{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HB3TIOG23RPQILU3IYKUEASJFB","short_pith_number":"pith:HB3TIOG2","schema_version":"1.0","canonical_sha256":"38773438dadc5f042e9b4615420249286d1f8eddc5508ebb7f96930fcd828a4a","source":{"kind":"arxiv","id":"2507.23402","version":1},"attestation_state":"computed","paper":{"title":"AGA: An adaptive group alignment framework for structured medical cross-modal representation learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiao Li, Wei Li, Xiaobin Sun, Xun Gong","submitted_at":"2025-07-31T10:14:49Z","abstract_excerpt":"Learning medical visual representations from paired images and reports is a promising direction in representation learning. However, current vision-language pretraining methods in the medical domain often simplify clinical reports into single entities or fragmented tokens, ignoring their inherent structure. In addition, contrastive learning frameworks typically depend on large quantities of hard negative samples, which is impractical for small-scale medical datasets. To tackle these challenges, we propose Adaptive Grouped Alignment (AGA), a new framework that captures structured semantics from"},"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":"2507.23402","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-31T10:14:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"53ed58dd78d222e5754883dcae6f523dff208c7f221ff30dc33f2a2c4980b4d8","abstract_canon_sha256":"7b0b24498382a9e63c9beb9ca81e3819ce1c10809b44e9f42e5611fb934b9ab1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:11.503515Z","signature_b64":"FglrS6IIXfp9cDuOmwYq+POwZCn7h0sB78gIwetGVVM2lBeTtfz0IuDtvLrTsB4AtGnHPWEo6xSRiSor3rCuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38773438dadc5f042e9b4615420249286d1f8eddc5508ebb7f96930fcd828a4a","last_reissued_at":"2026-07-05T11:46:11.503004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:11.503004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AGA: An adaptive group alignment framework for structured medical cross-modal representation learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiao Li, Wei Li, Xiaobin Sun, Xun Gong","submitted_at":"2025-07-31T10:14:49Z","abstract_excerpt":"Learning medical visual representations from paired images and reports is a promising direction in representation learning. However, current vision-language pretraining methods in the medical domain often simplify clinical reports into single entities or fragmented tokens, ignoring their inherent structure. In addition, contrastive learning frameworks typically depend on large quantities of hard negative samples, which is impractical for small-scale medical datasets. To tackle these challenges, we propose Adaptive Grouped Alignment (AGA), a new framework that captures structured semantics from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23402","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/2507.23402/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":"2507.23402","created_at":"2026-07-05T11:46:11.503069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.23402v1","created_at":"2026-07-05T11:46:11.503069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23402","created_at":"2026-07-05T11:46:11.503069+00:00"},{"alias_kind":"pith_short_12","alias_value":"HB3TIOG23RPQ","created_at":"2026-07-05T11:46:11.503069+00:00"},{"alias_kind":"pith_short_16","alias_value":"HB3TIOG23RPQILU3","created_at":"2026-07-05T11:46:11.503069+00:00"},{"alias_kind":"pith_short_8","alias_value":"HB3TIOG2","created_at":"2026-07-05T11:46:11.503069+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HB3TIOG23RPQILU3IYKUEASJFB","json":"https://pith.science/pith/HB3TIOG23RPQILU3IYKUEASJFB.json","graph_json":"https://pith.science/api/pith-number/HB3TIOG23RPQILU3IYKUEASJFB/graph.json","events_json":"https://pith.science/api/pith-number/HB3TIOG23RPQILU3IYKUEASJFB/events.json","paper":"https://pith.science/paper/HB3TIOG2"},"agent_actions":{"view_html":"https://pith.science/pith/HB3TIOG23RPQILU3IYKUEASJFB","download_json":"https://pith.science/pith/HB3TIOG23RPQILU3IYKUEASJFB.json","view_paper":"https://pith.science/paper/HB3TIOG2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.23402&json=true","fetch_graph":"https://pith.science/api/pith-number/HB3TIOG23RPQILU3IYKUEASJFB/graph.json","fetch_events":"https://pith.science/api/pith-number/HB3TIOG23RPQILU3IYKUEASJFB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HB3TIOG23RPQILU3IYKUEASJFB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HB3TIOG23RPQILU3IYKUEASJFB/action/storage_attestation","attest_author":"https://pith.science/pith/HB3TIOG23RPQILU3IYKUEASJFB/action/author_attestation","sign_citation":"https://pith.science/pith/HB3TIOG23RPQILU3IYKUEASJFB/action/citation_signature","submit_replication":"https://pith.science/pith/HB3TIOG23RPQILU3IYKUEASJFB/action/replication_record"}},"created_at":"2026-07-05T11:46:11.503069+00:00","updated_at":"2026-07-05T11:46:11.503069+00:00"}