{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LSQ5SI6HUHOSRGEOXTU4FOASDY","short_pith_number":"pith:LSQ5SI6H","canonical_record":{"source":{"id":"1808.09367","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T15:38:41Z","cross_cats_sorted":[],"title_canon_sha256":"2bd806b656cca7f9309612da8b943dbf2aa28e4b95d00421248848ed41c4a214","abstract_canon_sha256":"414efee6495118b2d550685a79e497af39f706174103dc822d98f70a235e6679"},"schema_version":"1.0"},"canonical_sha256":"5ca1d923c7a1dd28988ebce9c2b8121e21fd19887c2d2b77eaedb7bcbee003ed","source":{"kind":"arxiv","id":"1808.09367","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.09367","created_at":"2026-05-18T00:07:01Z"},{"alias_kind":"arxiv_version","alias_value":"1808.09367v1","created_at":"2026-05-18T00:07:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09367","created_at":"2026-05-18T00:07:01Z"},{"alias_kind":"pith_short_12","alias_value":"LSQ5SI6HUHOS","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LSQ5SI6HUHOSRGEO","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LSQ5SI6H","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LSQ5SI6HUHOSRGEOXTU4FOASDY","target":"record","payload":{"canonical_record":{"source":{"id":"1808.09367","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T15:38:41Z","cross_cats_sorted":[],"title_canon_sha256":"2bd806b656cca7f9309612da8b943dbf2aa28e4b95d00421248848ed41c4a214","abstract_canon_sha256":"414efee6495118b2d550685a79e497af39f706174103dc822d98f70a235e6679"},"schema_version":"1.0"},"canonical_sha256":"5ca1d923c7a1dd28988ebce9c2b8121e21fd19887c2d2b77eaedb7bcbee003ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:01.572893Z","signature_b64":"NaQb8ZQA9oTv1U+6mxdF2Q8Eg1sev2GVZTs2kw7HnnNxiGui5ghVd8bvPvCZDbPNGUa6rVMUfkVRBJE8n2UPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ca1d923c7a1dd28988ebce9c2b8121e21fd19887c2d2b77eaedb7bcbee003ed","last_reissued_at":"2026-05-18T00:07:01.572214Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:01.572214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.09367","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":"2026-05-18T00:07:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zQYq0jQkOs+8IBwApNYBrv9EQ6pmBsrzV6zNzsbLyLVY5i5dbOKRJzz9Za9Tx4P449zWHg5vJDI9PXcc1OauAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T12:03:54.297292Z"},"content_sha256":"02946a7188473c83c9a654e2adbe994272f56935d2cddfe043b3d8cc22e2631a","schema_version":"1.0","event_id":"sha256:02946a7188473c83c9a654e2adbe994272f56935d2cddfe043b3d8cc22e2631a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LSQ5SI6HUHOSRGEOXTU4FOASDY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deriving Machine Attention from Human Rationales","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mo Yu, Regina Barzilay, Shiyu Chang, Yujia Bao","submitted_at":"2018-08-28T15:38:41Z","abstract_excerpt":"Attention-based models are successful when trained on large amounts of data. In this paper, we demonstrate that even in the low-resource scenario, attention can be learned effectively. To this end, we start with discrete human-annotated rationales and map them into continuous attention. Our central hypothesis is that this mapping is general across domains, and thus can be transferred from resource-rich domains to low-resource ones. Our model jointly learns a domain-invariant representation and induces the desired mapping between rationales and attention. Our empirical results validate this hyp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09367","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":"2026-05-18T00:07:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RdRxQDJdrMWptxByUyCTtN/mgvvhIRKwwWspfNQ7OgLasBqj8MllwfyKFQSXZLCjmokvscF7AzjxqAOPLtwZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T12:03:54.297643Z"},"content_sha256":"0790aa182aee939a78145bb59dc1213f2c9dca0593d784a9c82ec209f11f2cf3","schema_version":"1.0","event_id":"sha256:0790aa182aee939a78145bb59dc1213f2c9dca0593d784a9c82ec209f11f2cf3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LSQ5SI6HUHOSRGEOXTU4FOASDY/bundle.json","state_url":"https://pith.science/pith/LSQ5SI6HUHOSRGEOXTU4FOASDY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LSQ5SI6HUHOSRGEOXTU4FOASDY/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":"2026-06-02T12:03:54Z","links":{"resolver":"https://pith.science/pith/LSQ5SI6HUHOSRGEOXTU4FOASDY","bundle":"https://pith.science/pith/LSQ5SI6HUHOSRGEOXTU4FOASDY/bundle.json","state":"https://pith.science/pith/LSQ5SI6HUHOSRGEOXTU4FOASDY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LSQ5SI6HUHOSRGEOXTU4FOASDY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LSQ5SI6HUHOSRGEOXTU4FOASDY","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":"414efee6495118b2d550685a79e497af39f706174103dc822d98f70a235e6679","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T15:38:41Z","title_canon_sha256":"2bd806b656cca7f9309612da8b943dbf2aa28e4b95d00421248848ed41c4a214"},"schema_version":"1.0","source":{"id":"1808.09367","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.09367","created_at":"2026-05-18T00:07:01Z"},{"alias_kind":"arxiv_version","alias_value":"1808.09367v1","created_at":"2026-05-18T00:07:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09367","created_at":"2026-05-18T00:07:01Z"},{"alias_kind":"pith_short_12","alias_value":"LSQ5SI6HUHOS","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LSQ5SI6HUHOSRGEO","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LSQ5SI6H","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:0790aa182aee939a78145bb59dc1213f2c9dca0593d784a9c82ec209f11f2cf3","target":"graph","created_at":"2026-05-18T00:07:01Z","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":"Attention-based models are successful when trained on large amounts of data. In this paper, we demonstrate that even in the low-resource scenario, attention can be learned effectively. To this end, we start with discrete human-annotated rationales and map them into continuous attention. Our central hypothesis is that this mapping is general across domains, and thus can be transferred from resource-rich domains to low-resource ones. Our model jointly learns a domain-invariant representation and induces the desired mapping between rationales and attention. Our empirical results validate this hyp","authors_text":"Mo Yu, Regina Barzilay, Shiyu Chang, Yujia Bao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T15:38:41Z","title":"Deriving Machine Attention from Human Rationales"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09367","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":"sha256:02946a7188473c83c9a654e2adbe994272f56935d2cddfe043b3d8cc22e2631a","target":"record","created_at":"2026-05-18T00:07:01Z","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":"414efee6495118b2d550685a79e497af39f706174103dc822d98f70a235e6679","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T15:38:41Z","title_canon_sha256":"2bd806b656cca7f9309612da8b943dbf2aa28e4b95d00421248848ed41c4a214"},"schema_version":"1.0","source":{"id":"1808.09367","kind":"arxiv","version":1}},"canonical_sha256":"5ca1d923c7a1dd28988ebce9c2b8121e21fd19887c2d2b77eaedb7bcbee003ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ca1d923c7a1dd28988ebce9c2b8121e21fd19887c2d2b77eaedb7bcbee003ed","first_computed_at":"2026-05-18T00:07:01.572214Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:01.572214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NaQb8ZQA9oTv1U+6mxdF2Q8Eg1sev2GVZTs2kw7HnnNxiGui5ghVd8bvPvCZDbPNGUa6rVMUfkVRBJE8n2UPCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:01.572893Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.09367","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02946a7188473c83c9a654e2adbe994272f56935d2cddfe043b3d8cc22e2631a","sha256:0790aa182aee939a78145bb59dc1213f2c9dca0593d784a9c82ec209f11f2cf3"],"state_sha256":"bf879a5824a746cbec16fb3ffc9edf100e328b43feb0b0e23f08b8c573a94544"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XBh63L98M83NRul2j83yR4DHQMdYng1PQugYMaR8C518/Z1h+/Ci/CefMFBntoFooiudaHzFACBJ21qSc8ujCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T12:03:54.299469Z","bundle_sha256":"aeba33d75a37390b21773e6546113e291fcfa2b087e3702e583c475edde57591"}}