{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:UWDQYOJMGPOWLHYNAKKXM2FO6G","short_pith_number":"pith:UWDQYOJM","canonical_record":{"source":{"id":"1704.08381","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-26T23:53:34Z","cross_cats_sorted":[],"title_canon_sha256":"586c8062a264a429b372f7fe681bef61999c8394a579222a042f84c96aa26d71","abstract_canon_sha256":"19fb640ad6282206d4c91f0be769c069f122129570a02e39a9e49fb7cb0b858b"},"schema_version":"1.0"},"canonical_sha256":"a5870c392c33dd659f0d02957668aef182f8822cd4cd18306df9a9a82a488557","source":{"kind":"arxiv","id":"1704.08381","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.08381","created_at":"2026-05-18T00:37:52Z"},{"alias_kind":"arxiv_version","alias_value":"1704.08381v3","created_at":"2026-05-18T00:37:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.08381","created_at":"2026-05-18T00:37:52Z"},{"alias_kind":"pith_short_12","alias_value":"UWDQYOJMGPOW","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"UWDQYOJMGPOWLHYN","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"UWDQYOJM","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:UWDQYOJMGPOWLHYNAKKXM2FO6G","target":"record","payload":{"canonical_record":{"source":{"id":"1704.08381","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-26T23:53:34Z","cross_cats_sorted":[],"title_canon_sha256":"586c8062a264a429b372f7fe681bef61999c8394a579222a042f84c96aa26d71","abstract_canon_sha256":"19fb640ad6282206d4c91f0be769c069f122129570a02e39a9e49fb7cb0b858b"},"schema_version":"1.0"},"canonical_sha256":"a5870c392c33dd659f0d02957668aef182f8822cd4cd18306df9a9a82a488557","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:37:52.490358Z","signature_b64":"ulxYqIbfL5ahLADQbFz403/6uc/0zc/HlBDLTJqi6m7eeeDajDTw/Y3EEAjThg8gjl6neKuZ5Y6y+cLCDl5MAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5870c392c33dd659f0d02957668aef182f8822cd4cd18306df9a9a82a488557","last_reissued_at":"2026-05-18T00:37:52.489715Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:37:52.489715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.08381","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:37:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"05h8XkdrVD1Q7q7q7fLEHburgSy9SX6GEiq/KmcBibiXoqAbj6hx3dj6vOZjFZ5GdNQhQaXSUaVT930WC/xcAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T12:05:57.216746Z"},"content_sha256":"6d1330a6cd463643c150f45b128eaf551140b87a964fc62fde85dc83d7befacc","schema_version":"1.0","event_id":"sha256:6d1330a6cd463643c150f45b128eaf551140b87a964fc62fde85dc83d7befacc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:UWDQYOJMGPOWLHYNAKKXM2FO6G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural AMR: Sequence-to-Sequence Models for Parsing and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ioannis Konstas, Luke Zettlemoyer, Mark Yatskar, Srinivasan Iyer, Yejin Choi","submitted_at":"2017-04-26T23:53:34Z","abstract_excerpt":"Sequence-to-sequence models have shown strong performance across a broad range of applications. However, their application to parsing and generating text usingAbstract Meaning Representation (AMR)has been limited, due to the relatively limited amount of labeled data and the non-sequential nature of the AMR graphs. We present a novel training procedure that can lift this limitation using millions of unlabeled sentences and careful preprocessing of the AMR graphs. For AMR parsing, our model achieves competitive results of 62.1SMATCH, the current best score reported without significant use of ext"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.08381","kind":"arxiv","version":3},"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":"2026-05-18T00:37:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CPryH8JKcJSBV0dzLTfxbeGd6pbJZWgSiGRzGLK/8VKorA5yWCQr90UA4svhc1Z7kt97SZ6lik0axVaueuYoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T12:05:57.217094Z"},"content_sha256":"bb69447a60e7743242869ee5ef1dc1c7bbc0ecb9a08c5e77445aee0d1afda541","schema_version":"1.0","event_id":"sha256:bb69447a60e7743242869ee5ef1dc1c7bbc0ecb9a08c5e77445aee0d1afda541"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UWDQYOJMGPOWLHYNAKKXM2FO6G/bundle.json","state_url":"https://pith.science/pith/UWDQYOJMGPOWLHYNAKKXM2FO6G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UWDQYOJMGPOWLHYNAKKXM2FO6G/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":"2026-06-02T12:05:57Z","links":{"resolver":"https://pith.science/pith/UWDQYOJMGPOWLHYNAKKXM2FO6G","bundle":"https://pith.science/pith/UWDQYOJMGPOWLHYNAKKXM2FO6G/bundle.json","state":"https://pith.science/pith/UWDQYOJMGPOWLHYNAKKXM2FO6G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UWDQYOJMGPOWLHYNAKKXM2FO6G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:UWDQYOJMGPOWLHYNAKKXM2FO6G","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":"19fb640ad6282206d4c91f0be769c069f122129570a02e39a9e49fb7cb0b858b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-26T23:53:34Z","title_canon_sha256":"586c8062a264a429b372f7fe681bef61999c8394a579222a042f84c96aa26d71"},"schema_version":"1.0","source":{"id":"1704.08381","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.08381","created_at":"2026-05-18T00:37:52Z"},{"alias_kind":"arxiv_version","alias_value":"1704.08381v3","created_at":"2026-05-18T00:37:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.08381","created_at":"2026-05-18T00:37:52Z"},{"alias_kind":"pith_short_12","alias_value":"UWDQYOJMGPOW","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"UWDQYOJMGPOWLHYN","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"UWDQYOJM","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:bb69447a60e7743242869ee5ef1dc1c7bbc0ecb9a08c5e77445aee0d1afda541","target":"graph","created_at":"2026-05-18T00:37:52Z","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":"Sequence-to-sequence models have shown strong performance across a broad range of applications. However, their application to parsing and generating text usingAbstract Meaning Representation (AMR)has been limited, due to the relatively limited amount of labeled data and the non-sequential nature of the AMR graphs. We present a novel training procedure that can lift this limitation using millions of unlabeled sentences and careful preprocessing of the AMR graphs. For AMR parsing, our model achieves competitive results of 62.1SMATCH, the current best score reported without significant use of ext","authors_text":"Ioannis Konstas, Luke Zettlemoyer, Mark Yatskar, Srinivasan Iyer, Yejin Choi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-26T23:53:34Z","title":"Neural AMR: Sequence-to-Sequence Models for Parsing and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.08381","kind":"arxiv","version":3},"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":"sha256:6d1330a6cd463643c150f45b128eaf551140b87a964fc62fde85dc83d7befacc","target":"record","created_at":"2026-05-18T00:37:52Z","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":"19fb640ad6282206d4c91f0be769c069f122129570a02e39a9e49fb7cb0b858b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-26T23:53:34Z","title_canon_sha256":"586c8062a264a429b372f7fe681bef61999c8394a579222a042f84c96aa26d71"},"schema_version":"1.0","source":{"id":"1704.08381","kind":"arxiv","version":3}},"canonical_sha256":"a5870c392c33dd659f0d02957668aef182f8822cd4cd18306df9a9a82a488557","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5870c392c33dd659f0d02957668aef182f8822cd4cd18306df9a9a82a488557","first_computed_at":"2026-05-18T00:37:52.489715Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:37:52.489715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ulxYqIbfL5ahLADQbFz403/6uc/0zc/HlBDLTJqi6m7eeeDajDTw/Y3EEAjThg8gjl6neKuZ5Y6y+cLCDl5MAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:37:52.490358Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.08381","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d1330a6cd463643c150f45b128eaf551140b87a964fc62fde85dc83d7befacc","sha256:bb69447a60e7743242869ee5ef1dc1c7bbc0ecb9a08c5e77445aee0d1afda541"],"state_sha256":"4f07081db825d655c8fd6a0b894f85934af057fff12e7e4bfa12f0646a2e48c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZEDmTV/Y9C4N9WTlDWkNGfcH21bCk9Fyi88XRTNPZPl/nkiFyJZJ6MSNF2bN4BvumwFsCyGpzDLwpIkONRmtAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T12:05:57.219105Z","bundle_sha256":"b5da402800e4434b4aaaffb9bdd8aa2a3771aa37a9383809624981c2c04e335b"}}