{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2JOK26E4WOPFMGSJEZEXOTNBSK","short_pith_number":"pith:2JOK26E4","schema_version":"1.0","canonical_sha256":"d25cad789cb39e561a492649774da1929ef4246c13db99f964b75644fd29ab95","source":{"kind":"arxiv","id":"2507.03531","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Alignment with Cross-Attentive GRUs for Fine-Grained Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Junhwa Kim, Namho Kim","submitted_at":"2025-07-04T12:35:52Z","abstract_excerpt":"Fine-grained video classification requires understanding complex spatio-temporal and semantic cues that often exceed the capacity of a single modality. In this paper, we propose a multimodal framework that fuses video, image, and text representations using GRU-based sequence encoders and cross-modal attention mechanisms. The model is trained using a combination of classification or regression loss, depending on the task, and is further regularized through feature-level augmentation and autoencoding techniques. To evaluate the generality of our framework, we conduct experiments on two challengi"},"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":"2507.03531","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-04T12:35:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"673a6f8a2726a7f306bd5977b2327ab1273114edbd12e360c371619ccbc70705","abstract_canon_sha256":"b239964de152905fe3b324adda494105105f95352ff267dcc70c25c27441a7d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:01.105205Z","signature_b64":"BfiKPjGdOC+NZgFuuoWOvcfwIvXcjQcnYpfCRa7vv+JkEW+YjnyZDD8D2bSmWEDiFxjHTmSBEBXZ9TX7TqOMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d25cad789cb39e561a492649774da1929ef4246c13db99f964b75644fd29ab95","last_reissued_at":"2026-07-05T11:32:01.104721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:01.104721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Alignment with Cross-Attentive GRUs for Fine-Grained Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Junhwa Kim, Namho Kim","submitted_at":"2025-07-04T12:35:52Z","abstract_excerpt":"Fine-grained video classification requires understanding complex spatio-temporal and semantic cues that often exceed the capacity of a single modality. In this paper, we propose a multimodal framework that fuses video, image, and text representations using GRU-based sequence encoders and cross-modal attention mechanisms. The model is trained using a combination of classification or regression loss, depending on the task, and is further regularized through feature-level augmentation and autoencoding techniques. To evaluate the generality of our framework, we conduct experiments on two challengi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03531","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/2507.03531/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":"2507.03531","created_at":"2026-07-05T11:32:01.104783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.03531v1","created_at":"2026-07-05T11:32:01.104783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03531","created_at":"2026-07-05T11:32:01.104783+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JOK26E4WOPF","created_at":"2026-07-05T11:32:01.104783+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JOK26E4WOPFMGSJ","created_at":"2026-07-05T11:32:01.104783+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JOK26E4","created_at":"2026-07-05T11:32:01.104783+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/2JOK26E4WOPFMGSJEZEXOTNBSK","json":"https://pith.science/pith/2JOK26E4WOPFMGSJEZEXOTNBSK.json","graph_json":"https://pith.science/api/pith-number/2JOK26E4WOPFMGSJEZEXOTNBSK/graph.json","events_json":"https://pith.science/api/pith-number/2JOK26E4WOPFMGSJEZEXOTNBSK/events.json","paper":"https://pith.science/paper/2JOK26E4"},"agent_actions":{"view_html":"https://pith.science/pith/2JOK26E4WOPFMGSJEZEXOTNBSK","download_json":"https://pith.science/pith/2JOK26E4WOPFMGSJEZEXOTNBSK.json","view_paper":"https://pith.science/paper/2JOK26E4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.03531&json=true","fetch_graph":"https://pith.science/api/pith-number/2JOK26E4WOPFMGSJEZEXOTNBSK/graph.json","fetch_events":"https://pith.science/api/pith-number/2JOK26E4WOPFMGSJEZEXOTNBSK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JOK26E4WOPFMGSJEZEXOTNBSK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JOK26E4WOPFMGSJEZEXOTNBSK/action/storage_attestation","attest_author":"https://pith.science/pith/2JOK26E4WOPFMGSJEZEXOTNBSK/action/author_attestation","sign_citation":"https://pith.science/pith/2JOK26E4WOPFMGSJEZEXOTNBSK/action/citation_signature","submit_replication":"https://pith.science/pith/2JOK26E4WOPFMGSJEZEXOTNBSK/action/replication_record"}},"created_at":"2026-07-05T11:32:01.104783+00:00","updated_at":"2026-07-05T11:32:01.104783+00:00"}