:22.238366+00:00","updated_at":"2026-07-05T00:26:22.238366+00:00"}