{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:46JOGQLGIZ4LBN7W6J6S46MJCG","short_pith_number":"pith:46JOGQLG","schema_version":"1.0","canonical_sha256":"e792e341664678b0b7f6f27d2e798911a4d5328e23be133749db7381c424ecd9","source":{"kind":"arxiv","id":"2405.12705","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Adaptive Inference for Document Image Classification with Anytime Early Exiting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jordy Van Landeghem, Marie-Francine Moens, Matthew Blaschko, Omar Hamed, Souhail Bakkali","submitted_at":"2024-05-21T11:52:14Z","abstract_excerpt":"This work addresses the need for a balanced approach between performance and efficiency in scalable production environments for visually-rich document understanding (VDU) tasks. Currently, there is a reliance on large document foundation models that offer advanced capabilities but come with a heavy computational burden. In this paper, we propose a multimodal early exit (EE) model design that incorporates various training strategies, exit layer types and placements. Our goal is to achieve a Pareto-optimal balance between predictive performance and efficiency for multimodal document image classi"},"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":"2405.12705","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-21T11:52:14Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"245c1fbf34b7972318c7417b51830cb3043dd8e1e88ac50c2c57b2a174c238c4","abstract_canon_sha256":"013c8ec4fcf83309bbcddc6be655cd8a5d6b046b9c47f6a5af9447c711aeb2e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:24.285854Z","signature_b64":"59UsAIE8j2K3ZDR3xG7Kup58FJYnpfI20Em4JfwGhjTDr5u7s9CZq6w8RvTlz17MkhrJI/f2km2Pbx5MVs2TCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e792e341664678b0b7f6f27d2e798911a4d5328e23be133749db7381c424ecd9","last_reissued_at":"2026-07-05T08:21:24.285441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:24.285441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Adaptive Inference for Document Image Classification with Anytime Early Exiting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jordy Van Landeghem, Marie-Francine Moens, Matthew Blaschko, Omar Hamed, Souhail Bakkali","submitted_at":"2024-05-21T11:52:14Z","abstract_excerpt":"This work addresses the need for a balanced approach between performance and efficiency in scalable production environments for visually-rich document understanding (VDU) tasks. Currently, there is a reliance on large document foundation models that offer advanced capabilities but come with a heavy computational burden. In this paper, we propose a multimodal early exit (EE) model design that incorporates various training strategies, exit layer types and placements. Our goal is to achieve a Pareto-optimal balance between predictive performance and efficiency for multimodal document image classi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12705","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/2405.12705/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":"2405.12705","created_at":"2026-07-05T08:21:24.285503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.12705v1","created_at":"2026-07-05T08:21:24.285503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12705","created_at":"2026-07-05T08:21:24.285503+00:00"},{"alias_kind":"pith_short_12","alias_value":"46JOGQLGIZ4L","created_at":"2026-07-05T08:21:24.285503+00:00"},{"alias_kind":"pith_short_16","alias_value":"46JOGQLGIZ4LBN7W","created_at":"2026-07-05T08:21:24.285503+00:00"},{"alias_kind":"pith_short_8","alias_value":"46JOGQLG","created_at":"2026-07-05T08:21:24.285503+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/46JOGQLGIZ4LBN7W6J6S46MJCG","json":"https://pith.science/pith/46JOGQLGIZ4LBN7W6J6S46MJCG.json","graph_json":"https://pith.science/api/pith-number/46JOGQLGIZ4LBN7W6J6S46MJCG/graph.json","events_json":"https://pith.science/api/pith-number/46JOGQLGIZ4LBN7W6J6S46MJCG/events.json","paper":"https://pith.science/paper/46JOGQLG"},"agent_actions":{"view_html":"https://pith.science/pith/46JOGQLGIZ4LBN7W6J6S46MJCG","download_json":"https://pith.science/pith/46JOGQLGIZ4LBN7W6J6S46MJCG.json","view_paper":"https://pith.science/paper/46JOGQLG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.12705&json=true","fetch_graph":"https://pith.science/api/pith-number/46JOGQLGIZ4LBN7W6J6S46MJCG/graph.json","fetch_events":"https://pith.science/api/pith-number/46JOGQLGIZ4LBN7W6J6S46MJCG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46JOGQLGIZ4LBN7W6J6S46MJCG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46JOGQLGIZ4LBN7W6J6S46MJCG/action/storage_attestation","attest_author":"https://pith.science/pith/46JOGQLGIZ4LBN7W6J6S46MJCG/action/author_attestation","sign_citation":"https://pith.science/pith/46JOGQLGIZ4LBN7W6J6S46MJCG/action/citation_signature","submit_replication":"https://pith.science/pith/46JOGQLGIZ4LBN7W6J6S46MJCG/action/replication_record"}},"created_at":"2026-07-05T08:21:24.285503+00:00","updated_at":"2026-07-05T08:21:24.285503+00:00"}