{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:NN3DLJLVLEM6DH6ANCMBX3TFVV","short_pith_number":"pith:NN3DLJLV","canonical_record":{"source":{"id":"2106.00851","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-01T23:24:51Z","cross_cats_sorted":[],"title_canon_sha256":"46744cef0fbb2440a014802516ebb9eb3848a9c89e8c8c42d602ddcba5c0e93f","abstract_canon_sha256":"f02a034183dde50cdba2cfff4e91cf9a1085d02f10d96f0db975e1f029caf423"},"schema_version":"1.0"},"canonical_sha256":"6b7635a5755919e19fc068981bee65ad7b6bc014112daee06019958cfc329998","source":{"kind":"arxiv","id":"2106.00851","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.00851","created_at":"2026-07-05T02:45:40Z"},{"alias_kind":"arxiv_version","alias_value":"2106.00851v1","created_at":"2026-07-05T02:45:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00851","created_at":"2026-07-05T02:45:40Z"},{"alias_kind":"pith_short_12","alias_value":"NN3DLJLVLEM6","created_at":"2026-07-05T02:45:40Z"},{"alias_kind":"pith_short_16","alias_value":"NN3DLJLVLEM6DH6A","created_at":"2026-07-05T02:45:40Z"},{"alias_kind":"pith_short_8","alias_value":"NN3DLJLV","created_at":"2026-07-05T02:45:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:NN3DLJLVLEM6DH6ANCMBX3TFVV","target":"record","payload":{"canonical_record":{"source":{"id":"2106.00851","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-01T23:24:51Z","cross_cats_sorted":[],"title_canon_sha256":"46744cef0fbb2440a014802516ebb9eb3848a9c89e8c8c42d602ddcba5c0e93f","abstract_canon_sha256":"f02a034183dde50cdba2cfff4e91cf9a1085d02f10d96f0db975e1f029caf423"},"schema_version":"1.0"},"canonical_sha256":"6b7635a5755919e19fc068981bee65ad7b6bc014112daee06019958cfc329998","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:40.709329Z","signature_b64":"o+hSmdlp0yrW+wWX1yuetoCchvGmKW1xFlW5q9y07HjLC9OLsd1z9XO+PDqvZ/gEm9Z4UcUAKN6mL6u147B1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b7635a5755919e19fc068981bee65ad7b6bc014112daee06019958cfc329998","last_reissued_at":"2026-07-05T02:45:40.708719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:40.708719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.00851","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:45:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BmpxK2gHQ5myU/+0LnfCb43Ok+V0kqoxiWbFmwn4aJzmlWw0ZC0Dpq2FoK73H8FRJ5ZZHiabCpKK1Qj9SOjlCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:29:40.540687Z"},"content_sha256":"ed9419110ab3a7690f97ec60dcdb7d181f8bdcffd22f32d964900d98d384d9f2","schema_version":"1.0","event_id":"sha256:ed9419110ab3a7690f97ec60dcdb7d181f8bdcffd22f32d964900d98d384d9f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:NN3DLJLVLEM6DH6ANCMBX3TFVV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Parameter-Efficient Neural Question Answering Models via Graph-Enriched Document Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Louis Castricato, Stephen Fitz, Won Young Shin","submitted_at":"2021-06-01T23:24:51Z","abstract_excerpt":"As the computational footprint of modern NLP systems grows, it becomes increasingly important to arrive at more efficient models. We show that by employing graph convolutional document representation, we can arrive at a question answering system that performs comparably to, and in some cases exceeds the SOTA solutions, while using less than 5\\% of their resources in terms of trainable parameters. As it currently stands, a major issue in applying GCNs to NLP is document representation. In this paper, we show that a GCN enriched document representation greatly improves the results seen in HotPot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00851","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/2106.00851/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":"2026-07-05T02:45:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4U/JFAYqFdrm4045P3L2aRuObuoJdJSorxp327/F9PhrvKAO/e3hQ4/Z2WiRfzIfA83chulAz7v4gHOv/zBVBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:29:40.541054Z"},"content_sha256":"c0fb8ca30f4aaf89c985672f8e3f44949ac5a8e0cfa9f5be0a309d022440b823","schema_version":"1.0","event_id":"sha256:c0fb8ca30f4aaf89c985672f8e3f44949ac5a8e0cfa9f5be0a309d022440b823"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NN3DLJLVLEM6DH6ANCMBX3TFVV/bundle.json","state_url":"https://pith.science/pith/NN3DLJLVLEM6DH6ANCMBX3TFVV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NN3DLJLVLEM6DH6ANCMBX3TFVV/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":"2026-07-06T23:29:40Z","links":{"resolver":"https://pith.science/pith/NN3DLJLVLEM6DH6ANCMBX3TFVV","bundle":"https://pith.science/pith/NN3DLJLVLEM6DH6ANCMBX3TFVV/bundle.json","state":"https://pith.science/pith/NN3DLJLVLEM6DH6ANCMBX3TFVV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NN3DLJLVLEM6DH6ANCMBX3TFVV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NN3DLJLVLEM6DH6ANCMBX3TFVV","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":"f02a034183dde50cdba2cfff4e91cf9a1085d02f10d96f0db975e1f029caf423","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-01T23:24:51Z","title_canon_sha256":"46744cef0fbb2440a014802516ebb9eb3848a9c89e8c8c42d602ddcba5c0e93f"},"schema_version":"1.0","source":{"id":"2106.00851","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.00851","created_at":"2026-07-05T02:45:40Z"},{"alias_kind":"arxiv_version","alias_value":"2106.00851v1","created_at":"2026-07-05T02:45:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00851","created_at":"2026-07-05T02:45:40Z"},{"alias_kind":"pith_short_12","alias_value":"NN3DLJLVLEM6","created_at":"2026-07-05T02:45:40Z"},{"alias_kind":"pith_short_16","alias_value":"NN3DLJLVLEM6DH6A","created_at":"2026-07-05T02:45:40Z"},{"alias_kind":"pith_short_8","alias_value":"NN3DLJLV","created_at":"2026-07-05T02:45:40Z"}],"graph_snapshots":[{"event_id":"sha256:c0fb8ca30f4aaf89c985672f8e3f44949ac5a8e0cfa9f5be0a309d022440b823","target":"graph","created_at":"2026-07-05T02:45:40Z","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/2106.00851/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As the computational footprint of modern NLP systems grows, it becomes increasingly important to arrive at more efficient models. We show that by employing graph convolutional document representation, we can arrive at a question answering system that performs comparably to, and in some cases exceeds the SOTA solutions, while using less than 5\\% of their resources in terms of trainable parameters. As it currently stands, a major issue in applying GCNs to NLP is document representation. In this paper, we show that a GCN enriched document representation greatly improves the results seen in HotPot","authors_text":"Louis Castricato, Stephen Fitz, Won Young Shin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-01T23:24:51Z","title":"Parameter-Efficient Neural Question Answering Models via Graph-Enriched Document Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00851","kind":"arxiv","version":1},"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:ed9419110ab3a7690f97ec60dcdb7d181f8bdcffd22f32d964900d98d384d9f2","target":"record","created_at":"2026-07-05T02:45:40Z","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":"f02a034183dde50cdba2cfff4e91cf9a1085d02f10d96f0db975e1f029caf423","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-01T23:24:51Z","title_canon_sha256":"46744cef0fbb2440a014802516ebb9eb3848a9c89e8c8c42d602ddcba5c0e93f"},"schema_version":"1.0","source":{"id":"2106.00851","kind":"arxiv","version":1}},"canonical_sha256":"6b7635a5755919e19fc068981bee65ad7b6bc014112daee06019958cfc329998","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b7635a5755919e19fc068981bee65ad7b6bc014112daee06019958cfc329998","first_computed_at":"2026-07-05T02:45:40.708719Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:45:40.708719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o+hSmdlp0yrW+wWX1yuetoCchvGmKW1xFlW5q9y07HjLC9OLsd1z9XO+PDqvZ/gEm9Z4UcUAKN6mL6u147B1AA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:45:40.709329Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.00851","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed9419110ab3a7690f97ec60dcdb7d181f8bdcffd22f32d964900d98d384d9f2","sha256:c0fb8ca30f4aaf89c985672f8e3f44949ac5a8e0cfa9f5be0a309d022440b823"],"state_sha256":"32a28c02fe24220e5fbfc223996ce1389b24b9f6d8cb66d619f4ae963e9e8a18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V7z2OKt6UbxQRa57tZEKsNGYKr043jUsoqPDAs9guMKFY0Cabb1XGtK/GdUUI2SfNGRkW9PpNH4mpdxmS761DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:29:40.543086Z","bundle_sha256":"10af7ca5f2e95127d416bef8f71bb210f2942bc875705b6199941b1687751752"}}