{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:FJAYYQX2DEOJAJVG6MCS2ZMTB2","short_pith_number":"pith:FJAYYQX2","canonical_record":{"source":{"id":"1607.02467","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-07-08T17:35:51Z","cross_cats_sorted":["cs.CL","cs.LG","cs.NE"],"title_canon_sha256":"b510e5a5c08b57b87d9469b18cb7d7904551fef64eaa64e48361b43c6766e2d2","abstract_canon_sha256":"a5059a46977518e196e5f848fc27cf061129f9b263aa244360ffc61e24d73cf8"},"schema_version":"1.0"},"canonical_sha256":"2a418c42fa191c9026a6f3052d65930e8da606054171e7b956f343ef33d465a0","source":{"kind":"arxiv","id":"1607.02467","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.02467","created_at":"2026-05-18T00:54:52Z"},{"alias_kind":"arxiv_version","alias_value":"1607.02467v2","created_at":"2026-05-18T00:54:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.02467","created_at":"2026-05-18T00:54:52Z"},{"alias_kind":"pith_short_12","alias_value":"FJAYYQX2DEOJ","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"FJAYYQX2DEOJAJVG","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"FJAYYQX2","created_at":"2026-05-18T12:30:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:FJAYYQX2DEOJAJVG6MCS2ZMTB2","target":"record","payload":{"canonical_record":{"source":{"id":"1607.02467","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-07-08T17:35:51Z","cross_cats_sorted":["cs.CL","cs.LG","cs.NE"],"title_canon_sha256":"b510e5a5c08b57b87d9469b18cb7d7904551fef64eaa64e48361b43c6766e2d2","abstract_canon_sha256":"a5059a46977518e196e5f848fc27cf061129f9b263aa244360ffc61e24d73cf8"},"schema_version":"1.0"},"canonical_sha256":"2a418c42fa191c9026a6f3052d65930e8da606054171e7b956f343ef33d465a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:54:52.740126Z","signature_b64":"fAi2GR6/6gOlD5/1w0OACVzJwxq+VpJBiB5dIjU3GHACQUI7nbORY5KghXSYYo8UXJWqqDfchH3zwPKXK7LYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a418c42fa191c9026a6f3052d65930e8da606054171e7b956f343ef33d465a0","last_reissued_at":"2026-05-18T00:54:52.739733Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:54:52.739733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1607.02467","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:54:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9iVRviYUQ96x0IJb6GESd8h65xQZEQbiQ4rQA3b02/DI3xrn2diOeI8+lqogrQ1w9r+DkgB9gJI3uihr0C2PBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T11:05:39.171962Z"},"content_sha256":"efc93744491598dd88f1ea8b10e971aeeaae495a0837ab6722e878e6dfbb2a58","schema_version":"1.0","event_id":"sha256:efc93744491598dd88f1ea8b10e971aeeaae495a0837ab6722e878e6dfbb2a58"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:FJAYYQX2DEOJAJVG6MCS2ZMTB2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Log-Linear RNNs: Towards Recurrent Neural Networks with Flexible Prior Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.NE"],"primary_cat":"cs.AI","authors_text":"Chunyang Xiao, Marc Dymetman","submitted_at":"2016-07-08T17:35:51Z","abstract_excerpt":"We introduce LL-RNNs (Log-Linear RNNs), an extension of Recurrent Neural Networks that replaces the softmax output layer by a log-linear output layer, of which the softmax is a special case. This conceptually simple move has two main advantages. First, it allows the learner to combat training data sparsity by allowing it to model words (or more generally, output symbols) as complex combinations of attributes without requiring that each combination is directly observed in the training data (as the softmax does). Second, it permits the inclusion of flexible prior knowledge in the form of a prior"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.02467","kind":"arxiv","version":2},"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":"2026-05-18T00:54:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZSqT2LnLRsfjmoR4J6orf7thOFSt4O3ADhNAADHWixfmazeuYvnuc+/nfxMsvh0cOx1qI9qLpo9G1FtZUyXYCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T11:05:39.172334Z"},"content_sha256":"3e94fec33927f2e2769f870822c27d8f2d71867e1596aaa3b82e752777c4697e","schema_version":"1.0","event_id":"sha256:3e94fec33927f2e2769f870822c27d8f2d71867e1596aaa3b82e752777c4697e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FJAYYQX2DEOJAJVG6MCS2ZMTB2/bundle.json","state_url":"https://pith.science/pith/FJAYYQX2DEOJAJVG6MCS2ZMTB2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FJAYYQX2DEOJAJVG6MCS2ZMTB2/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":"2026-05-28T11:05:39Z","links":{"resolver":"https://pith.science/pith/FJAYYQX2DEOJAJVG6MCS2ZMTB2","bundle":"https://pith.science/pith/FJAYYQX2DEOJAJVG6MCS2ZMTB2/bundle.json","state":"https://pith.science/pith/FJAYYQX2DEOJAJVG6MCS2ZMTB2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FJAYYQX2DEOJAJVG6MCS2ZMTB2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:FJAYYQX2DEOJAJVG6MCS2ZMTB2","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":"a5059a46977518e196e5f848fc27cf061129f9b263aa244360ffc61e24d73cf8","cross_cats_sorted":["cs.CL","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-07-08T17:35:51Z","title_canon_sha256":"b510e5a5c08b57b87d9469b18cb7d7904551fef64eaa64e48361b43c6766e2d2"},"schema_version":"1.0","source":{"id":"1607.02467","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.02467","created_at":"2026-05-18T00:54:52Z"},{"alias_kind":"arxiv_version","alias_value":"1607.02467v2","created_at":"2026-05-18T00:54:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.02467","created_at":"2026-05-18T00:54:52Z"},{"alias_kind":"pith_short_12","alias_value":"FJAYYQX2DEOJ","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"FJAYYQX2DEOJAJVG","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"FJAYYQX2","created_at":"2026-05-18T12:30:15Z"}],"graph_snapshots":[{"event_id":"sha256:3e94fec33927f2e2769f870822c27d8f2d71867e1596aaa3b82e752777c4697e","target":"graph","created_at":"2026-05-18T00:54:52Z","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":"We introduce LL-RNNs (Log-Linear RNNs), an extension of Recurrent Neural Networks that replaces the softmax output layer by a log-linear output layer, of which the softmax is a special case. This conceptually simple move has two main advantages. First, it allows the learner to combat training data sparsity by allowing it to model words (or more generally, output symbols) as complex combinations of attributes without requiring that each combination is directly observed in the training data (as the softmax does). Second, it permits the inclusion of flexible prior knowledge in the form of a prior","authors_text":"Chunyang Xiao, Marc Dymetman","cross_cats":["cs.CL","cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-07-08T17:35:51Z","title":"Log-Linear RNNs: Towards Recurrent Neural Networks with Flexible Prior Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.02467","kind":"arxiv","version":2},"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:efc93744491598dd88f1ea8b10e971aeeaae495a0837ab6722e878e6dfbb2a58","target":"record","created_at":"2026-05-18T00:54:52Z","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":"a5059a46977518e196e5f848fc27cf061129f9b263aa244360ffc61e24d73cf8","cross_cats_sorted":["cs.CL","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-07-08T17:35:51Z","title_canon_sha256":"b510e5a5c08b57b87d9469b18cb7d7904551fef64eaa64e48361b43c6766e2d2"},"schema_version":"1.0","source":{"id":"1607.02467","kind":"arxiv","version":2}},"canonical_sha256":"2a418c42fa191c9026a6f3052d65930e8da606054171e7b956f343ef33d465a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a418c42fa191c9026a6f3052d65930e8da606054171e7b956f343ef33d465a0","first_computed_at":"2026-05-18T00:54:52.739733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:54:52.739733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fAi2GR6/6gOlD5/1w0OACVzJwxq+VpJBiB5dIjU3GHACQUI7nbORY5KghXSYYo8UXJWqqDfchH3zwPKXK7LYDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:54:52.740126Z","signed_message":"canonical_sha256_bytes"},"source_id":"1607.02467","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efc93744491598dd88f1ea8b10e971aeeaae495a0837ab6722e878e6dfbb2a58","sha256:3e94fec33927f2e2769f870822c27d8f2d71867e1596aaa3b82e752777c4697e"],"state_sha256":"96b4cb5bc9d330c4e1dab15fa740b6a6fbbfcabb94f0c462dd3327b0ac46dd29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3P5nu+aVwHciO0eAkcIZqtv8ij+EVBGQMI0YNQSbyu4gP5aLyUd7i3Jm/k8euxDTlwTGfE/aO9RjO9YeOZczBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T11:05:39.174264Z","bundle_sha256":"5d19e8060c6b8c0095d6593545b05e2f95e4957963efbb4f854bf90dcb4e4b8c"}}