{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JAIBWS5L6KPXJ4JKFIXAROVRWZ","short_pith_number":"pith:JAIBWS5L","schema_version":"1.0","canonical_sha256":"48101b4babf29f74f12a2a2e08bab1b64b93994ef0a8eeedbeb823203d99a990","source":{"kind":"arxiv","id":"2412.03871","version":2},"attestation_state":"computed","paper":{"title":"CLIP-PING: Boosting Lightweight Vision-Language Models with Proximus Intrinsic Neighbors Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.ET","cs.IR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Choong Seon Hong, Chu Myaet Thwal, Eui-Nam Huh, Minh N. H. Nguyen, Ye Lin Tun","submitted_at":"2024-12-05T04:58:28Z","abstract_excerpt":"Beyond the success of Contrastive Language-Image Pre-training (CLIP), recent trends mark a shift toward exploring the applicability of lightweight vision-language models for resource-constrained scenarios. These models often deliver suboptimal performance when relying solely on a single image-text contrastive learning objective, spotlighting the need for more effective training mechanisms that guarantee robust cross-modal feature alignment. In this work, we propose CLIP-PING: Contrastive Language-Image Pre-training with Proximus Intrinsic Neighbors Guidance, a novel yet simple and efficient tr"},"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":"2412.03871","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T04:58:28Z","cross_cats_sorted":["cs.AI","cs.ET","cs.IR","cs.MM"],"title_canon_sha256":"73ac5fd87d282b3601ee011a959ab9671a2beb96f3089f18d58dadf2b596aab6","abstract_canon_sha256":"a9a33cb2248b85f6776d32752538a96c1fdcee1edd6a3a04e512bc2e10cf4fe4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:32.370392Z","signature_b64":"p23DYuaLtycJLEUYKrsZSAyDYai4+6Fpqix2XngBP93MQr6U3cwP/uggiCGmrJyH/uwUGSUJ7HSdYftMHpj2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48101b4babf29f74f12a2a2e08bab1b64b93994ef0a8eeedbeb823203d99a990","last_reissued_at":"2026-07-05T10:36:32.369820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:32.369820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIP-PING: Boosting Lightweight Vision-Language Models with Proximus Intrinsic Neighbors Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.ET","cs.IR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Choong Seon Hong, Chu Myaet Thwal, Eui-Nam Huh, Minh N. H. Nguyen, Ye Lin Tun","submitted_at":"2024-12-05T04:58:28Z","abstract_excerpt":"Beyond the success of Contrastive Language-Image Pre-training (CLIP), recent trends mark a shift toward exploring the applicability of lightweight vision-language models for resource-constrained scenarios. These models often deliver suboptimal performance when relying solely on a single image-text contrastive learning objective, spotlighting the need for more effective training mechanisms that guarantee robust cross-modal feature alignment. In this work, we propose CLIP-PING: Contrastive Language-Image Pre-training with Proximus Intrinsic Neighbors Guidance, a novel yet simple and efficient tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03871","kind":"arxiv","version":2},"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/2412.03871/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":"2412.03871","created_at":"2026-07-05T10:36:32.369884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03871v2","created_at":"2026-07-05T10:36:32.369884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03871","created_at":"2026-07-05T10:36:32.369884+00:00"},{"alias_kind":"pith_short_12","alias_value":"JAIBWS5L6KPX","created_at":"2026-07-05T10:36:32.369884+00:00"},{"alias_kind":"pith_short_16","alias_value":"JAIBWS5L6KPXJ4JK","created_at":"2026-07-05T10:36:32.369884+00:00"},{"alias_kind":"pith_short_8","alias_value":"JAIBWS5L","created_at":"2026-07-05T10:36:32.369884+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/JAIBWS5L6KPXJ4JKFIXAROVRWZ","json":"https://pith.science/pith/JAIBWS5L6KPXJ4JKFIXAROVRWZ.json","graph_json":"https://pith.science/api/pith-number/JAIBWS5L6KPXJ4JKFIXAROVRWZ/graph.json","events_json":"https://pith.science/api/pith-number/JAIBWS5L6KPXJ4JKFIXAROVRWZ/events.json","paper":"https://pith.science/paper/JAIBWS5L"},"agent_actions":{"view_html":"https://pith.science/pith/JAIBWS5L6KPXJ4JKFIXAROVRWZ","download_json":"https://pith.science/pith/JAIBWS5L6KPXJ4JKFIXAROVRWZ.json","view_paper":"https://pith.science/paper/JAIBWS5L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03871&json=true","fetch_graph":"https://pith.science/api/pith-number/JAIBWS5L6KPXJ4JKFIXAROVRWZ/graph.json","fetch_events":"https://pith.science/api/pith-number/JAIBWS5L6KPXJ4JKFIXAROVRWZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JAIBWS5L6KPXJ4JKFIXAROVRWZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JAIBWS5L6KPXJ4JKFIXAROVRWZ/action/storage_attestation","attest_author":"https://pith.science/pith/JAIBWS5L6KPXJ4JKFIXAROVRWZ/action/author_attestation","sign_citation":"https://pith.science/pith/JAIBWS5L6KPXJ4JKFIXAROVRWZ/action/citation_signature","submit_replication":"https://pith.science/pith/JAIBWS5L6KPXJ4JKFIXAROVRWZ/action/replication_record"}},"created_at":"2026-07-05T10:36:32.369884+00:00","updated_at":"2026-07-05T10:36:32.369884+00:00"}