{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:6IG6QOASZL3LDHGVEUUDTZLCPW","short_pith_number":"pith:6IG6QOAS","canonical_record":{"source":{"id":"1805.09366","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T18:19:11Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS","eess.SP","stat.ML"],"title_canon_sha256":"e24054eb253d111c26b8c0e0c19c7a0fe24acc8fdd05f3524ca693775ecd9797","abstract_canon_sha256":"9446678b52a5d1bd71cc574d5c8598ec434a9e019b6c6ef14328e010240a7ce4"},"schema_version":"1.0"},"canonical_sha256":"f20de83812caf6b19cd5252839e5627d8ede4b04284f7af1ba01b17bbbd34b02","source":{"kind":"arxiv","id":"1805.09366","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09366","created_at":"2026-05-18T00:00:30Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09366v2","created_at":"2026-05-18T00:00:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09366","created_at":"2026-05-18T00:00:30Z"},{"alias_kind":"pith_short_12","alias_value":"6IG6QOASZL3L","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"6IG6QOASZL3LDHGV","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"6IG6QOAS","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:6IG6QOASZL3LDHGVEUUDTZLCPW","target":"record","payload":{"canonical_record":{"source":{"id":"1805.09366","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T18:19:11Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS","eess.SP","stat.ML"],"title_canon_sha256":"e24054eb253d111c26b8c0e0c19c7a0fe24acc8fdd05f3524ca693775ecd9797","abstract_canon_sha256":"9446678b52a5d1bd71cc574d5c8598ec434a9e019b6c6ef14328e010240a7ce4"},"schema_version":"1.0"},"canonical_sha256":"f20de83812caf6b19cd5252839e5627d8ede4b04284f7af1ba01b17bbbd34b02","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:30.275291Z","signature_b64":"qW+IdJSFGSYN1GiOoSNwewKveBaWpjPFjbIpsHII96xKndIVwGeD7v88BHVGkDQgIRQJVhtIpsv0UqnlxIumCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f20de83812caf6b19cd5252839e5627d8ede4b04284f7af1ba01b17bbbd34b02","last_reissued_at":"2026-05-18T00:00:30.274780Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:30.274780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.09366","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":"2026-05-18T00:00:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oAexHHrZ4sjne+f12YUKn5pMope6MKIgFByrQnamARwGLegSon8JM8/+3eTa/5M7d63Wh5ZASgKTsewShLIUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T23:18:05.979112Z"},"content_sha256":"c3d530f198f80f0e2fc4090b71200430a833c33d99e144de56c199dcdf71d301","schema_version":"1.0","event_id":"sha256:c3d530f198f80f0e2fc4090b71200430a833c33d99e144de56c199dcdf71d301"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:6IG6QOASZL3LDHGVEUUDTZLCPW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-supervised classification by reaching consensus among modalities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS","eess.SP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Frank Rudzicz, Jekaterina Novikova, Zining Zhu","submitted_at":"2018-05-23T18:19:11Z","abstract_excerpt":"Deep learning has demonstrated abilities to learn complex structures, but they can be restricted by available data. Recently, Consensus Networks (CNs) were proposed to alleviate data sparsity by utilizing features from multiple modalities, but they too have been limited by the size of labeled data. In this paper, we extend CN to Transductive Consensus Networks (TCNs), suitable for semi-supervised learning. In TCNs, different modalities of input are compressed into latent representations, which we encourage to become indistinguishable during iterative adversarial training. To understand TCNs tw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09366","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":"2026-05-18T00:00:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0tRB3XSXdHAPxNQbkUQQuieLPXl74eimgvf5xy44+RgIRJVWlK+dqNjOl6dZxNMr1VcwSCclURGrxARf18rlDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T23:18:05.979649Z"},"content_sha256":"8c19f01be1586b862885858ead6364ba7d60a1102a4464c099c6fb14e8118520","schema_version":"1.0","event_id":"sha256:8c19f01be1586b862885858ead6364ba7d60a1102a4464c099c6fb14e8118520"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6IG6QOASZL3LDHGVEUUDTZLCPW/bundle.json","state_url":"https://pith.science/pith/6IG6QOASZL3LDHGVEUUDTZLCPW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6IG6QOASZL3LDHGVEUUDTZLCPW/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":"2026-05-27T23:18:05Z","links":{"resolver":"https://pith.science/pith/6IG6QOASZL3LDHGVEUUDTZLCPW","bundle":"https://pith.science/pith/6IG6QOASZL3LDHGVEUUDTZLCPW/bundle.json","state":"https://pith.science/pith/6IG6QOASZL3LDHGVEUUDTZLCPW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6IG6QOASZL3LDHGVEUUDTZLCPW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:6IG6QOASZL3LDHGVEUUDTZLCPW","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":"9446678b52a5d1bd71cc574d5c8598ec434a9e019b6c6ef14328e010240a7ce4","cross_cats_sorted":["cs.MM","cs.SD","eess.AS","eess.SP","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T18:19:11Z","title_canon_sha256":"e24054eb253d111c26b8c0e0c19c7a0fe24acc8fdd05f3524ca693775ecd9797"},"schema_version":"1.0","source":{"id":"1805.09366","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09366","created_at":"2026-05-18T00:00:30Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09366v2","created_at":"2026-05-18T00:00:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09366","created_at":"2026-05-18T00:00:30Z"},{"alias_kind":"pith_short_12","alias_value":"6IG6QOASZL3L","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"6IG6QOASZL3LDHGV","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"6IG6QOAS","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:8c19f01be1586b862885858ead6364ba7d60a1102a4464c099c6fb14e8118520","target":"graph","created_at":"2026-05-18T00:00:30Z","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":"Deep learning has demonstrated abilities to learn complex structures, but they can be restricted by available data. Recently, Consensus Networks (CNs) were proposed to alleviate data sparsity by utilizing features from multiple modalities, but they too have been limited by the size of labeled data. In this paper, we extend CN to Transductive Consensus Networks (TCNs), suitable for semi-supervised learning. In TCNs, different modalities of input are compressed into latent representations, which we encourage to become indistinguishable during iterative adversarial training. To understand TCNs tw","authors_text":"Frank Rudzicz, Jekaterina Novikova, Zining Zhu","cross_cats":["cs.MM","cs.SD","eess.AS","eess.SP","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T18:19:11Z","title":"Semi-supervised classification by reaching consensus among modalities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09366","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:c3d530f198f80f0e2fc4090b71200430a833c33d99e144de56c199dcdf71d301","target":"record","created_at":"2026-05-18T00:00:30Z","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":"9446678b52a5d1bd71cc574d5c8598ec434a9e019b6c6ef14328e010240a7ce4","cross_cats_sorted":["cs.MM","cs.SD","eess.AS","eess.SP","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T18:19:11Z","title_canon_sha256":"e24054eb253d111c26b8c0e0c19c7a0fe24acc8fdd05f3524ca693775ecd9797"},"schema_version":"1.0","source":{"id":"1805.09366","kind":"arxiv","version":2}},"canonical_sha256":"f20de83812caf6b19cd5252839e5627d8ede4b04284f7af1ba01b17bbbd34b02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f20de83812caf6b19cd5252839e5627d8ede4b04284f7af1ba01b17bbbd34b02","first_computed_at":"2026-05-18T00:00:30.274780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:30.274780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qW+IdJSFGSYN1GiOoSNwewKveBaWpjPFjbIpsHII96xKndIVwGeD7v88BHVGkDQgIRQJVhtIpsv0UqnlxIumCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:30.275291Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.09366","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3d530f198f80f0e2fc4090b71200430a833c33d99e144de56c199dcdf71d301","sha256:8c19f01be1586b862885858ead6364ba7d60a1102a4464c099c6fb14e8118520"],"state_sha256":"fbf11ac11332243e1d9cf70e17049b901b65871a395e631523f058654c0a17a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WeMWK0QNzC9L5f7j6mymvy1YZo62qvBdGQiI61iR4GQ4xW3tg26TfnsJLoAAcZ5EIeWWeH0NQdVakGKKPxn2AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T23:18:05.982948Z","bundle_sha256":"c72dcf5b7789320855fec9bb80ff8c96476c07a77a42e21401ddbf9736cb6b62"}}