{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VLGJEVMT5D3UAYWXTUE2BPEBPI","short_pith_number":"pith:VLGJEVMT","canonical_record":{"source":{"id":"1812.07627","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-18T20:07:56Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5012da61291895c5d2d78a0fcbea5f86dd3079143c36c882ef35451206ae2ef2","abstract_canon_sha256":"6f88c0931affbea0b0954e29fe67e2930a0536f1ed1659e2284048d8b74642b5"},"schema_version":"1.0"},"canonical_sha256":"aacc925593e8f74062d79d09a0bc817a36b521504df2ed2c69dfb48911deace8","source":{"kind":"arxiv","id":"1812.07627","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.07627","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"arxiv_version","alias_value":"1812.07627v1","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07627","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"pith_short_12","alias_value":"VLGJEVMT5D3U","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VLGJEVMT5D3UAYWX","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VLGJEVMT","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VLGJEVMT5D3UAYWXTUE2BPEBPI","target":"record","payload":{"canonical_record":{"source":{"id":"1812.07627","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-18T20:07:56Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5012da61291895c5d2d78a0fcbea5f86dd3079143c36c882ef35451206ae2ef2","abstract_canon_sha256":"6f88c0931affbea0b0954e29fe67e2930a0536f1ed1659e2284048d8b74642b5"},"schema_version":"1.0"},"canonical_sha256":"aacc925593e8f74062d79d09a0bc817a36b521504df2ed2c69dfb48911deace8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:56.506706Z","signature_b64":"XLG5Jw2bhSz/i+Yw95eYGa3eYRxdznkd1fDHKHssUzV4yAiaJPGFZxxwpQQTBqsxHuuv0jVcNzOwvFqd5k1KCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aacc925593e8f74062d79d09a0bc817a36b521504df2ed2c69dfb48911deace8","last_reissued_at":"2026-05-17T23:57:56.505981Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:56.505981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.07627","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":"2026-05-17T23:57:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ViTMSdzZpknhTkHTbr2I2+/qZ4fCLy3N9XxX6z3AkQx5Up8zPSpybE13LFDVPTAQAoy2Eym6x1tmbJ5S60hNDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:23:12.331226Z"},"content_sha256":"d04aaf0c963055bc53c945127c8824ad6628fdf9b3f8c3b8c7cd99bd6b21a8ec","schema_version":"1.0","event_id":"sha256:d04aaf0c963055bc53c945127c8824ad6628fdf9b3f8c3b8c7cd99bd6b21a8ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VLGJEVMT5D3UAYWXTUE2BPEBPI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Clustering-Oriented Representation Learning with Attractive-Repulsive Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andre Cianflone, Doina Precup, Guillaume Rabusseau, Jackie Chi Kit Cheung, Kian Kenyon-Dean, Lucas Page-Caccia","submitted_at":"2018-12-18T20:07:56Z","abstract_excerpt":"The standard loss function used to train neural network classifiers, categorical cross-entropy (CCE), seeks to maximize accuracy on the training data; building useful representations is not a necessary byproduct of this objective. In this work, we propose clustering-oriented representation learning (COREL) as an alternative to CCE in the context of a generalized attractive-repulsive loss framework. COREL has the consequence of building latent representations that collectively exhibit the quality of natural clustering within the latent space of the final hidden layer, according to a predefined "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07627","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":"2026-05-17T23:57:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e6LmigKlGX2WDsuLGeKKFVgBxkowCuS/O+i0I20uW8vWyYcxc8K6SDi+RWR5B6YPQ0KSKTIyvQey4pctXGi+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:23:12.331986Z"},"content_sha256":"976bb867d94eb0ee98865a614c0fa4ac6646a0bd904b5175ce19763831ee51e0","schema_version":"1.0","event_id":"sha256:976bb867d94eb0ee98865a614c0fa4ac6646a0bd904b5175ce19763831ee51e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VLGJEVMT5D3UAYWXTUE2BPEBPI/bundle.json","state_url":"https://pith.science/pith/VLGJEVMT5D3UAYWXTUE2BPEBPI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VLGJEVMT5D3UAYWXTUE2BPEBPI/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":"2026-05-25T15:23:12Z","links":{"resolver":"https://pith.science/pith/VLGJEVMT5D3UAYWXTUE2BPEBPI","bundle":"https://pith.science/pith/VLGJEVMT5D3UAYWXTUE2BPEBPI/bundle.json","state":"https://pith.science/pith/VLGJEVMT5D3UAYWXTUE2BPEBPI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VLGJEVMT5D3UAYWXTUE2BPEBPI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VLGJEVMT5D3UAYWXTUE2BPEBPI","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":"6f88c0931affbea0b0954e29fe67e2930a0536f1ed1659e2284048d8b74642b5","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-18T20:07:56Z","title_canon_sha256":"5012da61291895c5d2d78a0fcbea5f86dd3079143c36c882ef35451206ae2ef2"},"schema_version":"1.0","source":{"id":"1812.07627","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.07627","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"arxiv_version","alias_value":"1812.07627v1","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07627","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"pith_short_12","alias_value":"VLGJEVMT5D3U","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VLGJEVMT5D3UAYWX","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VLGJEVMT","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:976bb867d94eb0ee98865a614c0fa4ac6646a0bd904b5175ce19763831ee51e0","target":"graph","created_at":"2026-05-17T23:57:56Z","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":"The standard loss function used to train neural network classifiers, categorical cross-entropy (CCE), seeks to maximize accuracy on the training data; building useful representations is not a necessary byproduct of this objective. In this work, we propose clustering-oriented representation learning (COREL) as an alternative to CCE in the context of a generalized attractive-repulsive loss framework. COREL has the consequence of building latent representations that collectively exhibit the quality of natural clustering within the latent space of the final hidden layer, according to a predefined ","authors_text":"Andre Cianflone, Doina Precup, Guillaume Rabusseau, Jackie Chi Kit Cheung, Kian Kenyon-Dean, Lucas Page-Caccia","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-18T20:07:56Z","title":"Clustering-Oriented Representation Learning with Attractive-Repulsive Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07627","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:d04aaf0c963055bc53c945127c8824ad6628fdf9b3f8c3b8c7cd99bd6b21a8ec","target":"record","created_at":"2026-05-17T23:57:56Z","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":"6f88c0931affbea0b0954e29fe67e2930a0536f1ed1659e2284048d8b74642b5","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-18T20:07:56Z","title_canon_sha256":"5012da61291895c5d2d78a0fcbea5f86dd3079143c36c882ef35451206ae2ef2"},"schema_version":"1.0","source":{"id":"1812.07627","kind":"arxiv","version":1}},"canonical_sha256":"aacc925593e8f74062d79d09a0bc817a36b521504df2ed2c69dfb48911deace8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aacc925593e8f74062d79d09a0bc817a36b521504df2ed2c69dfb48911deace8","first_computed_at":"2026-05-17T23:57:56.505981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:56.505981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XLG5Jw2bhSz/i+Yw95eYGa3eYRxdznkd1fDHKHssUzV4yAiaJPGFZxxwpQQTBqsxHuuv0jVcNzOwvFqd5k1KCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:56.506706Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.07627","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d04aaf0c963055bc53c945127c8824ad6628fdf9b3f8c3b8c7cd99bd6b21a8ec","sha256:976bb867d94eb0ee98865a614c0fa4ac6646a0bd904b5175ce19763831ee51e0"],"state_sha256":"b6776228a9ffa46547edf5b9e159e7b8587c38f772cf38577e1500d13034d74e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xkeMcBMt1W14o6JhgRNK18FMMGpr/tt03ddjrrKLyKBTD91CjO6SAsL9hCOpuo3CGHqN7oUrfhq2XpTtPXLoAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T15:23:12.335705Z","bundle_sha256":"430b6b55081b0609ef7c5f955b733dda84cf7be36134013e27ec1b68191262e0"}}