{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:VKBH2QTEZRPYJRQQ4NP4OOA5RQ","short_pith_number":"pith:VKBH2QTE","canonical_record":{"source":{"id":"1609.06082","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-20T10:23:47Z","cross_cats_sorted":[],"title_canon_sha256":"fb506734b67c979d6f3384ef53e9a84de6001ee9b7f66b3accf1def2c00e2259","abstract_canon_sha256":"8c1535381cc617895c0c03f051110017dcbc57db416d7efc775c3dfd62b5c02b"},"schema_version":"1.0"},"canonical_sha256":"aa827d4264cc5f84c610e35fc7381d8c22bc3d24fd00b87e2b2c88b7e4a42e5b","source":{"kind":"arxiv","id":"1609.06082","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.06082","created_at":"2026-05-18T01:04:16Z"},{"alias_kind":"arxiv_version","alias_value":"1609.06082v1","created_at":"2026-05-18T01:04:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.06082","created_at":"2026-05-18T01:04:16Z"},{"alias_kind":"pith_short_12","alias_value":"VKBH2QTEZRPY","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"VKBH2QTEZRPYJRQQ","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"VKBH2QTE","created_at":"2026-05-18T12:30:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:VKBH2QTEZRPYJRQQ4NP4OOA5RQ","target":"record","payload":{"canonical_record":{"source":{"id":"1609.06082","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-20T10:23:47Z","cross_cats_sorted":[],"title_canon_sha256":"fb506734b67c979d6f3384ef53e9a84de6001ee9b7f66b3accf1def2c00e2259","abstract_canon_sha256":"8c1535381cc617895c0c03f051110017dcbc57db416d7efc775c3dfd62b5c02b"},"schema_version":"1.0"},"canonical_sha256":"aa827d4264cc5f84c610e35fc7381d8c22bc3d24fd00b87e2b2c88b7e4a42e5b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:16.717873Z","signature_b64":"JMFF8mNno2aViWSFa0FbvswUb/5gyJPCQXxuDA6rmCSVtetyvONESFxqUjMRLDvPW0lu3r1NcLRqyC3r8D1IBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa827d4264cc5f84c610e35fc7381d8c22bc3d24fd00b87e2b2c88b7e4a42e5b","last_reissued_at":"2026-05-18T01:04:16.717477Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:16.717477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.06082","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":"2026-05-18T01:04:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ACZGfEokOjaCZgRctGCaKL2fRpUfVdEvGRnhhVi1TxrulM3VGtVsJAS9cgF4ccGGBym7zRUeNGeXHcx5/bz0AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T02:41:28.967682Z"},"content_sha256":"f6961edd2ecb3d6d7bc348dea119020e3d1c444e279497941fbde608ac8d4aae","schema_version":"1.0","event_id":"sha256:f6961edd2ecb3d6d7bc348dea119020e3d1c444e279497941fbde608ac8d4aae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:VKBH2QTEZRPYJRQQ4NP4OOA5RQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Robust Representations of Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Timothy Baldwin, Trevor Cohn, Yitong Li","submitted_at":"2016-09-20T10:23:47Z","abstract_excerpt":"Deep neural networks have achieved remarkable results across many language processing tasks, however these methods are highly sensitive to noise and adversarial attacks. We present a regularization based method for limiting network sensitivity to its inputs, inspired by ideas from computer vision, thus learning models that are more robust. Empirical evaluation over a range of sentiment datasets with a convolutional neural network shows that, compared to a baseline model and the dropout method, our method achieves superior performance over noisy inputs and out-of-domain data."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.06082","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":""},"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":"2026-05-18T01:04:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r5YT0AFoc4zDM/s1lQBlDIhW0uhAbY0cWMah8gFbl4PZKCHY5UcdKsK8LI+xZX66OQ/35Iaa/qXHSjz45vFcDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T02:41:28.968024Z"},"content_sha256":"30cac2ff595f5a541e96ff2de68e322ac970df1432bfcb93ac07ae4848c147d8","schema_version":"1.0","event_id":"sha256:30cac2ff595f5a541e96ff2de68e322ac970df1432bfcb93ac07ae4848c147d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VKBH2QTEZRPYJRQQ4NP4OOA5RQ/bundle.json","state_url":"https://pith.science/pith/VKBH2QTEZRPYJRQQ4NP4OOA5RQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VKBH2QTEZRPYJRQQ4NP4OOA5RQ/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":"2026-06-01T02:41:28Z","links":{"resolver":"https://pith.science/pith/VKBH2QTEZRPYJRQQ4NP4OOA5RQ","bundle":"https://pith.science/pith/VKBH2QTEZRPYJRQQ4NP4OOA5RQ/bundle.json","state":"https://pith.science/pith/VKBH2QTEZRPYJRQQ4NP4OOA5RQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VKBH2QTEZRPYJRQQ4NP4OOA5RQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:VKBH2QTEZRPYJRQQ4NP4OOA5RQ","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":"8c1535381cc617895c0c03f051110017dcbc57db416d7efc775c3dfd62b5c02b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-20T10:23:47Z","title_canon_sha256":"fb506734b67c979d6f3384ef53e9a84de6001ee9b7f66b3accf1def2c00e2259"},"schema_version":"1.0","source":{"id":"1609.06082","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.06082","created_at":"2026-05-18T01:04:16Z"},{"alias_kind":"arxiv_version","alias_value":"1609.06082v1","created_at":"2026-05-18T01:04:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.06082","created_at":"2026-05-18T01:04:16Z"},{"alias_kind":"pith_short_12","alias_value":"VKBH2QTEZRPY","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"VKBH2QTEZRPYJRQQ","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"VKBH2QTE","created_at":"2026-05-18T12:30:48Z"}],"graph_snapshots":[{"event_id":"sha256:30cac2ff595f5a541e96ff2de68e322ac970df1432bfcb93ac07ae4848c147d8","target":"graph","created_at":"2026-05-18T01:04:16Z","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":"Deep neural networks have achieved remarkable results across many language processing tasks, however these methods are highly sensitive to noise and adversarial attacks. We present a regularization based method for limiting network sensitivity to its inputs, inspired by ideas from computer vision, thus learning models that are more robust. Empirical evaluation over a range of sentiment datasets with a convolutional neural network shows that, compared to a baseline model and the dropout method, our method achieves superior performance over noisy inputs and out-of-domain data.","authors_text":"Timothy Baldwin, Trevor Cohn, Yitong Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-20T10:23:47Z","title":"Learning Robust Representations of Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.06082","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:f6961edd2ecb3d6d7bc348dea119020e3d1c444e279497941fbde608ac8d4aae","target":"record","created_at":"2026-05-18T01:04:16Z","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":"8c1535381cc617895c0c03f051110017dcbc57db416d7efc775c3dfd62b5c02b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-20T10:23:47Z","title_canon_sha256":"fb506734b67c979d6f3384ef53e9a84de6001ee9b7f66b3accf1def2c00e2259"},"schema_version":"1.0","source":{"id":"1609.06082","kind":"arxiv","version":1}},"canonical_sha256":"aa827d4264cc5f84c610e35fc7381d8c22bc3d24fd00b87e2b2c88b7e4a42e5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa827d4264cc5f84c610e35fc7381d8c22bc3d24fd00b87e2b2c88b7e4a42e5b","first_computed_at":"2026-05-18T01:04:16.717477Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:04:16.717477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JMFF8mNno2aViWSFa0FbvswUb/5gyJPCQXxuDA6rmCSVtetyvONESFxqUjMRLDvPW0lu3r1NcLRqyC3r8D1IBA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:04:16.717873Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.06082","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6961edd2ecb3d6d7bc348dea119020e3d1c444e279497941fbde608ac8d4aae","sha256:30cac2ff595f5a541e96ff2de68e322ac970df1432bfcb93ac07ae4848c147d8"],"state_sha256":"4b8938cb6a11c7d11d8e7cb12c487552a82a81e241e1ff8ab4919f2ebda02b25"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TzMD8Hx7NiqTsP52tE4DV3jJ2oApJoBNYlm63dlnCgLXjl7BRwTUFbH/6hkuOC+KNAoKGNqWswwI0ugD/94DCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T02:41:28.970033Z","bundle_sha256":"9606ee62e07a7b3bb1b93cb168a35cdfbebe4a93c2230cc07970ecf19cd54db1"}}