{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OF2HKIVZMCD3CED6BZOYD27FTV","short_pith_number":"pith:OF2HKIVZ","canonical_record":{"source":{"id":"2310.15325","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T19:46:41Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"6c5585043a65b6729243fa1b78f966274f00afdce6bfec1c99ccc3932c4d1837","abstract_canon_sha256":"65fdd7ed8e61cfbde17c709526a59ba49fd0ced300674af1ee4e9a829746c317"},"schema_version":"1.0"},"canonical_sha256":"71747522b96087b1107e0e5d81ebe59d7e0bc96296638e5deda94d2fc9e56781","source":{"kind":"arxiv","id":"2310.15325","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.15325","created_at":"2026-07-05T07:04:24Z"},{"alias_kind":"arxiv_version","alias_value":"2310.15325v1","created_at":"2026-07-05T07:04:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15325","created_at":"2026-07-05T07:04:24Z"},{"alias_kind":"pith_short_12","alias_value":"OF2HKIVZMCD3","created_at":"2026-07-05T07:04:24Z"},{"alias_kind":"pith_short_16","alias_value":"OF2HKIVZMCD3CED6","created_at":"2026-07-05T07:04:24Z"},{"alias_kind":"pith_short_8","alias_value":"OF2HKIVZ","created_at":"2026-07-05T07:04:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OF2HKIVZMCD3CED6BZOYD27FTV","target":"record","payload":{"canonical_record":{"source":{"id":"2310.15325","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T19:46:41Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"6c5585043a65b6729243fa1b78f966274f00afdce6bfec1c99ccc3932c4d1837","abstract_canon_sha256":"65fdd7ed8e61cfbde17c709526a59ba49fd0ced300674af1ee4e9a829746c317"},"schema_version":"1.0"},"canonical_sha256":"71747522b96087b1107e0e5d81ebe59d7e0bc96296638e5deda94d2fc9e56781","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:24.562392Z","signature_b64":"46Rdv8L86YPX8ijdz9V3uXD941R18xh53oM6P2epVytNoo40m/mC8JtPFiyoY2BISCtSzC0mZDcYApsllR7zCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71747522b96087b1107e0e5d81ebe59d7e0bc96296638e5deda94d2fc9e56781","last_reissued_at":"2026-07-05T07:04:24.562010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:24.562010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.15325","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":"2026-07-05T07:04:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZecFYTQ0xHJlXUjxX/XHICRbXBMrcdDJY0Y7NQBiBtVwKPlqT982tj05Z7ZS0ypLtOKRXIfj3f1nWw6WUzGBDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:54:04.348989Z"},"content_sha256":"5419ac8a7c730eb844239c5f34ec2c02c89c706282da185e5d5f576e10ea7452","schema_version":"1.0","event_id":"sha256:5419ac8a7c730eb844239c5f34ec2c02c89c706282da185e5d5f576e10ea7452"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OF2HKIVZMCD3CED6BZOYD27FTV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LXMERT Model Compression for Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ghazaleh Mahmoudi, Hadi Sheikhi, Maryam Hashemi, Sara Kodeiri, Sauleh Eetemadi","submitted_at":"2023-10-23T19:46:41Z","abstract_excerpt":"Large-scale pretrained models such as LXMERT are becoming popular for learning cross-modal representations on text-image pairs for vision-language tasks. According to the lottery ticket hypothesis, NLP and computer vision models contain smaller subnetworks capable of being trained in isolation to full performance. In this paper, we combine these observations to evaluate whether such trainable subnetworks exist in LXMERT when fine-tuned on the VQA task. In addition, we perform a model size cost-benefit analysis by investigating how much pruning can be done without significant loss in accuracy. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15325","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/2310.15325/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":"2026-07-05T07:04:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xUGPJcYTpFiO8c3LH6anwL4RXPOLFPESdXPLgjevC5qRWvw/7ZoKXuNUVm+DkR0ZDE6k5Vng/V2YJw44S18mBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:54:04.351722Z"},"content_sha256":"78108dab52032f184e24c2c94827f27dd0fc95a9a14ae74210bce18354391453","schema_version":"1.0","event_id":"sha256:78108dab52032f184e24c2c94827f27dd0fc95a9a14ae74210bce18354391453"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OF2HKIVZMCD3CED6BZOYD27FTV/bundle.json","state_url":"https://pith.science/pith/OF2HKIVZMCD3CED6BZOYD27FTV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OF2HKIVZMCD3CED6BZOYD27FTV/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":"2026-08-07T20:54:04Z","links":{"resolver":"https://pith.science/pith/OF2HKIVZMCD3CED6BZOYD27FTV","bundle":"https://pith.science/pith/OF2HKIVZMCD3CED6BZOYD27FTV/bundle.json","state":"https://pith.science/pith/OF2HKIVZMCD3CED6BZOYD27FTV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OF2HKIVZMCD3CED6BZOYD27FTV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OF2HKIVZMCD3CED6BZOYD27FTV","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":"65fdd7ed8e61cfbde17c709526a59ba49fd0ced300674af1ee4e9a829746c317","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T19:46:41Z","title_canon_sha256":"6c5585043a65b6729243fa1b78f966274f00afdce6bfec1c99ccc3932c4d1837"},"schema_version":"1.0","source":{"id":"2310.15325","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.15325","created_at":"2026-07-05T07:04:24Z"},{"alias_kind":"arxiv_version","alias_value":"2310.15325v1","created_at":"2026-07-05T07:04:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15325","created_at":"2026-07-05T07:04:24Z"},{"alias_kind":"pith_short_12","alias_value":"OF2HKIVZMCD3","created_at":"2026-07-05T07:04:24Z"},{"alias_kind":"pith_short_16","alias_value":"OF2HKIVZMCD3CED6","created_at":"2026-07-05T07:04:24Z"},{"alias_kind":"pith_short_8","alias_value":"OF2HKIVZ","created_at":"2026-07-05T07:04:24Z"}],"graph_snapshots":[{"event_id":"sha256:78108dab52032f184e24c2c94827f27dd0fc95a9a14ae74210bce18354391453","target":"graph","created_at":"2026-07-05T07:04:24Z","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/2310.15325/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale pretrained models such as LXMERT are becoming popular for learning cross-modal representations on text-image pairs for vision-language tasks. According to the lottery ticket hypothesis, NLP and computer vision models contain smaller subnetworks capable of being trained in isolation to full performance. In this paper, we combine these observations to evaluate whether such trainable subnetworks exist in LXMERT when fine-tuned on the VQA task. In addition, we perform a model size cost-benefit analysis by investigating how much pruning can be done without significant loss in accuracy. ","authors_text":"Ghazaleh Mahmoudi, Hadi Sheikhi, Maryam Hashemi, Sara Kodeiri, Sauleh Eetemadi","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T19:46:41Z","title":"LXMERT Model Compression for Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15325","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":"sha256:5419ac8a7c730eb844239c5f34ec2c02c89c706282da185e5d5f576e10ea7452","target":"record","created_at":"2026-07-05T07:04:24Z","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":"65fdd7ed8e61cfbde17c709526a59ba49fd0ced300674af1ee4e9a829746c317","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T19:46:41Z","title_canon_sha256":"6c5585043a65b6729243fa1b78f966274f00afdce6bfec1c99ccc3932c4d1837"},"schema_version":"1.0","source":{"id":"2310.15325","kind":"arxiv","version":1}},"canonical_sha256":"71747522b96087b1107e0e5d81ebe59d7e0bc96296638e5deda94d2fc9e56781","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71747522b96087b1107e0e5d81ebe59d7e0bc96296638e5deda94d2fc9e56781","first_computed_at":"2026-07-05T07:04:24.562010Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:24.562010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"46Rdv8L86YPX8ijdz9V3uXD941R18xh53oM6P2epVytNoo40m/mC8JtPFiyoY2BISCtSzC0mZDcYApsllR7zCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:24.562392Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.15325","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5419ac8a7c730eb844239c5f34ec2c02c89c706282da185e5d5f576e10ea7452","sha256:78108dab52032f184e24c2c94827f27dd0fc95a9a14ae74210bce18354391453"],"state_sha256":"da5a8aa10232464a631b092d25dcbf1be7803fafe737111bd42687fda8ff8f85"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IkutoCSo5/KjPgT6rVnV4hDSs6beXYeJiNk+00oQFt9vGULIVyLy+tCBAlDZ59l4+s2YHLG75AtfBat8gtbSDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T20:54:04.358408Z","bundle_sha256":"0f361ab72b9c41e25fd5ed409917b18ce98e00f6bede36982f98e5d98f5af7d9"}}