{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UVLK67D2HHVUUXCUO7LBYRG3AU","short_pith_number":"pith:UVLK67D2","schema_version":"1.0","canonical_sha256":"a556af7c7a39eb4a5c5477d61c44db05275d9f07c82ba893c5ca529f4035ea43","source":{"kind":"arxiv","id":"2411.19719","version":1},"attestation_state":"computed","paper":{"title":"Relative Representations of Latent Spaces enable Efficient Semantic Channel Equalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Emilio Calvanese Strinati, Mohamed Sana, Paolo Di Lorenzo, Simone Fiorellino, Tom\\'as H\\\"uttebr\\\"aucker","submitted_at":"2024-11-29T14:08:48Z","abstract_excerpt":"In multi-user semantic communication, language mismatche poses a significant challenge when independently trained agents interact. We present a novel semantic equalization algorithm that enables communication between agents with different languages without additional retraining. Our algorithm is based on relative representations, a framework that enables different agents employing different neural network models to have unified representation. It proceeds by projecting the latent vectors of different models into a common space defined relative to a set of data samples called \\textit{anchors}, "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.19719","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-29T14:08:48Z","cross_cats_sorted":[],"title_canon_sha256":"1fcb4250f4f0e2f2ea55be72262b4c0d216630cd7474c829ea96a3bd0c6c7eae","abstract_canon_sha256":"5cde5e418abd9301d76e04eff8a331a002cf885294edd0387c43845116010785"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:07.159292Z","signature_b64":"QrXkwq3FCYU26vGEyIOJD3YKPl0pFoRgnCKOXtLLFmvwkE/GEBfwMaQOLhrG44KrxfxNPQB83cVewU7DqmGbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a556af7c7a39eb4a5c5477d61c44db05275d9f07c82ba893c5ca529f4035ea43","last_reissued_at":"2026-07-05T09:42:07.158705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:07.158705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relative Representations of Latent Spaces enable Efficient Semantic Channel Equalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Emilio Calvanese Strinati, Mohamed Sana, Paolo Di Lorenzo, Simone Fiorellino, Tom\\'as H\\\"uttebr\\\"aucker","submitted_at":"2024-11-29T14:08:48Z","abstract_excerpt":"In multi-user semantic communication, language mismatche poses a significant challenge when independently trained agents interact. We present a novel semantic equalization algorithm that enables communication between agents with different languages without additional retraining. Our algorithm is based on relative representations, a framework that enables different agents employing different neural network models to have unified representation. It proceeds by projecting the latent vectors of different models into a common space defined relative to a set of data samples called \\textit{anchors}, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19719","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.19719/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.19719","created_at":"2026-07-05T09:42:07.158765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.19719v1","created_at":"2026-07-05T09:42:07.158765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19719","created_at":"2026-07-05T09:42:07.158765+00:00"},{"alias_kind":"pith_short_12","alias_value":"UVLK67D2HHVU","created_at":"2026-07-05T09:42:07.158765+00:00"},{"alias_kind":"pith_short_16","alias_value":"UVLK67D2HHVUUXCU","created_at":"2026-07-05T09:42:07.158765+00:00"},{"alias_kind":"pith_short_8","alias_value":"UVLK67D2","created_at":"2026-07-05T09:42:07.158765+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30596","citing_title":"Improving Relative Representations with Learned Anchors and Whitened Inner Products","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UVLK67D2HHVUUXCUO7LBYRG3AU","json":"https://pith.science/pith/UVLK67D2HHVUUXCUO7LBYRG3AU.json","graph_json":"https://pith.science/api/pith-number/UVLK67D2HHVUUXCUO7LBYRG3AU/graph.json","events_json":"https://pith.science/api/pith-number/UVLK67D2HHVUUXCUO7LBYRG3AU/events.json","paper":"https://pith.science/paper/UVLK67D2"},"agent_actions":{"view_html":"https://pith.science/pith/UVLK67D2HHVUUXCUO7LBYRG3AU","download_json":"https://pith.science/pith/UVLK67D2HHVUUXCUO7LBYRG3AU.json","view_paper":"https://pith.science/paper/UVLK67D2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.19719&json=true","fetch_graph":"https://pith.science/api/pith-number/UVLK67D2HHVUUXCUO7LBYRG3AU/graph.json","fetch_events":"https://pith.science/api/pith-number/UVLK67D2HHVUUXCUO7LBYRG3AU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UVLK67D2HHVUUXCUO7LBYRG3AU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UVLK67D2HHVUUXCUO7LBYRG3AU/action/storage_attestation","attest_author":"https://pith.science/pith/UVLK67D2HHVUUXCUO7LBYRG3AU/action/author_attestation","sign_citation":"https://pith.science/pith/UVLK67D2HHVUUXCUO7LBYRG3AU/action/citation_signature","submit_replication":"https://pith.science/pith/UVLK67D2HHVUUXCUO7LBYRG3AU/action/replication_record"}},"created_at":"2026-07-05T09:42:07.158765+00:00","updated_at":"2026-07-05T09:42:07.158765+00:00"}