{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2AWDZ7VJ7DTO4UXSOOSWDYA5AP","short_pith_number":"pith:2AWDZ7VJ","canonical_record":{"source":{"id":"2310.00672","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-01T13:48:36Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"7458d47ec718c256b5d79ff804a84a83ae5c99f001f2c93b554c4cf38c16b5e1","abstract_canon_sha256":"58eb7e0d0069092a1eb7cb8f2ccd8e4f3ba3b48c4e773eecc38bbfcc1196142c"},"schema_version":"1.0"},"canonical_sha256":"d02c3cfea9f8e6ee52f273a561e01d03caed465613e32fa0c84ad4b96c1c77d8","source":{"kind":"arxiv","id":"2310.00672","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.00672","created_at":"2026-07-05T06:58:17Z"},{"alias_kind":"arxiv_version","alias_value":"2310.00672v2","created_at":"2026-07-05T06:58:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00672","created_at":"2026-07-05T06:58:17Z"},{"alias_kind":"pith_short_12","alias_value":"2AWDZ7VJ7DTO","created_at":"2026-07-05T06:58:17Z"},{"alias_kind":"pith_short_16","alias_value":"2AWDZ7VJ7DTO4UXS","created_at":"2026-07-05T06:58:17Z"},{"alias_kind":"pith_short_8","alias_value":"2AWDZ7VJ","created_at":"2026-07-05T06:58:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2AWDZ7VJ7DTO4UXSOOSWDYA5AP","target":"record","payload":{"canonical_record":{"source":{"id":"2310.00672","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-01T13:48:36Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"7458d47ec718c256b5d79ff804a84a83ae5c99f001f2c93b554c4cf38c16b5e1","abstract_canon_sha256":"58eb7e0d0069092a1eb7cb8f2ccd8e4f3ba3b48c4e773eecc38bbfcc1196142c"},"schema_version":"1.0"},"canonical_sha256":"d02c3cfea9f8e6ee52f273a561e01d03caed465613e32fa0c84ad4b96c1c77d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:17.711583Z","signature_b64":"QUFJc4WHru5lBMZAXB6k2JQAIn/stAwc6vbV8E8WK6CjKDwE1zJEUqmDVLVkxwgwEZQLiDVR/bK2UazxnT6TBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d02c3cfea9f8e6ee52f273a561e01d03caed465613e32fa0c84ad4b96c1c77d8","last_reissued_at":"2026-07-05T06:58:17.711066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:17.711066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.00672","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":"2026-07-05T06:58:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yjs5wmZZcghoMzzWNaPlP3OS2uaFQ/hFvjFvDSLilshqCwiLFsFgo3ICc/dYaP2webOao69oOE0YPAENFdtcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T14:45:59.366732Z"},"content_sha256":"cf467bd9110df828b607ea9e702b9076f848e3408541c374070c05599e6b1994","schema_version":"1.0","event_id":"sha256:cf467bd9110df828b607ea9e702b9076f848e3408541c374070c05599e6b1994"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2AWDZ7VJ7DTO4UXSOOSWDYA5AP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GeRA: Label-Efficient Geometrically Regularized Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Dustin Klebe, Justin Solomon, Leonid Karlinsky, Mikhail Yurochkin, Tal Shnitzer","submitted_at":"2023-10-01T13:48:36Z","abstract_excerpt":"Pretrained unimodal encoders incorporate rich semantic information into embedding space structures. To be similarly informative, multi-modal encoders typically require massive amounts of paired data for alignment and training. We introduce a semi-supervised Geometrically Regularized Alignment (GeRA) method to align the embedding spaces of pretrained unimodal encoders in a label-efficient way. Our method leverages the manifold geometry of unpaired (unlabeled) data to improve alignment performance. To prevent distortions to local geometry during the alignment process, potentially disrupting sema"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00672","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/2310.00672/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":"2026-07-05T06:58:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D26GalPdtrt0PnImk6OsqKvcibqkdDEWHZqchm6xvV6hiH6qnXYyeBpwgnTB6OEiwxmcqhcHj68h2TuPSWQSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T14:45:59.367524Z"},"content_sha256":"6043fd7db18c79146717f14f128b7f7e5d16876cf890472e530d74ecfee13ccd","schema_version":"1.0","event_id":"sha256:6043fd7db18c79146717f14f128b7f7e5d16876cf890472e530d74ecfee13ccd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2AWDZ7VJ7DTO4UXSOOSWDYA5AP/bundle.json","state_url":"https://pith.science/pith/2AWDZ7VJ7DTO4UXSOOSWDYA5AP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2AWDZ7VJ7DTO4UXSOOSWDYA5AP/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":"2026-08-19T14:45:59Z","links":{"resolver":"https://pith.science/pith/2AWDZ7VJ7DTO4UXSOOSWDYA5AP","bundle":"https://pith.science/pith/2AWDZ7VJ7DTO4UXSOOSWDYA5AP/bundle.json","state":"https://pith.science/pith/2AWDZ7VJ7DTO4UXSOOSWDYA5AP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2AWDZ7VJ7DTO4UXSOOSWDYA5AP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2AWDZ7VJ7DTO4UXSOOSWDYA5AP","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":"58eb7e0d0069092a1eb7cb8f2ccd8e4f3ba3b48c4e773eecc38bbfcc1196142c","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-01T13:48:36Z","title_canon_sha256":"7458d47ec718c256b5d79ff804a84a83ae5c99f001f2c93b554c4cf38c16b5e1"},"schema_version":"1.0","source":{"id":"2310.00672","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.00672","created_at":"2026-07-05T06:58:17Z"},{"alias_kind":"arxiv_version","alias_value":"2310.00672v2","created_at":"2026-07-05T06:58:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00672","created_at":"2026-07-05T06:58:17Z"},{"alias_kind":"pith_short_12","alias_value":"2AWDZ7VJ7DTO","created_at":"2026-07-05T06:58:17Z"},{"alias_kind":"pith_short_16","alias_value":"2AWDZ7VJ7DTO4UXS","created_at":"2026-07-05T06:58:17Z"},{"alias_kind":"pith_short_8","alias_value":"2AWDZ7VJ","created_at":"2026-07-05T06:58:17Z"}],"graph_snapshots":[{"event_id":"sha256:6043fd7db18c79146717f14f128b7f7e5d16876cf890472e530d74ecfee13ccd","target":"graph","created_at":"2026-07-05T06:58:17Z","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/2310.00672/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained unimodal encoders incorporate rich semantic information into embedding space structures. To be similarly informative, multi-modal encoders typically require massive amounts of paired data for alignment and training. We introduce a semi-supervised Geometrically Regularized Alignment (GeRA) method to align the embedding spaces of pretrained unimodal encoders in a label-efficient way. Our method leverages the manifold geometry of unpaired (unlabeled) data to improve alignment performance. To prevent distortions to local geometry during the alignment process, potentially disrupting sema","authors_text":"Dustin Klebe, Justin Solomon, Leonid Karlinsky, Mikhail Yurochkin, Tal Shnitzer","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-01T13:48:36Z","title":"GeRA: Label-Efficient Geometrically Regularized Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00672","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:cf467bd9110df828b607ea9e702b9076f848e3408541c374070c05599e6b1994","target":"record","created_at":"2026-07-05T06:58:17Z","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":"58eb7e0d0069092a1eb7cb8f2ccd8e4f3ba3b48c4e773eecc38bbfcc1196142c","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-01T13:48:36Z","title_canon_sha256":"7458d47ec718c256b5d79ff804a84a83ae5c99f001f2c93b554c4cf38c16b5e1"},"schema_version":"1.0","source":{"id":"2310.00672","kind":"arxiv","version":2}},"canonical_sha256":"d02c3cfea9f8e6ee52f273a561e01d03caed465613e32fa0c84ad4b96c1c77d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d02c3cfea9f8e6ee52f273a561e01d03caed465613e32fa0c84ad4b96c1c77d8","first_computed_at":"2026-07-05T06:58:17.711066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:58:17.711066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QUFJc4WHru5lBMZAXB6k2JQAIn/stAwc6vbV8E8WK6CjKDwE1zJEUqmDVLVkxwgwEZQLiDVR/bK2UazxnT6TBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:58:17.711583Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.00672","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf467bd9110df828b607ea9e702b9076f848e3408541c374070c05599e6b1994","sha256:6043fd7db18c79146717f14f128b7f7e5d16876cf890472e530d74ecfee13ccd"],"state_sha256":"ea12ce88fc33a06d9024a9619278ffdb9c73110857a1507b31c1857de13d89d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"//A3RxG3wTBg7ZV/qvEfhujpsV9BmkUT0PH3kou63wmak6dJBiJILM0P0svlrMzixDXpzu2xHhkyQb5WG9kDBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T14:45:59.374687Z","bundle_sha256":"9812dac0e5579e7707203ddfbbb321bbe8f6c1ddeb70cf20337ff72995b93791"}}