{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:EPEU43UM2NFZKPNVAQSEK2WWMG","short_pith_number":"pith:EPEU43UM","canonical_record":{"source":{"id":"1703.01454","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-04T13:35:49Z","cross_cats_sorted":[],"title_canon_sha256":"78d1ce9022b426c69ff563ca1c8b56886b0043cf612dbf7c3f0bffe010886713","abstract_canon_sha256":"39b19b7561baa441f781492b38ab25cce772a86fe6ba5662b7cafcf377da6c48"},"schema_version":"1.0"},"canonical_sha256":"23c94e6e8cd34b953db50424456ad6619c16dc7fb623fab026290555fdae9498","source":{"kind":"arxiv","id":"1703.01454","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.01454","created_at":"2026-05-18T00:24:31Z"},{"alias_kind":"arxiv_version","alias_value":"1703.01454v2","created_at":"2026-05-18T00:24:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01454","created_at":"2026-05-18T00:24:31Z"},{"alias_kind":"pith_short_12","alias_value":"EPEU43UM2NFZ","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EPEU43UM2NFZKPNV","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EPEU43UM","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:EPEU43UM2NFZKPNVAQSEK2WWMG","target":"record","payload":{"canonical_record":{"source":{"id":"1703.01454","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-04T13:35:49Z","cross_cats_sorted":[],"title_canon_sha256":"78d1ce9022b426c69ff563ca1c8b56886b0043cf612dbf7c3f0bffe010886713","abstract_canon_sha256":"39b19b7561baa441f781492b38ab25cce772a86fe6ba5662b7cafcf377da6c48"},"schema_version":"1.0"},"canonical_sha256":"23c94e6e8cd34b953db50424456ad6619c16dc7fb623fab026290555fdae9498","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:31.463280Z","signature_b64":"cdAKdksEZStzEi5r1VUxZTViaxoZF3YyD9YOf8Q4h1ZESCu+amHjkRiskf6LBwOvOq2I7HVKLGiE7/UpBPfkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23c94e6e8cd34b953db50424456ad6619c16dc7fb623fab026290555fdae9498","last_reissued_at":"2026-05-18T00:24:31.462717Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:31.462717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.01454","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":"2026-05-18T00:24:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9qT9/t9lcA5BNSelIYmrWfuWpHgra6jF6kyo3UiLLtXifcuIBJh6Qgw0hn7jEHzuAPtplVpZjRByVyn5cN6DBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T22:03:15.158482Z"},"content_sha256":"f91e7680a0f6c81dd2328a854fa9bd57f85c4995032963862d38776b585b75b2","schema_version":"1.0","event_id":"sha256:f91e7680a0f6c81dd2328a854fa9bd57f85c4995032963862d38776b585b75b2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:EPEU43UM2NFZKPNVAQSEK2WWMG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Deep Matrix Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kien Do, Svetha Venkatesh, Truyen Tran","submitted_at":"2017-03-04T13:35:49Z","abstract_excerpt":"We present a new distributed representation in deep neural nets wherein the information is represented in native form as a matrix. This differs from current neural architectures that rely on vector representations. We consider matrices as central to the architecture and they compose the input, hidden and output layers. The model representation is more compact and elegant -- the number of parameters grows only with the largest dimension of the incoming layer rather than the number of hidden units. We derive several new deep networks: (i) feed-forward nets that map an input matrix into an output"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01454","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":"2026-05-18T00:24:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A7w4y7pTwZcwM+Yx9k/0bnDf7TBs9DIoa7j+Occ8WiSTzXa69Lerbim2p+zs7DQWDJkV3qWA7tOwZqhjInDjCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T22:03:15.158836Z"},"content_sha256":"b56dc41610273ab7689f183349443954438d075fcc2a8e6e1db5b5fd4553c422","schema_version":"1.0","event_id":"sha256:b56dc41610273ab7689f183349443954438d075fcc2a8e6e1db5b5fd4553c422"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EPEU43UM2NFZKPNVAQSEK2WWMG/bundle.json","state_url":"https://pith.science/pith/EPEU43UM2NFZKPNVAQSEK2WWMG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EPEU43UM2NFZKPNVAQSEK2WWMG/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":"2026-05-19T22:03:15Z","links":{"resolver":"https://pith.science/pith/EPEU43UM2NFZKPNVAQSEK2WWMG","bundle":"https://pith.science/pith/EPEU43UM2NFZKPNVAQSEK2WWMG/bundle.json","state":"https://pith.science/pith/EPEU43UM2NFZKPNVAQSEK2WWMG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EPEU43UM2NFZKPNVAQSEK2WWMG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:EPEU43UM2NFZKPNVAQSEK2WWMG","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":"39b19b7561baa441f781492b38ab25cce772a86fe6ba5662b7cafcf377da6c48","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-04T13:35:49Z","title_canon_sha256":"78d1ce9022b426c69ff563ca1c8b56886b0043cf612dbf7c3f0bffe010886713"},"schema_version":"1.0","source":{"id":"1703.01454","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.01454","created_at":"2026-05-18T00:24:31Z"},{"alias_kind":"arxiv_version","alias_value":"1703.01454v2","created_at":"2026-05-18T00:24:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01454","created_at":"2026-05-18T00:24:31Z"},{"alias_kind":"pith_short_12","alias_value":"EPEU43UM2NFZ","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EPEU43UM2NFZKPNV","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EPEU43UM","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:b56dc41610273ab7689f183349443954438d075fcc2a8e6e1db5b5fd4553c422","target":"graph","created_at":"2026-05-18T00:24:31Z","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 a new distributed representation in deep neural nets wherein the information is represented in native form as a matrix. This differs from current neural architectures that rely on vector representations. We consider matrices as central to the architecture and they compose the input, hidden and output layers. The model representation is more compact and elegant -- the number of parameters grows only with the largest dimension of the incoming layer rather than the number of hidden units. We derive several new deep networks: (i) feed-forward nets that map an input matrix into an output","authors_text":"Kien Do, Svetha Venkatesh, Truyen Tran","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-04T13:35:49Z","title":"Learning Deep Matrix Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01454","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:f91e7680a0f6c81dd2328a854fa9bd57f85c4995032963862d38776b585b75b2","target":"record","created_at":"2026-05-18T00:24:31Z","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":"39b19b7561baa441f781492b38ab25cce772a86fe6ba5662b7cafcf377da6c48","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-04T13:35:49Z","title_canon_sha256":"78d1ce9022b426c69ff563ca1c8b56886b0043cf612dbf7c3f0bffe010886713"},"schema_version":"1.0","source":{"id":"1703.01454","kind":"arxiv","version":2}},"canonical_sha256":"23c94e6e8cd34b953db50424456ad6619c16dc7fb623fab026290555fdae9498","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23c94e6e8cd34b953db50424456ad6619c16dc7fb623fab026290555fdae9498","first_computed_at":"2026-05-18T00:24:31.462717Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:24:31.462717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cdAKdksEZStzEi5r1VUxZTViaxoZF3YyD9YOf8Q4h1ZESCu+amHjkRiskf6LBwOvOq2I7HVKLGiE7/UpBPfkBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:24:31.463280Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.01454","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f91e7680a0f6c81dd2328a854fa9bd57f85c4995032963862d38776b585b75b2","sha256:b56dc41610273ab7689f183349443954438d075fcc2a8e6e1db5b5fd4553c422"],"state_sha256":"25ebc2350282c1c5cae42cbdf3bc91a9e16ffa1b6dddb45cd28d9e6227626143"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uaHoudGLR0TKokexQbNMWGESCOH9rYfpXcNj0jkGtKsBFuERBfDzm7PbXhbVatW3Pclt77ZVDeXqzpuLhn5GAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T22:03:15.160966Z","bundle_sha256":"4652fd737f4632c208bdfa453f22e27ef93dc715e8545a224dbb3e360ed59850"}}