{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:MTO5JVR62AK7RGPDKAQWOGVRD2","short_pith_number":"pith:MTO5JVR6","canonical_record":{"source":{"id":"1911.03855","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2019-11-10T05:13:29Z","cross_cats_sorted":["cs.CL","cs.CY"],"title_canon_sha256":"88d3180d120f18a3619c3fb1c990cd982aa8980d578fb8b3bc377aea73d89250","abstract_canon_sha256":"eaebeb9e1323dfeb437d0685ce82c2f9ad618cde4252db5038253038dd5f3ce9"},"schema_version":"1.0"},"canonical_sha256":"64ddd4d63ed015f899e35021671ab11e9d77004b977cb7191911c641d0063584","source":{"kind":"arxiv","id":"1911.03855","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.03855","created_at":"2026-07-05T04:29:22Z"},{"alias_kind":"arxiv_version","alias_value":"1911.03855v4","created_at":"2026-07-05T04:29:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.03855","created_at":"2026-07-05T04:29:22Z"},{"alias_kind":"pith_short_12","alias_value":"MTO5JVR62AK7","created_at":"2026-07-05T04:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"MTO5JVR62AK7RGPD","created_at":"2026-07-05T04:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"MTO5JVR6","created_at":"2026-07-05T04:29:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:MTO5JVR62AK7RGPDKAQWOGVRD2","target":"record","payload":{"canonical_record":{"source":{"id":"1911.03855","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2019-11-10T05:13:29Z","cross_cats_sorted":["cs.CL","cs.CY"],"title_canon_sha256":"88d3180d120f18a3619c3fb1c990cd982aa8980d578fb8b3bc377aea73d89250","abstract_canon_sha256":"eaebeb9e1323dfeb437d0685ce82c2f9ad618cde4252db5038253038dd5f3ce9"},"schema_version":"1.0"},"canonical_sha256":"64ddd4d63ed015f899e35021671ab11e9d77004b977cb7191911c641d0063584","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:29:22.549671Z","signature_b64":"TtmXgD5pbz7+e30jN+Ei0RTipOLaYNLteyVg3eJm/XLzKyOYhWr5siolehca+eLPTHh9hEYeiKbDuL6tlYOoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64ddd4d63ed015f899e35021671ab11e9d77004b977cb7191911c641d0063584","last_reissued_at":"2026-07-05T04:29:22.549241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:29:22.549241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.03855","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:29:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZdnadxyCjxJTtpcOwL9zJogeQFR2uzWLIFvN+o7dOvy8my9cNSpEA+Qe2p12UFTex4+8Qrba1qrHRqIqqjelCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:29:08.315509Z"},"content_sha256":"a827ee6322bc48a39162a17d90fd9fef367ba84f4c5e2d429e0762a8dcc26ccf","schema_version":"1.0","event_id":"sha256:a827ee6322bc48a39162a17d90fd9fef367ba84f4c5e2d429e0762a8dcc26ccf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:MTO5JVR62AK7RGPDKAQWOGVRD2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Correcting Sociodemographic Selection Biases for Population Prediction from Social Media","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CY"],"primary_cat":"cs.SI","authors_text":"Farhan Ahmed, H. Andrew Schwartz, Keshav Gupta, Lyle Ungar, Salvatore Giorgi, Sandra Matz, Veronica Lynn","submitted_at":"2019-11-10T05:13:29Z","abstract_excerpt":"Social media is increasingly used for large-scale population predictions, such as estimating community health statistics. However, social media users are not typically a representative sample of the intended population -- a \"selection bias\". Within the social sciences, such a bias is typically addressed with restratification techniques, where observations are reweighted according to how under- or over-sampled their socio-demographic groups are. Yet, restratifaction is rarely evaluated for improving prediction. In this two-part study, we first evaluate standard, \"out-of-the-box\" restratificatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.03855","kind":"arxiv","version":4},"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/1911.03855/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:29:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NnV466mhbxgo6/mXrZslJAI2jpvuhRF8UYfTB7oRw6iclkFYjfIBESxQ0c5IBE9vQ03ERf+3mW9tAhcVbsVwBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:29:08.315903Z"},"content_sha256":"bfa71d024582ecded9485cbfeb91a361111c3b2007517409c05596d01ca7f0cb","schema_version":"1.0","event_id":"sha256:bfa71d024582ecded9485cbfeb91a361111c3b2007517409c05596d01ca7f0cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MTO5JVR62AK7RGPDKAQWOGVRD2/bundle.json","state_url":"https://pith.science/pith/MTO5JVR62AK7RGPDKAQWOGVRD2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MTO5JVR62AK7RGPDKAQWOGVRD2/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":"2026-07-07T15:29:08Z","links":{"resolver":"https://pith.science/pith/MTO5JVR62AK7RGPDKAQWOGVRD2","bundle":"https://pith.science/pith/MTO5JVR62AK7RGPDKAQWOGVRD2/bundle.json","state":"https://pith.science/pith/MTO5JVR62AK7RGPDKAQWOGVRD2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MTO5JVR62AK7RGPDKAQWOGVRD2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MTO5JVR62AK7RGPDKAQWOGVRD2","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":"eaebeb9e1323dfeb437d0685ce82c2f9ad618cde4252db5038253038dd5f3ce9","cross_cats_sorted":["cs.CL","cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2019-11-10T05:13:29Z","title_canon_sha256":"88d3180d120f18a3619c3fb1c990cd982aa8980d578fb8b3bc377aea73d89250"},"schema_version":"1.0","source":{"id":"1911.03855","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.03855","created_at":"2026-07-05T04:29:22Z"},{"alias_kind":"arxiv_version","alias_value":"1911.03855v4","created_at":"2026-07-05T04:29:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.03855","created_at":"2026-07-05T04:29:22Z"},{"alias_kind":"pith_short_12","alias_value":"MTO5JVR62AK7","created_at":"2026-07-05T04:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"MTO5JVR62AK7RGPD","created_at":"2026-07-05T04:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"MTO5JVR6","created_at":"2026-07-05T04:29:22Z"}],"graph_snapshots":[{"event_id":"sha256:bfa71d024582ecded9485cbfeb91a361111c3b2007517409c05596d01ca7f0cb","target":"graph","created_at":"2026-07-05T04:29:22Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1911.03855/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Social media is increasingly used for large-scale population predictions, such as estimating community health statistics. However, social media users are not typically a representative sample of the intended population -- a \"selection bias\". Within the social sciences, such a bias is typically addressed with restratification techniques, where observations are reweighted according to how under- or over-sampled their socio-demographic groups are. Yet, restratifaction is rarely evaluated for improving prediction. In this two-part study, we first evaluate standard, \"out-of-the-box\" restratificatio","authors_text":"Farhan Ahmed, H. Andrew Schwartz, Keshav Gupta, Lyle Ungar, Salvatore Giorgi, Sandra Matz, Veronica Lynn","cross_cats":["cs.CL","cs.CY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2019-11-10T05:13:29Z","title":"Correcting Sociodemographic Selection Biases for Population Prediction from Social Media"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.03855","kind":"arxiv","version":4},"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:a827ee6322bc48a39162a17d90fd9fef367ba84f4c5e2d429e0762a8dcc26ccf","target":"record","created_at":"2026-07-05T04:29:22Z","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":"eaebeb9e1323dfeb437d0685ce82c2f9ad618cde4252db5038253038dd5f3ce9","cross_cats_sorted":["cs.CL","cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2019-11-10T05:13:29Z","title_canon_sha256":"88d3180d120f18a3619c3fb1c990cd982aa8980d578fb8b3bc377aea73d89250"},"schema_version":"1.0","source":{"id":"1911.03855","kind":"arxiv","version":4}},"canonical_sha256":"64ddd4d63ed015f899e35021671ab11e9d77004b977cb7191911c641d0063584","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64ddd4d63ed015f899e35021671ab11e9d77004b977cb7191911c641d0063584","first_computed_at":"2026-07-05T04:29:22.549241Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:29:22.549241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TtmXgD5pbz7+e30jN+Ei0RTipOLaYNLteyVg3eJm/XLzKyOYhWr5siolehca+eLPTHh9hEYeiKbDuL6tlYOoCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:29:22.549671Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.03855","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a827ee6322bc48a39162a17d90fd9fef367ba84f4c5e2d429e0762a8dcc26ccf","sha256:bfa71d024582ecded9485cbfeb91a361111c3b2007517409c05596d01ca7f0cb"],"state_sha256":"c5c149594631300dfdbcc492852b86ceb6ff587d9cc37e3fea7e86265279476b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KHcap7tJvTzkHAUzUuViSEqoPr87wiiY7+7yIb5nQoNoH88mK31lbzj9VS0X/rHGDwOagnki1G/Flu7qkzD9Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:29:08.317798Z","bundle_sha256":"39a0a87440ed02035bda768fb57bb0d9591aa60d1eea5e070467c8c16dd96e23"}}