{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QRMTFCWX227I32EPYNXOWCFB3V","short_pith_number":"pith:QRMTFCWX","canonical_record":{"source":{"id":"2606.11682","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T05:52:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0d910bb4bbb3f35b8c147656b715234c12a4205231a421159d84f6ecc6fb4fd2","abstract_canon_sha256":"72124728f7d1f3fdb555c1eacb1312775cfe9517f96a527311b2543a1d6a2853"},"schema_version":"1.0"},"canonical_sha256":"8459328ad7d6be8de88fc36eeb08a1dd7c4ed1937c875df00e1119263e0c08f7","source":{"kind":"arxiv","id":"2606.11682","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11682","created_at":"2026-06-11T01:10:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11682v1","created_at":"2026-06-11T01:10:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11682","created_at":"2026-06-11T01:10:02Z"},{"alias_kind":"pith_short_12","alias_value":"QRMTFCWX227I","created_at":"2026-06-11T01:10:02Z"},{"alias_kind":"pith_short_16","alias_value":"QRMTFCWX227I32EP","created_at":"2026-06-11T01:10:02Z"},{"alias_kind":"pith_short_8","alias_value":"QRMTFCWX","created_at":"2026-06-11T01:10:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QRMTFCWX227I32EPYNXOWCFB3V","target":"record","payload":{"canonical_record":{"source":{"id":"2606.11682","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T05:52:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0d910bb4bbb3f35b8c147656b715234c12a4205231a421159d84f6ecc6fb4fd2","abstract_canon_sha256":"72124728f7d1f3fdb555c1eacb1312775cfe9517f96a527311b2543a1d6a2853"},"schema_version":"1.0"},"canonical_sha256":"8459328ad7d6be8de88fc36eeb08a1dd7c4ed1937c875df00e1119263e0c08f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:02.595402Z","signature_b64":"cJofpgOF1VcwRe3JOD/aPmFgy5EqSFxWCTmyGJ5WD3RVjmWa2wCrk66SfFunTnP/8K6PkAEhwF+Iz1FjIgWRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8459328ad7d6be8de88fc36eeb08a1dd7c4ed1937c875df00e1119263e0c08f7","last_reissued_at":"2026-06-11T01:10:02.594714Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:02.594714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.11682","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-11T01:10:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7GrBqSC6PUKlB+WuQpeJXFBM3gAZnYUTeG/IFsxw4AAv6vu4Q8K9AZcC7VYjOhkyLfh+UXpXuAXQ3wyR0bS2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T22:07:13.865495Z"},"content_sha256":"a84c070880f7e509f6971333699573eb92c5542c1f2aaee9b1a52a1bdf01445f","schema_version":"1.0","event_id":"sha256:a84c070880f7e509f6971333699573eb92c5542c1f2aaee9b1a52a1bdf01445f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QRMTFCWX227I32EPYNXOWCFB3V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Parameter-Efficient Adapter Tuning for Tabular-Image Multimodal Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiaqi Luo","submitted_at":"2026-06-10T05:52:12Z","abstract_excerpt":"Tabular-image multimodal learning aims to improve predictive modeling by jointly using structured tabular attributes and visual data. Although pretrained encoders provide strong modality-specific representations, full fine-tuning can be computationally expensive, while keeping encoders frozen may limit task-specific adaptation. We propose the Tabular-Image Adapter (TI-Adapter), a modality-specific adapter-based fine-tuning framework for efficient multimodal adaptation. TI-Adapter freezes the pretrained tabular encoder and learns an adapter after the extracted tabular embedding, while adapting "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11682","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/2606.11682/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":"2026-06-11T01:10:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a94F3doyAJMOnZU6fRqThNN75Dxwww91EfhsX7Gm+huunhd1xFOetqcnO/gbuhA7QJh2B1j6+KcLeh9yyDIvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T22:07:13.865878Z"},"content_sha256":"5a09f9be7d02994b71e19931f7c84b7cc7a9ae0618f2d83e3f888fe9a22ae045","schema_version":"1.0","event_id":"sha256:5a09f9be7d02994b71e19931f7c84b7cc7a9ae0618f2d83e3f888fe9a22ae045"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QRMTFCWX227I32EPYNXOWCFB3V/bundle.json","state_url":"https://pith.science/pith/QRMTFCWX227I32EPYNXOWCFB3V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QRMTFCWX227I32EPYNXOWCFB3V/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":"2026-06-20T22:07:13Z","links":{"resolver":"https://pith.science/pith/QRMTFCWX227I32EPYNXOWCFB3V","bundle":"https://pith.science/pith/QRMTFCWX227I32EPYNXOWCFB3V/bundle.json","state":"https://pith.science/pith/QRMTFCWX227I32EPYNXOWCFB3V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QRMTFCWX227I32EPYNXOWCFB3V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QRMTFCWX227I32EPYNXOWCFB3V","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":"72124728f7d1f3fdb555c1eacb1312775cfe9517f96a527311b2543a1d6a2853","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T05:52:12Z","title_canon_sha256":"0d910bb4bbb3f35b8c147656b715234c12a4205231a421159d84f6ecc6fb4fd2"},"schema_version":"1.0","source":{"id":"2606.11682","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11682","created_at":"2026-06-11T01:10:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11682v1","created_at":"2026-06-11T01:10:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11682","created_at":"2026-06-11T01:10:02Z"},{"alias_kind":"pith_short_12","alias_value":"QRMTFCWX227I","created_at":"2026-06-11T01:10:02Z"},{"alias_kind":"pith_short_16","alias_value":"QRMTFCWX227I32EP","created_at":"2026-06-11T01:10:02Z"},{"alias_kind":"pith_short_8","alias_value":"QRMTFCWX","created_at":"2026-06-11T01:10:02Z"}],"graph_snapshots":[{"event_id":"sha256:5a09f9be7d02994b71e19931f7c84b7cc7a9ae0618f2d83e3f888fe9a22ae045","target":"graph","created_at":"2026-06-11T01:10:02Z","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/2606.11682/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tabular-image multimodal learning aims to improve predictive modeling by jointly using structured tabular attributes and visual data. Although pretrained encoders provide strong modality-specific representations, full fine-tuning can be computationally expensive, while keeping encoders frozen may limit task-specific adaptation. We propose the Tabular-Image Adapter (TI-Adapter), a modality-specific adapter-based fine-tuning framework for efficient multimodal adaptation. TI-Adapter freezes the pretrained tabular encoder and learns an adapter after the extracted tabular embedding, while adapting ","authors_text":"Jiaqi Luo","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T05:52:12Z","title":"Parameter-Efficient Adapter Tuning for Tabular-Image Multimodal Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11682","kind":"arxiv","version":1},"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:a84c070880f7e509f6971333699573eb92c5542c1f2aaee9b1a52a1bdf01445f","target":"record","created_at":"2026-06-11T01:10:02Z","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":"72124728f7d1f3fdb555c1eacb1312775cfe9517f96a527311b2543a1d6a2853","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T05:52:12Z","title_canon_sha256":"0d910bb4bbb3f35b8c147656b715234c12a4205231a421159d84f6ecc6fb4fd2"},"schema_version":"1.0","source":{"id":"2606.11682","kind":"arxiv","version":1}},"canonical_sha256":"8459328ad7d6be8de88fc36eeb08a1dd7c4ed1937c875df00e1119263e0c08f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8459328ad7d6be8de88fc36eeb08a1dd7c4ed1937c875df00e1119263e0c08f7","first_computed_at":"2026-06-11T01:10:02.594714Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:10:02.594714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cJofpgOF1VcwRe3JOD/aPmFgy5EqSFxWCTmyGJ5WD3RVjmWa2wCrk66SfFunTnP/8K6PkAEhwF+Iz1FjIgWRCQ==","signature_status":"signed_v1","signed_at":"2026-06-11T01:10:02.595402Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11682","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a84c070880f7e509f6971333699573eb92c5542c1f2aaee9b1a52a1bdf01445f","sha256:5a09f9be7d02994b71e19931f7c84b7cc7a9ae0618f2d83e3f888fe9a22ae045"],"state_sha256":"a4031e9a452785d71c4cada9e67adf2ca04f19c644e3b4a4efefbac976e4ec86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MO+mzezls8E5kej5FgqpbnKfQsMYd0WCOosXWpw1HYLngHsadNhLy465a5ajYUbuvHR+LpcQcGoSL39VyRb/Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T22:07:13.867925Z","bundle_sha256":"61240b7946c8311aafda8ebc5b9481125db0f3f94430a074eadc07907b69c3b6"}}