{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:W4ZRHNQZCJUG3MEHUTESHFL37T","short_pith_number":"pith:W4ZRHNQZ","schema_version":"1.0","canonical_sha256":"b73313b61912686db087a4c923957bfcfd66a518641b03c9aa7ab4aa55bdeb60","source":{"kind":"arxiv","id":"1909.02635","version":1},"attestation_state":"computed","paper":{"title":"Effective Use of Transformer Networks for Entity Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditya Gupta, Greg Durrett","submitted_at":"2019-09-05T21:13:37Z","abstract_excerpt":"Tracking entities in procedural language requires understanding the transformations arising from actions on entities as well as those entities' interactions. While self-attention-based pre-trained language encoders like GPT and BERT have been successfully applied across a range of natural language understanding tasks, their ability to handle the nuances of procedural texts is still untested. In this paper, we explore the use of pre-trained transformer networks for entity tracking tasks in procedural text. First, we test standard lightweight approaches for prediction with pre-trained transforme"},"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":"1909.02635","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-05T21:13:37Z","cross_cats_sorted":[],"title_canon_sha256":"c47fedde115911d3fadd0aa5f3c554d197bcaba958e476e747108729a02f0a5f","abstract_canon_sha256":"e1cea39c49deb0f0ef353660fc89d71b84595eeb988df8baea7887d227706ae6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:41.308762Z","signature_b64":"P38FLU9kWJhMx3MCkvjVpGpQagTSzQteZq79k+dc5SSm58Ay6NttkuwksNiRM6bFtTi8HXEKmefPA9iZn3RRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b73313b61912686db087a4c923957bfcfd66a518641b03c9aa7ab4aa55bdeb60","last_reissued_at":"2026-07-05T00:02:41.308234Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:41.308234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effective Use of Transformer Networks for Entity Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditya Gupta, Greg Durrett","submitted_at":"2019-09-05T21:13:37Z","abstract_excerpt":"Tracking entities in procedural language requires understanding the transformations arising from actions on entities as well as those entities' interactions. While self-attention-based pre-trained language encoders like GPT and BERT have been successfully applied across a range of natural language understanding tasks, their ability to handle the nuances of procedural texts is still untested. In this paper, we explore the use of pre-trained transformer networks for entity tracking tasks in procedural text. First, we test standard lightweight approaches for prediction with pre-trained transforme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02635","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/1909.02635/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":"1909.02635","created_at":"2026-07-05T00:02:41.308321+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.02635v1","created_at":"2026-07-05T00:02:41.308321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02635","created_at":"2026-07-05T00:02:41.308321+00:00"},{"alias_kind":"pith_short_12","alias_value":"W4ZRHNQZCJUG","created_at":"2026-07-05T00:02:41.308321+00:00"},{"alias_kind":"pith_short_16","alias_value":"W4ZRHNQZCJUG3MEH","created_at":"2026-07-05T00:02:41.308321+00:00"},{"alias_kind":"pith_short_8","alias_value":"W4ZRHNQZ","created_at":"2026-07-05T00:02:41.308321+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/W4ZRHNQZCJUG3MEHUTESHFL37T","json":"https://pith.science/pith/W4ZRHNQZCJUG3MEHUTESHFL37T.json","graph_json":"https://pith.science/api/pith-number/W4ZRHNQZCJUG3MEHUTESHFL37T/graph.json","events_json":"https://pith.science/api/pith-number/W4ZRHNQZCJUG3MEHUTESHFL37T/events.json","paper":"https://pith.science/paper/W4ZRHNQZ"},"agent_actions":{"view_html":"https://pith.science/pith/W4ZRHNQZCJUG3MEHUTESHFL37T","download_json":"https://pith.science/pith/W4ZRHNQZCJUG3MEHUTESHFL37T.json","view_paper":"https://pith.science/paper/W4ZRHNQZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.02635&json=true","fetch_graph":"https://pith.science/api/pith-number/W4ZRHNQZCJUG3MEHUTESHFL37T/graph.json","fetch_events":"https://pith.science/api/pith-number/W4ZRHNQZCJUG3MEHUTESHFL37T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W4ZRHNQZCJUG3MEHUTESHFL37T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W4ZRHNQZCJUG3MEHUTESHFL37T/action/storage_attestation","attest_author":"https://pith.science/pith/W4ZRHNQZCJUG3MEHUTESHFL37T/action/author_attestation","sign_citation":"https://pith.science/pith/W4ZRHNQZCJUG3MEHUTESHFL37T/action/citation_signature","submit_replication":"https://pith.science/pith/W4ZRHNQZCJUG3MEHUTESHFL37T/action/replication_record"}},"created_at":"2026-07-05T00:02:41.308321+00:00","updated_at":"2026-07-05T00:02:41.308321+00:00"}