{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CBQOQGFYS53IEXNPRDRYYUCTAD","short_pith_number":"pith:CBQOQGFY","schema_version":"1.0","canonical_sha256":"1060e818b89776825daf88e38c505300ebd39b877ba35548ca3b7e9a43318d06","source":{"kind":"arxiv","id":"2004.14287","version":1},"attestation_state":"computed","paper":{"title":"General Purpose Text Embeddings from Pre-trained Language Models for Scalable Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haoran Li, Jingfei Du, Myle Ott, Veselin Stoyanov, Xing Zhou","submitted_at":"2020-04-29T16:11:26Z","abstract_excerpt":"The state of the art on many NLP tasks is currently achieved by large pre-trained language models, which require a considerable amount of computation. We explore a setting where many different predictions are made on a single piece of text. In that case, some of the computational cost during inference can be amortized over the different tasks using a shared text encoder. We compare approaches for training such an encoder and show that encoders pre-trained over multiple tasks generalize well to unseen tasks. We also compare ways of extracting fixed- and limited-size representations from this en"},"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":"2004.14287","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T16:11:26Z","cross_cats_sorted":[],"title_canon_sha256":"ba868c670ff9cf26db2de97d0bbfb2b97855dec961e86ecc5b76e19813d7fa5a","abstract_canon_sha256":"ff30cf63bbb83f4d31abd7bd96743d8cf3c468dbdd8b0f4ef24e294d326b6549"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:19.142367Z","signature_b64":"mJCC+EUs33uCE3wHfTaiPtga6lHMaurMUpildMNJ0i6dYWp1SbbqsZpCiFulMZ1ZTcMR76rK2Ys8bgK52uh9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1060e818b89776825daf88e38c505300ebd39b877ba35548ca3b7e9a43318d06","last_reissued_at":"2026-07-05T00:59:19.141950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:19.141950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"General Purpose Text Embeddings from Pre-trained Language Models for Scalable Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haoran Li, Jingfei Du, Myle Ott, Veselin Stoyanov, Xing Zhou","submitted_at":"2020-04-29T16:11:26Z","abstract_excerpt":"The state of the art on many NLP tasks is currently achieved by large pre-trained language models, which require a considerable amount of computation. We explore a setting where many different predictions are made on a single piece of text. In that case, some of the computational cost during inference can be amortized over the different tasks using a shared text encoder. We compare approaches for training such an encoder and show that encoders pre-trained over multiple tasks generalize well to unseen tasks. We also compare ways of extracting fixed- and limited-size representations from this en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14287","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/2004.14287/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":"2004.14287","created_at":"2026-07-05T00:59:19.142000+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.14287v1","created_at":"2026-07-05T00:59:19.142000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14287","created_at":"2026-07-05T00:59:19.142000+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBQOQGFYS53I","created_at":"2026-07-05T00:59:19.142000+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBQOQGFYS53IEXNP","created_at":"2026-07-05T00:59:19.142000+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBQOQGFY","created_at":"2026-07-05T00:59:19.142000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CBQOQGFYS53IEXNPRDRYYUCTAD","json":"https://pith.science/pith/CBQOQGFYS53IEXNPRDRYYUCTAD.json","graph_json":"https://pith.science/api/pith-number/CBQOQGFYS53IEXNPRDRYYUCTAD/graph.json","events_json":"https://pith.science/api/pith-number/CBQOQGFYS53IEXNPRDRYYUCTAD/events.json","paper":"https://pith.science/paper/CBQOQGFY"},"agent_actions":{"view_html":"https://pith.science/pith/CBQOQGFYS53IEXNPRDRYYUCTAD","download_json":"https://pith.science/pith/CBQOQGFYS53IEXNPRDRYYUCTAD.json","view_paper":"https://pith.science/paper/CBQOQGFY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.14287&json=true","fetch_graph":"https://pith.science/api/pith-number/CBQOQGFYS53IEXNPRDRYYUCTAD/graph.json","fetch_events":"https://pith.science/api/pith-number/CBQOQGFYS53IEXNPRDRYYUCTAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBQOQGFYS53IEXNPRDRYYUCTAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBQOQGFYS53IEXNPRDRYYUCTAD/action/storage_attestation","attest_author":"https://pith.science/pith/CBQOQGFYS53IEXNPRDRYYUCTAD/action/author_attestation","sign_citation":"https://pith.science/pith/CBQOQGFYS53IEXNPRDRYYUCTAD/action/citation_signature","submit_replication":"https://pith.science/pith/CBQOQGFYS53IEXNPRDRYYUCTAD/action/replication_record"}},"created_at":"2026-07-05T00:59:19.142000+00:00","updated_at":"2026-07-05T00:59:19.142000+00:00"}