{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7E7NB34RATN2OXCKGWXR37BDFF","short_pith_number":"pith:7E7NB34R","canonical_record":{"source":{"id":"1810.06682","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-15T20:50:05Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"83017a4b6cfb9f20ae1db3aea65b206ad910e227b44c4f11a1fa674cee96db66","abstract_canon_sha256":"aaccbb05587554de777c25a9e450210deaf5d123c112264b4e2769d7a8d7526f"},"schema_version":"1.0"},"canonical_sha256":"f93ed0ef9104dba75c4a35af1dfc23295e6c2fe8bc7259101cf7730677145f04","source":{"kind":"arxiv","id":"1810.06682","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.06682","created_at":"2026-05-17T23:51:33Z"},{"alias_kind":"arxiv_version","alias_value":"1810.06682v2","created_at":"2026-05-17T23:51:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06682","created_at":"2026-05-17T23:51:33Z"},{"alias_kind":"pith_short_12","alias_value":"7E7NB34RATN2","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7E7NB34RATN2OXCK","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7E7NB34R","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7E7NB34RATN2OXCKGWXR37BDFF","target":"record","payload":{"canonical_record":{"source":{"id":"1810.06682","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-15T20:50:05Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"83017a4b6cfb9f20ae1db3aea65b206ad910e227b44c4f11a1fa674cee96db66","abstract_canon_sha256":"aaccbb05587554de777c25a9e450210deaf5d123c112264b4e2769d7a8d7526f"},"schema_version":"1.0"},"canonical_sha256":"f93ed0ef9104dba75c4a35af1dfc23295e6c2fe8bc7259101cf7730677145f04","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:33.091999Z","signature_b64":"LK015NMKqGOGRNsdZiGXTtQ6hOKYzVTPj6GOU1wm4W00K/V7JEWBkr4OJEaDISGG/T+Vjo59v8mBbtM3FeIPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f93ed0ef9104dba75c4a35af1dfc23295e6c2fe8bc7259101cf7730677145f04","last_reissued_at":"2026-05-17T23:51:33.091516Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:33.091516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.06682","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":"2026-05-17T23:51:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zG3bDpYKbN/JbjMBUuK09R5j2qnCXn4+9BpznTSNWnirDZ9wlSnBZGynL352XE57FewE3BPZBK62Sp9EEvl5BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:04:55.003437Z"},"content_sha256":"84f3424854c0de04dbda378bb9a9a771bc05e14ab5ffba75bc022a598c537fe3","schema_version":"1.0","event_id":"sha256:84f3424854c0de04dbda378bb9a9a771bc05e14ab5ffba75bc022a598c537fe3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7E7NB34RATN2OXCKGWXR37BDFF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Trellis Networks for Sequence Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"J. Zico Kolter, Shaojie Bai, Vladlen Koltun","submitted_at":"2018-10-15T20:50:05Z","abstract_excerpt":"We present trellis networks, a new architecture for sequence modeling. On the one hand, a trellis network is a temporal convolutional network with special structure, characterized by weight tying across depth and direct injection of the input into deep layers. On the other hand, we show that truncated recurrent networks are equivalent to trellis networks with special sparsity structure in their weight matrices. Thus trellis networks with general weight matrices generalize truncated recurrent networks. We leverage these connections to design high-performing trellis networks that absorb structur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06682","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":"2026-05-17T23:51:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vp0ixcXmuTznqdnJdMZOTlnLjKsMH2HjhqIIXfGLNBu7ql5vY36VYeBBiS6TaA1gvqsJbRpMFW2cij/TRlmPBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:04:55.003803Z"},"content_sha256":"e029b06ff398298f327a489da5458b30e60b01c8738c64cbdf2e32153be26dd3","schema_version":"1.0","event_id":"sha256:e029b06ff398298f327a489da5458b30e60b01c8738c64cbdf2e32153be26dd3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7E7NB34RATN2OXCKGWXR37BDFF/bundle.json","state_url":"https://pith.science/pith/7E7NB34RATN2OXCKGWXR37BDFF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7E7NB34RATN2OXCKGWXR37BDFF/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":"2026-08-06T08:04:55Z","links":{"resolver":"https://pith.science/pith/7E7NB34RATN2OXCKGWXR37BDFF","bundle":"https://pith.science/pith/7E7NB34RATN2OXCKGWXR37BDFF/bundle.json","state":"https://pith.science/pith/7E7NB34RATN2OXCKGWXR37BDFF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7E7NB34RATN2OXCKGWXR37BDFF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7E7NB34RATN2OXCKGWXR37BDFF","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":"aaccbb05587554de777c25a9e450210deaf5d123c112264b4e2769d7a8d7526f","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-15T20:50:05Z","title_canon_sha256":"83017a4b6cfb9f20ae1db3aea65b206ad910e227b44c4f11a1fa674cee96db66"},"schema_version":"1.0","source":{"id":"1810.06682","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.06682","created_at":"2026-05-17T23:51:33Z"},{"alias_kind":"arxiv_version","alias_value":"1810.06682v2","created_at":"2026-05-17T23:51:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06682","created_at":"2026-05-17T23:51:33Z"},{"alias_kind":"pith_short_12","alias_value":"7E7NB34RATN2","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7E7NB34RATN2OXCK","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7E7NB34R","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:e029b06ff398298f327a489da5458b30e60b01c8738c64cbdf2e32153be26dd3","target":"graph","created_at":"2026-05-17T23:51:33Z","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 present trellis networks, a new architecture for sequence modeling. On the one hand, a trellis network is a temporal convolutional network with special structure, characterized by weight tying across depth and direct injection of the input into deep layers. On the other hand, we show that truncated recurrent networks are equivalent to trellis networks with special sparsity structure in their weight matrices. Thus trellis networks with general weight matrices generalize truncated recurrent networks. We leverage these connections to design high-performing trellis networks that absorb structur","authors_text":"J. Zico Kolter, Shaojie Bai, Vladlen Koltun","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-15T20:50:05Z","title":"Trellis Networks for Sequence Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06682","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":"sha256:84f3424854c0de04dbda378bb9a9a771bc05e14ab5ffba75bc022a598c537fe3","target":"record","created_at":"2026-05-17T23:51:33Z","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":"aaccbb05587554de777c25a9e450210deaf5d123c112264b4e2769d7a8d7526f","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-15T20:50:05Z","title_canon_sha256":"83017a4b6cfb9f20ae1db3aea65b206ad910e227b44c4f11a1fa674cee96db66"},"schema_version":"1.0","source":{"id":"1810.06682","kind":"arxiv","version":2}},"canonical_sha256":"f93ed0ef9104dba75c4a35af1dfc23295e6c2fe8bc7259101cf7730677145f04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f93ed0ef9104dba75c4a35af1dfc23295e6c2fe8bc7259101cf7730677145f04","first_computed_at":"2026-05-17T23:51:33.091516Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:33.091516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LK015NMKqGOGRNsdZiGXTtQ6hOKYzVTPj6GOU1wm4W00K/V7JEWBkr4OJEaDISGG/T+Vjo59v8mBbtM3FeIPDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:33.091999Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.06682","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84f3424854c0de04dbda378bb9a9a771bc05e14ab5ffba75bc022a598c537fe3","sha256:e029b06ff398298f327a489da5458b30e60b01c8738c64cbdf2e32153be26dd3"],"state_sha256":"9c365cf32959a9d8f65cfe26d07113f242bd5b2c2d30aa0950793a3c1419ac38"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ct/Rxjj08d7bNBwZALYTDcSLBrkgxy/WQ1gz0vyJAvZlKWLgNY53gpRP0+7P7zcGaMy+4+ddtVTrbq1NaQSTBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:04:55.007596Z","bundle_sha256":"7633320cc41ab9d3e4121ef4c6e1ccaa7f7b7cde8a3706726cba6593b86a4099"}}