{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UOSPVVQFIRBAPFANRR3OX2SYW6","short_pith_number":"pith:UOSPVVQF","canonical_record":{"source":{"id":"2503.08497","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-11T14:48:01Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1e6a1ba9ff084465724bfedcccd5167635a26d3d3e9862d2013b046ecb6b73f3","abstract_canon_sha256":"508e4b69d3f34184b4338efb711e47d20ae881fa47987254c9a2f54f2ae94614"},"schema_version":"1.0"},"canonical_sha256":"a3a4fad605444207940d8c76ebea58b7bd037b4e4892f03d82ea5dc91e10b65c","source":{"kind":"arxiv","id":"2503.08497","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08497","created_at":"2026-07-05T10:39:26Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08497v2","created_at":"2026-07-05T10:39:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08497","created_at":"2026-07-05T10:39:26Z"},{"alias_kind":"pith_short_12","alias_value":"UOSPVVQFIRBA","created_at":"2026-07-05T10:39:26Z"},{"alias_kind":"pith_short_16","alias_value":"UOSPVVQFIRBAPFAN","created_at":"2026-07-05T10:39:26Z"},{"alias_kind":"pith_short_8","alias_value":"UOSPVVQF","created_at":"2026-07-05T10:39:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UOSPVVQFIRBAPFANRR3OX2SYW6","target":"record","payload":{"canonical_record":{"source":{"id":"2503.08497","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-11T14:48:01Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1e6a1ba9ff084465724bfedcccd5167635a26d3d3e9862d2013b046ecb6b73f3","abstract_canon_sha256":"508e4b69d3f34184b4338efb711e47d20ae881fa47987254c9a2f54f2ae94614"},"schema_version":"1.0"},"canonical_sha256":"a3a4fad605444207940d8c76ebea58b7bd037b4e4892f03d82ea5dc91e10b65c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:26.888470Z","signature_b64":"LL4astGkBVw9TpeHJQuWdWv0Bzt8g5coNx1EaUvoe7brBPUm4FQfFqdiEoepyat7QAqgH2QAs6J5zq2b9zSwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3a4fad605444207940d8c76ebea58b7bd037b4e4892f03d82ea5dc91e10b65c","last_reissued_at":"2026-07-05T10:39:26.887929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:26.887929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.08497","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":"2026-07-05T10:39:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fuAy0F+C8WqUR3rX9Y/vg/rTr4V1F2hUoUAtGvNcNSOW3Y0ecZ7VpBRHnWNyF1cSxsACHLk1BIoN79Ugt/X6DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:49:45.829114Z"},"content_sha256":"5e7dec230d0ae34d7a9d178e8effa98eac3862d3e25cb086dbc11d5bb178ab9b","schema_version":"1.0","event_id":"sha256:5e7dec230d0ae34d7a9d178e8effa98eac3862d3e25cb086dbc11d5bb178ab9b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UOSPVVQFIRBAPFANRR3OX2SYW6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MMRL: Multi-Modal Representation Learning for Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Xiaodong Gu, Yuncheng Guo","submitted_at":"2025-03-11T14:48:01Z","abstract_excerpt":"Large-scale pre-trained Vision-Language Models (VLMs) have become essential for transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, diminishing their performance on new tasks. To tackle this issue, we propose a novel Multi-Modal Representation Learning (MMRL) framework that introduces a shared, learnable, and modality-agnostic representation space. MMRL projects the space tokens to text and image representation tokens, facilitating more effective multi-modal interactions. Unlike previous approaches that solely optimize c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08497","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/2503.08497/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":"2026-07-05T10:39:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PvQ/bxzOv8NY424oUfEF5vtT7Pe+9ABlqzYqKKru0FPpHfzweuBoZ6U3uSWR+VqVfGD8LI7H0KZ0n/i6dVMDAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:49:45.829682Z"},"content_sha256":"9b28f77c64f12817c7d1aeb8caee7f338aba7fd6a8c377cbb161340df4c5ccc6","schema_version":"1.0","event_id":"sha256:9b28f77c64f12817c7d1aeb8caee7f338aba7fd6a8c377cbb161340df4c5ccc6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UOSPVVQFIRBAPFANRR3OX2SYW6/bundle.json","state_url":"https://pith.science/pith/UOSPVVQFIRBAPFANRR3OX2SYW6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UOSPVVQFIRBAPFANRR3OX2SYW6/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":"2026-08-18T04:49:45Z","links":{"resolver":"https://pith.science/pith/UOSPVVQFIRBAPFANRR3OX2SYW6","bundle":"https://pith.science/pith/UOSPVVQFIRBAPFANRR3OX2SYW6/bundle.json","state":"https://pith.science/pith/UOSPVVQFIRBAPFANRR3OX2SYW6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UOSPVVQFIRBAPFANRR3OX2SYW6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UOSPVVQFIRBAPFANRR3OX2SYW6","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":"508e4b69d3f34184b4338efb711e47d20ae881fa47987254c9a2f54f2ae94614","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-11T14:48:01Z","title_canon_sha256":"1e6a1ba9ff084465724bfedcccd5167635a26d3d3e9862d2013b046ecb6b73f3"},"schema_version":"1.0","source":{"id":"2503.08497","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08497","created_at":"2026-07-05T10:39:26Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08497v2","created_at":"2026-07-05T10:39:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08497","created_at":"2026-07-05T10:39:26Z"},{"alias_kind":"pith_short_12","alias_value":"UOSPVVQFIRBA","created_at":"2026-07-05T10:39:26Z"},{"alias_kind":"pith_short_16","alias_value":"UOSPVVQFIRBAPFAN","created_at":"2026-07-05T10:39:26Z"},{"alias_kind":"pith_short_8","alias_value":"UOSPVVQF","created_at":"2026-07-05T10:39:26Z"}],"graph_snapshots":[{"event_id":"sha256:9b28f77c64f12817c7d1aeb8caee7f338aba7fd6a8c377cbb161340df4c5ccc6","target":"graph","created_at":"2026-07-05T10:39:26Z","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/2503.08497/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale pre-trained Vision-Language Models (VLMs) have become essential for transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, diminishing their performance on new tasks. To tackle this issue, we propose a novel Multi-Modal Representation Learning (MMRL) framework that introduces a shared, learnable, and modality-agnostic representation space. MMRL projects the space tokens to text and image representation tokens, facilitating more effective multi-modal interactions. Unlike previous approaches that solely optimize c","authors_text":"Xiaodong Gu, Yuncheng Guo","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-11T14:48:01Z","title":"MMRL: Multi-Modal Representation Learning for Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08497","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":"sha256:5e7dec230d0ae34d7a9d178e8effa98eac3862d3e25cb086dbc11d5bb178ab9b","target":"record","created_at":"2026-07-05T10:39:26Z","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":"508e4b69d3f34184b4338efb711e47d20ae881fa47987254c9a2f54f2ae94614","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-11T14:48:01Z","title_canon_sha256":"1e6a1ba9ff084465724bfedcccd5167635a26d3d3e9862d2013b046ecb6b73f3"},"schema_version":"1.0","source":{"id":"2503.08497","kind":"arxiv","version":2}},"canonical_sha256":"a3a4fad605444207940d8c76ebea58b7bd037b4e4892f03d82ea5dc91e10b65c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3a4fad605444207940d8c76ebea58b7bd037b4e4892f03d82ea5dc91e10b65c","first_computed_at":"2026-07-05T10:39:26.887929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:26.887929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LL4astGkBVw9TpeHJQuWdWv0Bzt8g5coNx1EaUvoe7brBPUm4FQfFqdiEoepyat7QAqgH2QAs6J5zq2b9zSwCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:26.888470Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.08497","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e7dec230d0ae34d7a9d178e8effa98eac3862d3e25cb086dbc11d5bb178ab9b","sha256:9b28f77c64f12817c7d1aeb8caee7f338aba7fd6a8c377cbb161340df4c5ccc6"],"state_sha256":"4c634258fa4a5c3f1da12883ec51783a1bde792f2808403f1cb493694a2f74a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1+M6VDn+lTzyVE3LQzBoVEnPdhLHR6K9B4PeR/e039POgRCe2aS/1PUiZEhkhONL1cBTLjdxxZNP16bHgoGEDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T04:49:45.834828Z","bundle_sha256":"4b43a947da32156093681a5b2be6a03f885fb74bf8b75069e88d2b30888a1768"}}