{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:CEDZ6NOJX7HIMNOQ2HWQ2H4BFN","short_pith_number":"pith:CEDZ6NOJ","canonical_record":{"source":{"id":"1904.04733","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-09T15:33:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8298e472b9cec03d6cbfc1c20709b8254700243561ac9579b3d48a1ee773ab78","abstract_canon_sha256":"0d99d104065b7785d61c3b5c9263ce880e7fd50380913c3991c35b9eb4f35875"},"schema_version":"1.0"},"canonical_sha256":"11079f35c9bfce8635d0d1ed0d1f812b54f754c1d096bcba486e9652ebf0ad14","source":{"kind":"arxiv","id":"1904.04733","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04733","created_at":"2026-05-17T23:48:29Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04733v3","created_at":"2026-05-17T23:48:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04733","created_at":"2026-05-17T23:48:29Z"},{"alias_kind":"pith_short_12","alias_value":"CEDZ6NOJX7HI","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"CEDZ6NOJX7HIMNOQ","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"CEDZ6NOJ","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:CEDZ6NOJX7HIMNOQ2HWQ2H4BFN","target":"record","payload":{"canonical_record":{"source":{"id":"1904.04733","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-09T15:33:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8298e472b9cec03d6cbfc1c20709b8254700243561ac9579b3d48a1ee773ab78","abstract_canon_sha256":"0d99d104065b7785d61c3b5c9263ce880e7fd50380913c3991c35b9eb4f35875"},"schema_version":"1.0"},"canonical_sha256":"11079f35c9bfce8635d0d1ed0d1f812b54f754c1d096bcba486e9652ebf0ad14","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:29.403018Z","signature_b64":"CTBV/QkkhQ5KoeZ5ZVVl7O/3VVSin1HVOOb2X43blXKJtFluXzL+mkPEXpPf73QFzTJoB06D394BsqvoCm9+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11079f35c9bfce8635d0d1ed0d1f812b54f754c1d096bcba486e9652ebf0ad14","last_reissued_at":"2026-05-17T23:48:29.400239Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:29.400239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.04733","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":"2026-05-17T23:48:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4hb5TNJO/7+5TaAS1W0TLjSp+tiThVUgTSeb4U1KWD9T6s1+1gx3HaMKCyJ3CBK4andLxLbdCN7xjTpbWGKYDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T23:44:19.312145Z"},"content_sha256":"6142af44a3f194b55022dc958589d4b706581a9d1dfad8be9bc95d609229c45d","schema_version":"1.0","event_id":"sha256:6142af44a3f194b55022dc958589d4b706581a9d1dfad8be9bc95d609229c45d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:CEDZ6NOJX7HIMNOQ2HWQ2H4BFN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Seq2Biseq: Bidirectional Output-wise Recurrent Neural Networks for Sequence Modelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Lo\\\"ic Grobol, Marco Dinarelli","submitted_at":"2019-04-09T15:33:59Z","abstract_excerpt":"During the last couple of years, Recurrent Neural Networks (RNN) have reached state-of-the-art performances on most of the sequence modelling problems. In particular, the \"sequence to sequence\" model and the neural CRF have proved to be very effective in this domain. In this article, we propose a new RNN architecture for sequence labelling, leveraging gated recurrent layers to take arbitrarily long contexts into account, and using two decoders operating forward and backward. We compare several variants of the proposed solution and their performances to the state-of-the-art. Most of our results"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04733","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":"2026-05-17T23:48:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HebkiYfAgBjvJbnqAFM92ktrapiZaDFwsc41PIcnyKZpGUO3+6K+9NkhyItBjeUBEhz222uVCiXJrDOgEk3oAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T23:44:19.312510Z"},"content_sha256":"693ee68a9d99440532cea967544d76a258a1b5e3b4ea32cbb66ca7f09e96773c","schema_version":"1.0","event_id":"sha256:693ee68a9d99440532cea967544d76a258a1b5e3b4ea32cbb66ca7f09e96773c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CEDZ6NOJX7HIMNOQ2HWQ2H4BFN/bundle.json","state_url":"https://pith.science/pith/CEDZ6NOJX7HIMNOQ2HWQ2H4BFN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CEDZ6NOJX7HIMNOQ2HWQ2H4BFN/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":"2026-06-25T23:44:19Z","links":{"resolver":"https://pith.science/pith/CEDZ6NOJX7HIMNOQ2HWQ2H4BFN","bundle":"https://pith.science/pith/CEDZ6NOJX7HIMNOQ2HWQ2H4BFN/bundle.json","state":"https://pith.science/pith/CEDZ6NOJX7HIMNOQ2HWQ2H4BFN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CEDZ6NOJX7HIMNOQ2HWQ2H4BFN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:CEDZ6NOJX7HIMNOQ2HWQ2H4BFN","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":"0d99d104065b7785d61c3b5c9263ce880e7fd50380913c3991c35b9eb4f35875","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-09T15:33:59Z","title_canon_sha256":"8298e472b9cec03d6cbfc1c20709b8254700243561ac9579b3d48a1ee773ab78"},"schema_version":"1.0","source":{"id":"1904.04733","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04733","created_at":"2026-05-17T23:48:29Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04733v3","created_at":"2026-05-17T23:48:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04733","created_at":"2026-05-17T23:48:29Z"},{"alias_kind":"pith_short_12","alias_value":"CEDZ6NOJX7HI","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"CEDZ6NOJX7HIMNOQ","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"CEDZ6NOJ","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:693ee68a9d99440532cea967544d76a258a1b5e3b4ea32cbb66ca7f09e96773c","target":"graph","created_at":"2026-05-17T23:48:29Z","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":"During the last couple of years, Recurrent Neural Networks (RNN) have reached state-of-the-art performances on most of the sequence modelling problems. In particular, the \"sequence to sequence\" model and the neural CRF have proved to be very effective in this domain. In this article, we propose a new RNN architecture for sequence labelling, leveraging gated recurrent layers to take arbitrarily long contexts into account, and using two decoders operating forward and backward. We compare several variants of the proposed solution and their performances to the state-of-the-art. Most of our results","authors_text":"Lo\\\"ic Grobol, Marco Dinarelli","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-09T15:33:59Z","title":"Seq2Biseq: Bidirectional Output-wise Recurrent Neural Networks for Sequence Modelling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04733","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":"sha256:6142af44a3f194b55022dc958589d4b706581a9d1dfad8be9bc95d609229c45d","target":"record","created_at":"2026-05-17T23:48:29Z","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":"0d99d104065b7785d61c3b5c9263ce880e7fd50380913c3991c35b9eb4f35875","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-09T15:33:59Z","title_canon_sha256":"8298e472b9cec03d6cbfc1c20709b8254700243561ac9579b3d48a1ee773ab78"},"schema_version":"1.0","source":{"id":"1904.04733","kind":"arxiv","version":3}},"canonical_sha256":"11079f35c9bfce8635d0d1ed0d1f812b54f754c1d096bcba486e9652ebf0ad14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11079f35c9bfce8635d0d1ed0d1f812b54f754c1d096bcba486e9652ebf0ad14","first_computed_at":"2026-05-17T23:48:29.400239Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:29.400239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CTBV/QkkhQ5KoeZ5ZVVl7O/3VVSin1HVOOb2X43blXKJtFluXzL+mkPEXpPf73QFzTJoB06D394BsqvoCm9+CA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:29.403018Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.04733","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6142af44a3f194b55022dc958589d4b706581a9d1dfad8be9bc95d609229c45d","sha256:693ee68a9d99440532cea967544d76a258a1b5e3b4ea32cbb66ca7f09e96773c"],"state_sha256":"82c744879cc78c51fdde654710e310613bef15957752fa1d033d0b8d68a7e110"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qr5vhen8WLc4Qq80ZBbZ4Her6bk1bTEAjKzrkbMixwGDrM4TH3mqowo4DBiPRWMyaiUhAsgCYMYdW2Wd/s51Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T23:44:19.314629Z","bundle_sha256":"b79f3adf9136dc4b45e8b7b966e8456bf0d0974443eb07cf13faf55cd8096573"}}