{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SFMIMTVXTULXLH7X6Y3DHCOBJ2","short_pith_number":"pith:SFMIMTVX","canonical_record":{"source":{"id":"2405.16213","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-25T12:51:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5586afd86120831658c1b8ec13bf140dfc9447950e38c97cfcdaff7f989c8526","abstract_canon_sha256":"ffcba68e0071ff814eed7749a664b49c288a57b6b5a234e9af24ff2cc982dfc1"},"schema_version":"1.0"},"canonical_sha256":"9158864eb79d17759ff7f6363389c14eb0eda9c29faa9e2a2ebc94217bd43fef","source":{"kind":"arxiv","id":"2405.16213","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16213","created_at":"2026-07-05T10:48:16Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16213v2","created_at":"2026-07-05T10:48:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16213","created_at":"2026-07-05T10:48:16Z"},{"alias_kind":"pith_short_12","alias_value":"SFMIMTVXTULX","created_at":"2026-07-05T10:48:16Z"},{"alias_kind":"pith_short_16","alias_value":"SFMIMTVXTULXLH7X","created_at":"2026-07-05T10:48:16Z"},{"alias_kind":"pith_short_8","alias_value":"SFMIMTVX","created_at":"2026-07-05T10:48:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SFMIMTVXTULXLH7X6Y3DHCOBJ2","target":"record","payload":{"canonical_record":{"source":{"id":"2405.16213","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-25T12:51:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5586afd86120831658c1b8ec13bf140dfc9447950e38c97cfcdaff7f989c8526","abstract_canon_sha256":"ffcba68e0071ff814eed7749a664b49c288a57b6b5a234e9af24ff2cc982dfc1"},"schema_version":"1.0"},"canonical_sha256":"9158864eb79d17759ff7f6363389c14eb0eda9c29faa9e2a2ebc94217bd43fef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:16.233511Z","signature_b64":"/YBoU1O4wn1NkmjhoQ+ZimYt2jcGdqUKzEAo+lc3pRpY7mSR/mUeL8BJ5fwTboF3h5BuMk5k6SZZnXkZRRNAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9158864eb79d17759ff7f6363389c14eb0eda9c29faa9e2a2ebc94217bd43fef","last_reissued_at":"2026-07-05T10:48:16.233079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:16.233079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.16213","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":"2026-07-05T10:48:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P8BT6ieRpOVSH6JW2AcIbFS7LT8Jj799FJgQALmYXNITKKQl1UNt97lVIAJbcrtyu9sKjQjs8U9GRxaIETNEAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:28:06.795471Z"},"content_sha256":"a0df0771e4c080d66d4b2947a7c13c805e2fb644d35a04136e0603b4d2349a07","schema_version":"1.0","event_id":"sha256:a0df0771e4c080d66d4b2947a7c13c805e2fb644d35a04136e0603b4d2349a07"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SFMIMTVXTULXLH7X6Y3DHCOBJ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Visual-Semantic Subspace Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Hauptmann, Gabriel Moreira, Jo\\~ao Paulo Costeira, Manuel Marques","submitted_at":"2024-05-25T12:51:38Z","abstract_excerpt":"Learning image representations that capture rich semantic relationships remains a significant challenge. Existing approaches are either contrastive, lacking robust theoretical guarantees, or struggle to effectively represent the partial orders inherent to structured visual-semantic data. In this paper, we introduce a nuclear norm-based loss function, grounded in the same information theoretic principles that have proved effective in self-supervised learning. We present a theoretical characterization of this loss, demonstrating that, in addition to promoting class orthogonality, it encodes the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16213","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/2405.16213/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":"2026-07-05T10:48:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WpDS1oOHP5ts7X5h+23hFzXTDjpuF8sHW+1QnQPSje79fUIDiPcXLztrdKvGACRL3wXIDpr2dAZOpvsrdxLMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:28:06.796476Z"},"content_sha256":"78c07daecdb6cd155db1063c9d3c9fa659b00afc0e72eee52e836688da09e9b8","schema_version":"1.0","event_id":"sha256:78c07daecdb6cd155db1063c9d3c9fa659b00afc0e72eee52e836688da09e9b8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SFMIMTVXTULXLH7X6Y3DHCOBJ2/bundle.json","state_url":"https://pith.science/pith/SFMIMTVXTULXLH7X6Y3DHCOBJ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SFMIMTVXTULXLH7X6Y3DHCOBJ2/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":"2026-08-19T11:28:06Z","links":{"resolver":"https://pith.science/pith/SFMIMTVXTULXLH7X6Y3DHCOBJ2","bundle":"https://pith.science/pith/SFMIMTVXTULXLH7X6Y3DHCOBJ2/bundle.json","state":"https://pith.science/pith/SFMIMTVXTULXLH7X6Y3DHCOBJ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SFMIMTVXTULXLH7X6Y3DHCOBJ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SFMIMTVXTULXLH7X6Y3DHCOBJ2","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":"ffcba68e0071ff814eed7749a664b49c288a57b6b5a234e9af24ff2cc982dfc1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-25T12:51:38Z","title_canon_sha256":"5586afd86120831658c1b8ec13bf140dfc9447950e38c97cfcdaff7f989c8526"},"schema_version":"1.0","source":{"id":"2405.16213","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16213","created_at":"2026-07-05T10:48:16Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16213v2","created_at":"2026-07-05T10:48:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16213","created_at":"2026-07-05T10:48:16Z"},{"alias_kind":"pith_short_12","alias_value":"SFMIMTVXTULX","created_at":"2026-07-05T10:48:16Z"},{"alias_kind":"pith_short_16","alias_value":"SFMIMTVXTULXLH7X","created_at":"2026-07-05T10:48:16Z"},{"alias_kind":"pith_short_8","alias_value":"SFMIMTVX","created_at":"2026-07-05T10:48:16Z"}],"graph_snapshots":[{"event_id":"sha256:78c07daecdb6cd155db1063c9d3c9fa659b00afc0e72eee52e836688da09e9b8","target":"graph","created_at":"2026-07-05T10:48:16Z","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/2405.16213/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning image representations that capture rich semantic relationships remains a significant challenge. Existing approaches are either contrastive, lacking robust theoretical guarantees, or struggle to effectively represent the partial orders inherent to structured visual-semantic data. In this paper, we introduce a nuclear norm-based loss function, grounded in the same information theoretic principles that have proved effective in self-supervised learning. We present a theoretical characterization of this loss, demonstrating that, in addition to promoting class orthogonality, it encodes the ","authors_text":"Alexander Hauptmann, Gabriel Moreira, Jo\\~ao Paulo Costeira, Manuel Marques","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-25T12:51:38Z","title":"Learning Visual-Semantic Subspace Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16213","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:a0df0771e4c080d66d4b2947a7c13c805e2fb644d35a04136e0603b4d2349a07","target":"record","created_at":"2026-07-05T10:48:16Z","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":"ffcba68e0071ff814eed7749a664b49c288a57b6b5a234e9af24ff2cc982dfc1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-25T12:51:38Z","title_canon_sha256":"5586afd86120831658c1b8ec13bf140dfc9447950e38c97cfcdaff7f989c8526"},"schema_version":"1.0","source":{"id":"2405.16213","kind":"arxiv","version":2}},"canonical_sha256":"9158864eb79d17759ff7f6363389c14eb0eda9c29faa9e2a2ebc94217bd43fef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9158864eb79d17759ff7f6363389c14eb0eda9c29faa9e2a2ebc94217bd43fef","first_computed_at":"2026-07-05T10:48:16.233079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:16.233079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/YBoU1O4wn1NkmjhoQ+ZimYt2jcGdqUKzEAo+lc3pRpY7mSR/mUeL8BJ5fwTboF3h5BuMk5k6SZZnXkZRRNAAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:16.233511Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16213","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0df0771e4c080d66d4b2947a7c13c805e2fb644d35a04136e0603b4d2349a07","sha256:78c07daecdb6cd155db1063c9d3c9fa659b00afc0e72eee52e836688da09e9b8"],"state_sha256":"5b40dcdeb5ab022961bb7ad16266ec67c3e63d21594f8de92fb96acf32b36b1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZD/sP1WAGNX44VSUoyHorVJpcm4QKK483C6zJQgA/vMLT3MF5qwQ4dfwsmy8cL9b01mik7ZlfYpVhWcM4Ka+Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T11:28:06.801963Z","bundle_sha256":"1ad2f0c2caa9214f61d1825c0b46db6b227812e05c1b311c8a037adadd269109"}}