{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:I6RKKPERQ2UMZUKGD43XLSUNNB","short_pith_number":"pith:I6RKKPER","canonical_record":{"source":{"id":"1707.00762","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-03T21:16:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0a37b476e71a2e59333b772ace9a9925b3396aa3987fad5741ecad91921fa39b","abstract_canon_sha256":"0b75383b15494a7c8d2d5de0fad47c8b25fcf9831214d49b31b251eaa387555e"},"schema_version":"1.0"},"canonical_sha256":"47a2a53c9186a8ccd1461f3775ca8d685468e990fd4c730be37784d118515585","source":{"kind":"arxiv","id":"1707.00762","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.00762","created_at":"2026-05-18T00:40:52Z"},{"alias_kind":"arxiv_version","alias_value":"1707.00762v2","created_at":"2026-05-18T00:40:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.00762","created_at":"2026-05-18T00:40:52Z"},{"alias_kind":"pith_short_12","alias_value":"I6RKKPERQ2UM","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"I6RKKPERQ2UMZUKG","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"I6RKKPER","created_at":"2026-05-18T12:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:I6RKKPERQ2UMZUKGD43XLSUNNB","target":"record","payload":{"canonical_record":{"source":{"id":"1707.00762","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-03T21:16:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0a37b476e71a2e59333b772ace9a9925b3396aa3987fad5741ecad91921fa39b","abstract_canon_sha256":"0b75383b15494a7c8d2d5de0fad47c8b25fcf9831214d49b31b251eaa387555e"},"schema_version":"1.0"},"canonical_sha256":"47a2a53c9186a8ccd1461f3775ca8d685468e990fd4c730be37784d118515585","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:52.535293Z","signature_b64":"3+Pb9FCBqnyt1Na6P/l1e3gCjrnnDF3uQbEEm4oveNJ9wTvB+Dx7qaCyz70MGrprorIje7i5+gGd5FhNbUg1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47a2a53c9186a8ccd1461f3775ca8d685468e990fd4c730be37784d118515585","last_reissued_at":"2026-05-18T00:40:52.534671Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:52.534671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.00762","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":"2026-05-18T00:40:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3bD6oK89Y7uLeWzWx61RYVqaMV3W2pHFGpHr+1d7VryUx4Ob9Qy2fWF2mMMJ2QZ9VXno4PKJ8XA80YzPsSm5DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:56:44.367640Z"},"content_sha256":"5c6694a8d0a48d64da32756a9ddecdcd3f4fd6f4142e52ee6b4ec0a1372323b0","schema_version":"1.0","event_id":"sha256:5c6694a8d0a48d64da32756a9ddecdcd3f4fd6f4142e52ee6b4ec0a1372323b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:I6RKKPERQ2UMZUKGD43XLSUNNB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multiscale sequence modeling with a learned dictionary","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Amartya Sanyal, Bart van Merri\\\"enboer, Hugo Larochelle, Yoshua Bengio","submitted_at":"2017-07-03T21:16:49Z","abstract_excerpt":"We propose a generalization of neural network sequence models. Instead of predicting one symbol at a time, our multi-scale model makes predictions over multiple, potentially overlapping multi-symbol tokens. A variation of the byte-pair encoding (BPE) compression algorithm is used to learn the dictionary of tokens that the model is trained with. When applied to language modelling, our model has the flexibility of character-level models while maintaining many of the performance benefits of word-level models. Our experiments show that this model performs better than a regular LSTM on language mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.00762","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":"2026-05-18T00:40:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LvfPLHbelzP1xwAll6xYZ6ZzHUOECw1aBWmHr2alCnyM5+i7EcWzaKnvLQUNp73/y2D7TLcg6kS7j5itdVgjBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:56:44.368304Z"},"content_sha256":"80f5180ecee3258a78234936529e5690d444c5f2b30acb5e5ef566d05ffc534a","schema_version":"1.0","event_id":"sha256:80f5180ecee3258a78234936529e5690d444c5f2b30acb5e5ef566d05ffc534a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I6RKKPERQ2UMZUKGD43XLSUNNB/bundle.json","state_url":"https://pith.science/pith/I6RKKPERQ2UMZUKGD43XLSUNNB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I6RKKPERQ2UMZUKGD43XLSUNNB/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":"2026-05-27T15:56:44Z","links":{"resolver":"https://pith.science/pith/I6RKKPERQ2UMZUKGD43XLSUNNB","bundle":"https://pith.science/pith/I6RKKPERQ2UMZUKGD43XLSUNNB/bundle.json","state":"https://pith.science/pith/I6RKKPERQ2UMZUKGD43XLSUNNB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I6RKKPERQ2UMZUKGD43XLSUNNB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:I6RKKPERQ2UMZUKGD43XLSUNNB","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":"0b75383b15494a7c8d2d5de0fad47c8b25fcf9831214d49b31b251eaa387555e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-03T21:16:49Z","title_canon_sha256":"0a37b476e71a2e59333b772ace9a9925b3396aa3987fad5741ecad91921fa39b"},"schema_version":"1.0","source":{"id":"1707.00762","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.00762","created_at":"2026-05-18T00:40:52Z"},{"alias_kind":"arxiv_version","alias_value":"1707.00762v2","created_at":"2026-05-18T00:40:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.00762","created_at":"2026-05-18T00:40:52Z"},{"alias_kind":"pith_short_12","alias_value":"I6RKKPERQ2UM","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"I6RKKPERQ2UMZUKG","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"I6RKKPER","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:80f5180ecee3258a78234936529e5690d444c5f2b30acb5e5ef566d05ffc534a","target":"graph","created_at":"2026-05-18T00:40:52Z","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 propose a generalization of neural network sequence models. Instead of predicting one symbol at a time, our multi-scale model makes predictions over multiple, potentially overlapping multi-symbol tokens. A variation of the byte-pair encoding (BPE) compression algorithm is used to learn the dictionary of tokens that the model is trained with. When applied to language modelling, our model has the flexibility of character-level models while maintaining many of the performance benefits of word-level models. Our experiments show that this model performs better than a regular LSTM on language mod","authors_text":"Amartya Sanyal, Bart van Merri\\\"enboer, Hugo Larochelle, Yoshua Bengio","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-03T21:16:49Z","title":"Multiscale sequence modeling with a learned dictionary"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.00762","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":"sha256:5c6694a8d0a48d64da32756a9ddecdcd3f4fd6f4142e52ee6b4ec0a1372323b0","target":"record","created_at":"2026-05-18T00:40:52Z","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":"0b75383b15494a7c8d2d5de0fad47c8b25fcf9831214d49b31b251eaa387555e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-03T21:16:49Z","title_canon_sha256":"0a37b476e71a2e59333b772ace9a9925b3396aa3987fad5741ecad91921fa39b"},"schema_version":"1.0","source":{"id":"1707.00762","kind":"arxiv","version":2}},"canonical_sha256":"47a2a53c9186a8ccd1461f3775ca8d685468e990fd4c730be37784d118515585","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47a2a53c9186a8ccd1461f3775ca8d685468e990fd4c730be37784d118515585","first_computed_at":"2026-05-18T00:40:52.534671Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:40:52.534671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3+Pb9FCBqnyt1Na6P/l1e3gCjrnnDF3uQbEEm4oveNJ9wTvB+Dx7qaCyz70MGrprorIje7i5+gGd5FhNbUg1Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:40:52.535293Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.00762","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c6694a8d0a48d64da32756a9ddecdcd3f4fd6f4142e52ee6b4ec0a1372323b0","sha256:80f5180ecee3258a78234936529e5690d444c5f2b30acb5e5ef566d05ffc534a"],"state_sha256":"9d2d71a8fd65c29cef0dd69761d035042bac3e85a3bb7f09669e997fc419e5df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nqw8Cy4gWomibCsNFlIziIgFPGg2JIeYDPHlblnZDxlQaCqzd8t3Vsq9JyB3At6NTRPrgOJjjw1c9/jtOjoLBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T15:56:44.370957Z","bundle_sha256":"8ee5bd17ef788d9c25d1069a4c5d38602ee027cf11b698b96043c1e5385aea5b"}}