{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:SEVMLXZZT5D6FSH3L6KNOKN3OR","short_pith_number":"pith:SEVMLXZZ","canonical_record":{"source":{"id":"1601.01272","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-01-06T18:44:07Z","cross_cats_sorted":[],"title_canon_sha256":"86a630a4e10ea547c37e5a32d1c6e1a86b315e633ab7d7962ae9257511b72b53","abstract_canon_sha256":"0ef6f341fa46e5ea7c32d4f90a89f398c54ff6d6e051c868568028fad5b5c973"},"schema_version":"1.0"},"canonical_sha256":"912ac5df399f47e2c8fb5f94d729bb7444b52f42db5c45acd9fa0c5b05307229","source":{"kind":"arxiv","id":"1601.01272","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1601.01272","created_at":"2026-05-18T01:16:29Z"},{"alias_kind":"arxiv_version","alias_value":"1601.01272v2","created_at":"2026-05-18T01:16:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.01272","created_at":"2026-05-18T01:16:29Z"},{"alias_kind":"pith_short_12","alias_value":"SEVMLXZZT5D6","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"SEVMLXZZT5D6FSH3","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"SEVMLXZZ","created_at":"2026-05-18T12:30:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:SEVMLXZZT5D6FSH3L6KNOKN3OR","target":"record","payload":{"canonical_record":{"source":{"id":"1601.01272","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-01-06T18:44:07Z","cross_cats_sorted":[],"title_canon_sha256":"86a630a4e10ea547c37e5a32d1c6e1a86b315e633ab7d7962ae9257511b72b53","abstract_canon_sha256":"0ef6f341fa46e5ea7c32d4f90a89f398c54ff6d6e051c868568028fad5b5c973"},"schema_version":"1.0"},"canonical_sha256":"912ac5df399f47e2c8fb5f94d729bb7444b52f42db5c45acd9fa0c5b05307229","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:29.323431Z","signature_b64":"1GXGZkOUrXqXAQbuJ8YD52y/ALEcfIH0sJtiIuDwsFtL6tWR7BGMrVQC7SGYoyJQo7ng7ofZfTAE1irbjLJ4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"912ac5df399f47e2c8fb5f94d729bb7444b52f42db5c45acd9fa0c5b05307229","last_reissued_at":"2026-05-18T01:16:29.322907Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:29.322907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1601.01272","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":"2026-05-18T01:16:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LMRFM9CWEBqm74H96alp4XqFUmrna/svmN0D3oibAOIjjizqN3QFNMMLB6p9jwehlk9kUvQqhwhGWHOf8mogCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:42:46.705064Z"},"content_sha256":"db74f74e05446b5b3359f3a8bf936a8d59d393c783da7214e793c0bcd14b5794","schema_version":"1.0","event_id":"sha256:db74f74e05446b5b3359f3a8bf936a8d59d393c783da7214e793c0bcd14b5794"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:SEVMLXZZT5D6FSH3L6KNOKN3OR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recurrent Memory Networks for Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arianna Bisazza, Christof Monz, Ke Tran","submitted_at":"2016-01-06T18:44:07Z","abstract_excerpt":"Recurrent Neural Networks (RNN) have obtained excellent result in many natural language processing (NLP) tasks. However, understanding and interpreting the source of this success remains a challenge. In this paper, we propose Recurrent Memory Network (RMN), a novel RNN architecture, that not only amplifies the power of RNN but also facilitates our understanding of its internal functioning and allows us to discover underlying patterns in data. We demonstrate the power of RMN on language modeling and sentence completion tasks. On language modeling, RMN outperforms Long Short-Term Memory (LSTM) n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.01272","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":"2026-05-18T01:16:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0CFLWTnpwLjqfYMLHP7q1dVRrvMafQHXuPd0NR9fv9yHyrItnBjyZvhWWXW8g5npL0yeu9vclPaZikXbOUdqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:42:46.706331Z"},"content_sha256":"0338d816fe653b6595693cdd9c45fa30c0f5ff862259d6ef546a9f423253f9aa","schema_version":"1.0","event_id":"sha256:0338d816fe653b6595693cdd9c45fa30c0f5ff862259d6ef546a9f423253f9aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SEVMLXZZT5D6FSH3L6KNOKN3OR/bundle.json","state_url":"https://pith.science/pith/SEVMLXZZT5D6FSH3L6KNOKN3OR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SEVMLXZZT5D6FSH3L6KNOKN3OR/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":"2026-05-25T17:42:46Z","links":{"resolver":"https://pith.science/pith/SEVMLXZZT5D6FSH3L6KNOKN3OR","bundle":"https://pith.science/pith/SEVMLXZZT5D6FSH3L6KNOKN3OR/bundle.json","state":"https://pith.science/pith/SEVMLXZZT5D6FSH3L6KNOKN3OR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SEVMLXZZT5D6FSH3L6KNOKN3OR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:SEVMLXZZT5D6FSH3L6KNOKN3OR","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":"0ef6f341fa46e5ea7c32d4f90a89f398c54ff6d6e051c868568028fad5b5c973","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-01-06T18:44:07Z","title_canon_sha256":"86a630a4e10ea547c37e5a32d1c6e1a86b315e633ab7d7962ae9257511b72b53"},"schema_version":"1.0","source":{"id":"1601.01272","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1601.01272","created_at":"2026-05-18T01:16:29Z"},{"alias_kind":"arxiv_version","alias_value":"1601.01272v2","created_at":"2026-05-18T01:16:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.01272","created_at":"2026-05-18T01:16:29Z"},{"alias_kind":"pith_short_12","alias_value":"SEVMLXZZT5D6","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"SEVMLXZZT5D6FSH3","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"SEVMLXZZ","created_at":"2026-05-18T12:30:44Z"}],"graph_snapshots":[{"event_id":"sha256:0338d816fe653b6595693cdd9c45fa30c0f5ff862259d6ef546a9f423253f9aa","target":"graph","created_at":"2026-05-18T01:16:29Z","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":"Recurrent Neural Networks (RNN) have obtained excellent result in many natural language processing (NLP) tasks. However, understanding and interpreting the source of this success remains a challenge. In this paper, we propose Recurrent Memory Network (RMN), a novel RNN architecture, that not only amplifies the power of RNN but also facilitates our understanding of its internal functioning and allows us to discover underlying patterns in data. We demonstrate the power of RMN on language modeling and sentence completion tasks. On language modeling, RMN outperforms Long Short-Term Memory (LSTM) n","authors_text":"Arianna Bisazza, Christof Monz, Ke Tran","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-01-06T18:44:07Z","title":"Recurrent Memory Networks for Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.01272","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:db74f74e05446b5b3359f3a8bf936a8d59d393c783da7214e793c0bcd14b5794","target":"record","created_at":"2026-05-18T01:16:29Z","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":"0ef6f341fa46e5ea7c32d4f90a89f398c54ff6d6e051c868568028fad5b5c973","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-01-06T18:44:07Z","title_canon_sha256":"86a630a4e10ea547c37e5a32d1c6e1a86b315e633ab7d7962ae9257511b72b53"},"schema_version":"1.0","source":{"id":"1601.01272","kind":"arxiv","version":2}},"canonical_sha256":"912ac5df399f47e2c8fb5f94d729bb7444b52f42db5c45acd9fa0c5b05307229","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"912ac5df399f47e2c8fb5f94d729bb7444b52f42db5c45acd9fa0c5b05307229","first_computed_at":"2026-05-18T01:16:29.322907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:16:29.322907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1GXGZkOUrXqXAQbuJ8YD52y/ALEcfIH0sJtiIuDwsFtL6tWR7BGMrVQC7SGYoyJQo7ng7ofZfTAE1irbjLJ4Cw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:16:29.323431Z","signed_message":"canonical_sha256_bytes"},"source_id":"1601.01272","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db74f74e05446b5b3359f3a8bf936a8d59d393c783da7214e793c0bcd14b5794","sha256:0338d816fe653b6595693cdd9c45fa30c0f5ff862259d6ef546a9f423253f9aa"],"state_sha256":"a6fc79334be56593c4f84ad6b6c00ac5b45ae00c63f3d95e5035de02b5d54c69"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OuajyO0qPRMjdt8e2IjfQ97Qcjjf2XclMaQ6+cK+QFKOzeQjtSLynnVCc2PRUU6PLd/G7/qHjypSPuKepj/dDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T17:42:46.709630Z","bundle_sha256":"26d76bf8fb13ed210d02e9eb87bd8fb50a28a8c494cda73efd61de7f9c5100c7"}}