{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:WQFTXJZKRZRSJO2MABUMGFVHMG","short_pith_number":"pith:WQFTXJZK","canonical_record":{"source":{"id":"1611.01436","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-04T16:12:46Z","cross_cats_sorted":[],"title_canon_sha256":"553d42c6bd6e14f30e11251e866e124200c3a10e3d6f8546da4c8daddbb44d5a","abstract_canon_sha256":"49525eea4b125efd661afbe4e0af5ea417eba9c9e9acc048cdc3965acf7726b2"},"schema_version":"1.0"},"canonical_sha256":"b40b3ba72a8e6324bb4c0068c316a761a91ef3364891aa4efa5b063d1d61be68","source":{"kind":"arxiv","id":"1611.01436","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01436","created_at":"2026-05-18T00:48:26Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01436v2","created_at":"2026-05-18T00:48:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01436","created_at":"2026-05-18T00:48:26Z"},{"alias_kind":"pith_short_12","alias_value":"WQFTXJZKRZRS","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"WQFTXJZKRZRSJO2M","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"WQFTXJZK","created_at":"2026-05-18T12:30:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:WQFTXJZKRZRSJO2MABUMGFVHMG","target":"record","payload":{"canonical_record":{"source":{"id":"1611.01436","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-04T16:12:46Z","cross_cats_sorted":[],"title_canon_sha256":"553d42c6bd6e14f30e11251e866e124200c3a10e3d6f8546da4c8daddbb44d5a","abstract_canon_sha256":"49525eea4b125efd661afbe4e0af5ea417eba9c9e9acc048cdc3965acf7726b2"},"schema_version":"1.0"},"canonical_sha256":"b40b3ba72a8e6324bb4c0068c316a761a91ef3364891aa4efa5b063d1d61be68","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:26.234565Z","signature_b64":"QKuf5sa31rLFPyfyNLfwMcsG3RA/F/N2d6yYyUG/i1ST6vHBIapzP/FMSV8k8M97WLefvy3ZU4ZL1/f7jAjoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b40b3ba72a8e6324bb4c0068c316a761a91ef3364891aa4efa5b063d1d61be68","last_reissued_at":"2026-05-18T00:48:26.233874Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:26.233874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.01436","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:48:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NLm2NPU6UvuRd+UmUb8LJTmVQEMxFU7PjVE3hfH2YSJWZUfeIcRTYJXjTJLphdeI0SeS7fN2mQzoknS9awhGAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T06:02:49.904291Z"},"content_sha256":"bfa5459520ee87b98ede05e37d359ad060bf59c25e42d00120dc3d44dc8b5cc9","schema_version":"1.0","event_id":"sha256:bfa5459520ee87b98ede05e37d359ad060bf59c25e42d00120dc3d44dc8b5cc9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:WQFTXJZKRZRSJO2MABUMGFVHMG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Recurrent Span Representations for Extractive Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ankur Parikh, Dipanjan Das, Jonathan Berant, Kenton Lee, Shimi Salant, Tom Kwiatkowski","submitted_at":"2016-11-04T16:12:46Z","abstract_excerpt":"The reading comprehension task, that asks questions about a given evidence document, is a central problem in natural language understanding. Recent formulations of this task have typically focused on answer selection from a set of candidates pre-defined manually or through the use of an external NLP pipeline. However, Rajpurkar et al. (2016) recently released the SQuAD dataset in which the answers can be arbitrary strings from the supplied text. In this paper, we focus on this answer extraction task, presenting a novel model architecture that efficiently builds fixed length representations of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01436","kind":"arxiv","version":2},"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":"2026-05-18T00:48:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9k1s7QU070QNj1Y/ZHIfvTBjGuNQjQhne7xuegHyfY0N8ZlU5pVwgmaVJtlKxcyfNZOyYQON9o/FqcMaQ9gOBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T06:02:49.904910Z"},"content_sha256":"be23e4728f41f168634364bc38fa3b3e9e2cbc1f90289a2286d7868420d1b306","schema_version":"1.0","event_id":"sha256:be23e4728f41f168634364bc38fa3b3e9e2cbc1f90289a2286d7868420d1b306"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WQFTXJZKRZRSJO2MABUMGFVHMG/bundle.json","state_url":"https://pith.science/pith/WQFTXJZKRZRSJO2MABUMGFVHMG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WQFTXJZKRZRSJO2MABUMGFVHMG/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":"2026-06-07T06:02:49Z","links":{"resolver":"https://pith.science/pith/WQFTXJZKRZRSJO2MABUMGFVHMG","bundle":"https://pith.science/pith/WQFTXJZKRZRSJO2MABUMGFVHMG/bundle.json","state":"https://pith.science/pith/WQFTXJZKRZRSJO2MABUMGFVHMG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WQFTXJZKRZRSJO2MABUMGFVHMG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:WQFTXJZKRZRSJO2MABUMGFVHMG","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":"49525eea4b125efd661afbe4e0af5ea417eba9c9e9acc048cdc3965acf7726b2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-04T16:12:46Z","title_canon_sha256":"553d42c6bd6e14f30e11251e866e124200c3a10e3d6f8546da4c8daddbb44d5a"},"schema_version":"1.0","source":{"id":"1611.01436","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01436","created_at":"2026-05-18T00:48:26Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01436v2","created_at":"2026-05-18T00:48:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01436","created_at":"2026-05-18T00:48:26Z"},{"alias_kind":"pith_short_12","alias_value":"WQFTXJZKRZRS","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"WQFTXJZKRZRSJO2M","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"WQFTXJZK","created_at":"2026-05-18T12:30:51Z"}],"graph_snapshots":[{"event_id":"sha256:be23e4728f41f168634364bc38fa3b3e9e2cbc1f90289a2286d7868420d1b306","target":"graph","created_at":"2026-05-18T00:48:26Z","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":"The reading comprehension task, that asks questions about a given evidence document, is a central problem in natural language understanding. Recent formulations of this task have typically focused on answer selection from a set of candidates pre-defined manually or through the use of an external NLP pipeline. However, Rajpurkar et al. (2016) recently released the SQuAD dataset in which the answers can be arbitrary strings from the supplied text. In this paper, we focus on this answer extraction task, presenting a novel model architecture that efficiently builds fixed length representations of ","authors_text":"Ankur Parikh, Dipanjan Das, Jonathan Berant, Kenton Lee, Shimi Salant, Tom Kwiatkowski","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-04T16:12:46Z","title":"Learning Recurrent Span Representations for Extractive Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01436","kind":"arxiv","version":2},"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:bfa5459520ee87b98ede05e37d359ad060bf59c25e42d00120dc3d44dc8b5cc9","target":"record","created_at":"2026-05-18T00:48:26Z","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":"49525eea4b125efd661afbe4e0af5ea417eba9c9e9acc048cdc3965acf7726b2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-04T16:12:46Z","title_canon_sha256":"553d42c6bd6e14f30e11251e866e124200c3a10e3d6f8546da4c8daddbb44d5a"},"schema_version":"1.0","source":{"id":"1611.01436","kind":"arxiv","version":2}},"canonical_sha256":"b40b3ba72a8e6324bb4c0068c316a761a91ef3364891aa4efa5b063d1d61be68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b40b3ba72a8e6324bb4c0068c316a761a91ef3364891aa4efa5b063d1d61be68","first_computed_at":"2026-05-18T00:48:26.233874Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:48:26.233874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QKuf5sa31rLFPyfyNLfwMcsG3RA/F/N2d6yYyUG/i1ST6vHBIapzP/FMSV8k8M97WLefvy3ZU4ZL1/f7jAjoDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:48:26.234565Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.01436","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfa5459520ee87b98ede05e37d359ad060bf59c25e42d00120dc3d44dc8b5cc9","sha256:be23e4728f41f168634364bc38fa3b3e9e2cbc1f90289a2286d7868420d1b306"],"state_sha256":"c729c5d13824be7d1145e1cec4fe49bd31436c36d0f71f1471beacee46c58e12"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/iSZUaq1AZEgVi6yffSlD7C3Smriw8aWaMWfvR73ZI965kY8GP2N7Re6CcnI3uYluXbO95EVV2e+B5ReYocmCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T06:02:49.908297Z","bundle_sha256":"c09cf2a8594c2bc51e4ebf8b7252a3634926acc6983f26e8f3877e84dbf22805"}}