{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QHS4SJYM2W27OMF3ED6WILP56K","short_pith_number":"pith:QHS4SJYM","canonical_record":{"source":{"id":"1912.02280","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-04T22:13:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7a3d573fb08316d571bb9b04e16dc6a282f2e1b511da33c1277a88e9670d7dc3","abstract_canon_sha256":"30d96ad9c5d43e299c45d90f07ec489ea369f793e43138ffd9ac2f59cc25a9c3"},"schema_version":"1.0"},"canonical_sha256":"81e5c9270cd5b5f730bb20fd642dfdf2998df96b3143d4013b771281c0d67d8a","source":{"kind":"arxiv","id":"1912.02280","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.02280","created_at":"2026-07-05T00:28:15Z"},{"alias_kind":"arxiv_version","alias_value":"1912.02280v2","created_at":"2026-07-05T00:28:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.02280","created_at":"2026-07-05T00:28:15Z"},{"alias_kind":"pith_short_12","alias_value":"QHS4SJYM2W27","created_at":"2026-07-05T00:28:15Z"},{"alias_kind":"pith_short_16","alias_value":"QHS4SJYM2W27OMF3","created_at":"2026-07-05T00:28:15Z"},{"alias_kind":"pith_short_8","alias_value":"QHS4SJYM","created_at":"2026-07-05T00:28:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QHS4SJYM2W27OMF3ED6WILP56K","target":"record","payload":{"canonical_record":{"source":{"id":"1912.02280","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-04T22:13:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7a3d573fb08316d571bb9b04e16dc6a282f2e1b511da33c1277a88e9670d7dc3","abstract_canon_sha256":"30d96ad9c5d43e299c45d90f07ec489ea369f793e43138ffd9ac2f59cc25a9c3"},"schema_version":"1.0"},"canonical_sha256":"81e5c9270cd5b5f730bb20fd642dfdf2998df96b3143d4013b771281c0d67d8a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:28:15.758018Z","signature_b64":"IutIdonjH/S+RB3cO06wWdb/oDeRgC0fKD4W/e3f3Ryxws6tcdhj1qWxlIus7c4sxgWVZ9uSaq7YVIYrBL8aAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81e5c9270cd5b5f730bb20fd642dfdf2998df96b3143d4013b771281c0d67d8a","last_reissued_at":"2026-07-05T00:28:15.757543Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:28:15.757543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.02280","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":"2026-07-05T00:28:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3fGOjrIifVxb1YQI3aHwxTsClnYXgwLHWyf5DGEfJxu1TawBhEfIuFAbB/dTpove7BxA8d9gah6LnsNHGO5ZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:00:16.586572Z"},"content_sha256":"c74c2da800709f2c768ac023a8bce315531397449337dad17cdd557349ff8ae1","schema_version":"1.0","event_id":"sha256:c74c2da800709f2c768ac023a8bce315531397449337dad17cdd557349ff8ae1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QHS4SJYM2W27OMF3ED6WILP56K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Natural Alpha Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Luigi Malag\\`o, Riccardo Volpi","submitted_at":"2019-12-04T22:13:16Z","abstract_excerpt":"Learning an embedding for a large collection of items is a popular approach to overcome the computational limitations associated to one-hot encodings. The aim of item embedding is to learn a low dimensional space for the representations, able to capture with its geometry relevant features or relationships for the data at hand. This can be achieved for example by exploiting adjacencies among items in large sets of unlabelled data. In this paper we interpret in an Information Geometric framework the item embeddings obtained from conditional models. By exploiting the $\\alpha$-geometry of the expo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.02280","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.02280/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:28:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q+S2/bOhLXwoYa92u/KZQi165CHx8782+q3ekw7JcLKumWk+Dj8AuHXwuH9lyGybiuWv8n5DzoXr97ur9sdxDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:00:16.587323Z"},"content_sha256":"67bea4c6e1e1b95eef150b98f76197a53e82d971b8f87189c1d26d10f910bb82","schema_version":"1.0","event_id":"sha256:67bea4c6e1e1b95eef150b98f76197a53e82d971b8f87189c1d26d10f910bb82"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QHS4SJYM2W27OMF3ED6WILP56K/bundle.json","state_url":"https://pith.science/pith/QHS4SJYM2W27OMF3ED6WILP56K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QHS4SJYM2W27OMF3ED6WILP56K/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":"2026-08-07T16:00:16Z","links":{"resolver":"https://pith.science/pith/QHS4SJYM2W27OMF3ED6WILP56K","bundle":"https://pith.science/pith/QHS4SJYM2W27OMF3ED6WILP56K/bundle.json","state":"https://pith.science/pith/QHS4SJYM2W27OMF3ED6WILP56K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QHS4SJYM2W27OMF3ED6WILP56K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QHS4SJYM2W27OMF3ED6WILP56K","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":"30d96ad9c5d43e299c45d90f07ec489ea369f793e43138ffd9ac2f59cc25a9c3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-04T22:13:16Z","title_canon_sha256":"7a3d573fb08316d571bb9b04e16dc6a282f2e1b511da33c1277a88e9670d7dc3"},"schema_version":"1.0","source":{"id":"1912.02280","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.02280","created_at":"2026-07-05T00:28:15Z"},{"alias_kind":"arxiv_version","alias_value":"1912.02280v2","created_at":"2026-07-05T00:28:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.02280","created_at":"2026-07-05T00:28:15Z"},{"alias_kind":"pith_short_12","alias_value":"QHS4SJYM2W27","created_at":"2026-07-05T00:28:15Z"},{"alias_kind":"pith_short_16","alias_value":"QHS4SJYM2W27OMF3","created_at":"2026-07-05T00:28:15Z"},{"alias_kind":"pith_short_8","alias_value":"QHS4SJYM","created_at":"2026-07-05T00:28:15Z"}],"graph_snapshots":[{"event_id":"sha256:67bea4c6e1e1b95eef150b98f76197a53e82d971b8f87189c1d26d10f910bb82","target":"graph","created_at":"2026-07-05T00:28:15Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1912.02280/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning an embedding for a large collection of items is a popular approach to overcome the computational limitations associated to one-hot encodings. The aim of item embedding is to learn a low dimensional space for the representations, able to capture with its geometry relevant features or relationships for the data at hand. This can be achieved for example by exploiting adjacencies among items in large sets of unlabelled data. In this paper we interpret in an Information Geometric framework the item embeddings obtained from conditional models. By exploiting the $\\alpha$-geometry of the expo","authors_text":"Luigi Malag\\`o, Riccardo Volpi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-04T22:13:16Z","title":"Natural Alpha Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.02280","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:c74c2da800709f2c768ac023a8bce315531397449337dad17cdd557349ff8ae1","target":"record","created_at":"2026-07-05T00:28:15Z","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":"30d96ad9c5d43e299c45d90f07ec489ea369f793e43138ffd9ac2f59cc25a9c3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-04T22:13:16Z","title_canon_sha256":"7a3d573fb08316d571bb9b04e16dc6a282f2e1b511da33c1277a88e9670d7dc3"},"schema_version":"1.0","source":{"id":"1912.02280","kind":"arxiv","version":2}},"canonical_sha256":"81e5c9270cd5b5f730bb20fd642dfdf2998df96b3143d4013b771281c0d67d8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81e5c9270cd5b5f730bb20fd642dfdf2998df96b3143d4013b771281c0d67d8a","first_computed_at":"2026-07-05T00:28:15.757543Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:28:15.757543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IutIdonjH/S+RB3cO06wWdb/oDeRgC0fKD4W/e3f3Ryxws6tcdhj1qWxlIus7c4sxgWVZ9uSaq7YVIYrBL8aAA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:28:15.758018Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.02280","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c74c2da800709f2c768ac023a8bce315531397449337dad17cdd557349ff8ae1","sha256:67bea4c6e1e1b95eef150b98f76197a53e82d971b8f87189c1d26d10f910bb82"],"state_sha256":"3b137080f1cd889331a0d22ab8bf073a1a777d4e3ac347ecbab9e1ca1a170aa0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7UpqITz8H802jIqqilgnbL2vZLOWtd5jB8KSz5I8LE9gWDhNtkdegXER6FSPmX4egyZ8kYmjRoJu9at/urn/Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:00:16.613302Z","bundle_sha256":"133dfd309fa54d1a6ce560ee42b2f13e576c064a74fe71b483f2db5b721bf67c"}}