{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:G4AN7V2SYUKDKTN2CCAFQY4YKI","short_pith_number":"pith:G4AN7V2S","canonical_record":{"source":{"id":"1805.09621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-24T12:01:53Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"d00c7e3765097ac729651baaf3119175a053984357f1d4525be35fd13d9aa3bd","abstract_canon_sha256":"31408a090d10f5cf410fd600b57071ecd310120f3319751408a8f80539eb10e3"},"schema_version":"1.0"},"canonical_sha256":"3700dfd752c514354dba1080586398523a4137386275d45b988de1d59b2f77a7","source":{"kind":"arxiv","id":"1805.09621","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09621","created_at":"2026-05-18T00:15:03Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09621v1","created_at":"2026-05-18T00:15:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09621","created_at":"2026-05-18T00:15:03Z"},{"alias_kind":"pith_short_12","alias_value":"G4AN7V2SYUKD","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"G4AN7V2SYUKDKTN2","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"G4AN7V2S","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:G4AN7V2SYUKDKTN2CCAFQY4YKI","target":"record","payload":{"canonical_record":{"source":{"id":"1805.09621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-24T12:01:53Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"d00c7e3765097ac729651baaf3119175a053984357f1d4525be35fd13d9aa3bd","abstract_canon_sha256":"31408a090d10f5cf410fd600b57071ecd310120f3319751408a8f80539eb10e3"},"schema_version":"1.0"},"canonical_sha256":"3700dfd752c514354dba1080586398523a4137386275d45b988de1d59b2f77a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:03.380679Z","signature_b64":"bFGdW2Oowq+2k2xUE4xjYc7k+Tg9L7kPGDM+XyEsY+6iKTjkjOBemmgJU+45jVzLa/LHjgnIAFNZ8rrstbMDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3700dfd752c514354dba1080586398523a4137386275d45b988de1d59b2f77a7","last_reissued_at":"2026-05-18T00:15:03.380016Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:03.380016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.09621","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yKft9SJ1KmkMm9F5nH7ol3456HBn6fhGqzBXopEkzhjKyKxg0Jxv7L5AwEtCOJ6sJ5oG8zsu7RJbHSTtsu3xDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T13:52:15.206712Z"},"content_sha256":"c01c2c3cf19a820ce99a9933bc54a664f820460f4de54d8eaff22a3e0277e5b7","schema_version":"1.0","event_id":"sha256:c01c2c3cf19a820ce99a9933bc54a664f820460f4de54d8eaff22a3e0277e5b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:G4AN7V2SYUKDKTN2CCAFQY4YKI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Backpropagation with N-D Vector-Valued Neurons Using Arbitrary Bilinear Products","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jyh-Shing R. Jang, Tak-Shing T. Chan, Yi-Hsuan Yang, Zhe-Cheng Fan","submitted_at":"2018-05-24T12:01:53Z","abstract_excerpt":"Vector-valued neural learning has emerged as a promising direction in deep learning recently. Traditionally, training data for neural networks (NNs) are formulated as a vector of scalars; however, its performance may not be optimal since associations among adjacent scalars are not modeled. In this paper, we propose a new vector neural architecture called the Arbitrary BIlinear Product Neural Network (ABIPNN), which processes information as vectors in each neuron, and the feedforward projections are defined using arbitrary bilinear products. Such bilinear products can include circular convoluti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09621","kind":"arxiv","version":1},"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":"2026-05-18T00:15:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gAUHDuJZi+dhpLVI9A53s+cD90Wpz17vKKeB8FNuOmhuJO7CJqCMdOAaJ9Dn9SQ0J/73Q05I3pzVUJIEOKU5Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T13:52:15.207341Z"},"content_sha256":"cd54f85c8c921243434f89ce99139074fb738b60098242ccd1faf143ea469434","schema_version":"1.0","event_id":"sha256:cd54f85c8c921243434f89ce99139074fb738b60098242ccd1faf143ea469434"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G4AN7V2SYUKDKTN2CCAFQY4YKI/bundle.json","state_url":"https://pith.science/pith/G4AN7V2SYUKDKTN2CCAFQY4YKI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G4AN7V2SYUKDKTN2CCAFQY4YKI/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":"2026-05-31T13:52:15Z","links":{"resolver":"https://pith.science/pith/G4AN7V2SYUKDKTN2CCAFQY4YKI","bundle":"https://pith.science/pith/G4AN7V2SYUKDKTN2CCAFQY4YKI/bundle.json","state":"https://pith.science/pith/G4AN7V2SYUKDKTN2CCAFQY4YKI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G4AN7V2SYUKDKTN2CCAFQY4YKI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:G4AN7V2SYUKDKTN2CCAFQY4YKI","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":"31408a090d10f5cf410fd600b57071ecd310120f3319751408a8f80539eb10e3","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-24T12:01:53Z","title_canon_sha256":"d00c7e3765097ac729651baaf3119175a053984357f1d4525be35fd13d9aa3bd"},"schema_version":"1.0","source":{"id":"1805.09621","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09621","created_at":"2026-05-18T00:15:03Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09621v1","created_at":"2026-05-18T00:15:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09621","created_at":"2026-05-18T00:15:03Z"},{"alias_kind":"pith_short_12","alias_value":"G4AN7V2SYUKD","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"G4AN7V2SYUKDKTN2","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"G4AN7V2S","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:cd54f85c8c921243434f89ce99139074fb738b60098242ccd1faf143ea469434","target":"graph","created_at":"2026-05-18T00:15:03Z","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":"Vector-valued neural learning has emerged as a promising direction in deep learning recently. Traditionally, training data for neural networks (NNs) are formulated as a vector of scalars; however, its performance may not be optimal since associations among adjacent scalars are not modeled. In this paper, we propose a new vector neural architecture called the Arbitrary BIlinear Product Neural Network (ABIPNN), which processes information as vectors in each neuron, and the feedforward projections are defined using arbitrary bilinear products. Such bilinear products can include circular convoluti","authors_text":"Jyh-Shing R. Jang, Tak-Shing T. Chan, Yi-Hsuan Yang, Zhe-Cheng Fan","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-24T12:01:53Z","title":"Backpropagation with N-D Vector-Valued Neurons Using Arbitrary Bilinear Products"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09621","kind":"arxiv","version":1},"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:c01c2c3cf19a820ce99a9933bc54a664f820460f4de54d8eaff22a3e0277e5b7","target":"record","created_at":"2026-05-18T00:15:03Z","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":"31408a090d10f5cf410fd600b57071ecd310120f3319751408a8f80539eb10e3","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-24T12:01:53Z","title_canon_sha256":"d00c7e3765097ac729651baaf3119175a053984357f1d4525be35fd13d9aa3bd"},"schema_version":"1.0","source":{"id":"1805.09621","kind":"arxiv","version":1}},"canonical_sha256":"3700dfd752c514354dba1080586398523a4137386275d45b988de1d59b2f77a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3700dfd752c514354dba1080586398523a4137386275d45b988de1d59b2f77a7","first_computed_at":"2026-05-18T00:15:03.380016Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:03.380016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bFGdW2Oowq+2k2xUE4xjYc7k+Tg9L7kPGDM+XyEsY+6iKTjkjOBemmgJU+45jVzLa/LHjgnIAFNZ8rrstbMDDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:03.380679Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.09621","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c01c2c3cf19a820ce99a9933bc54a664f820460f4de54d8eaff22a3e0277e5b7","sha256:cd54f85c8c921243434f89ce99139074fb738b60098242ccd1faf143ea469434"],"state_sha256":"13eaa34f86c877cb9b2f02c1f3e8e21aef3dc3238930864f8f27edb87d770055"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LLoeeGe9M5228Erjuuuo5JxfgiigYAKKDCNbxtsI4OBz6z50C1+dsSRP0jklmmFzAu/vvN6UxnM5ynY8PI7xBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T13:52:15.211062Z","bundle_sha256":"bdbfb1f897709214b1eddf8fd2329c62dea4ba940e4c7cd3f42f992cf6e06370"}}