{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:L4VSSIR5ZLGFCY4SBT6EZU55DS","short_pith_number":"pith:L4VSSIR5","canonical_record":{"source":{"id":"2302.05016","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-10T02:22:44Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"415cdd632406317bd7370d262ba25cab57a69cb5aedc6869af99e1dc1d5e8727","abstract_canon_sha256":"27b2247a940b93609c130bbf8fb9ae48c59e31751fe6cef4111947e03397ae4f"},"schema_version":"1.0"},"canonical_sha256":"5f2b29223dcacc5163920cfc4cd3bd1c9607c0774747adf8b92bef3526e2140f","source":{"kind":"arxiv","id":"2302.05016","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.05016","created_at":"2026-07-05T06:01:17Z"},{"alias_kind":"arxiv_version","alias_value":"2302.05016v2","created_at":"2026-07-05T06:01:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05016","created_at":"2026-07-05T06:01:17Z"},{"alias_kind":"pith_short_12","alias_value":"L4VSSIR5ZLGF","created_at":"2026-07-05T06:01:17Z"},{"alias_kind":"pith_short_16","alias_value":"L4VSSIR5ZLGFCY4S","created_at":"2026-07-05T06:01:17Z"},{"alias_kind":"pith_short_8","alias_value":"L4VSSIR5","created_at":"2026-07-05T06:01:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:L4VSSIR5ZLGFCY4SBT6EZU55DS","target":"record","payload":{"canonical_record":{"source":{"id":"2302.05016","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-10T02:22:44Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"415cdd632406317bd7370d262ba25cab57a69cb5aedc6869af99e1dc1d5e8727","abstract_canon_sha256":"27b2247a940b93609c130bbf8fb9ae48c59e31751fe6cef4111947e03397ae4f"},"schema_version":"1.0"},"canonical_sha256":"5f2b29223dcacc5163920cfc4cd3bd1c9607c0774747adf8b92bef3526e2140f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:01:17.110558Z","signature_b64":"4VK2pvpPA9edzY4zoo92Ns0Jy62wRIpolV6AiFHBAUFssexMKV/M9q+x2CK/1KuMP0B0pRTBH5jyjl6uvJ06Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f2b29223dcacc5163920cfc4cd3bd1c9607c0774747adf8b92bef3526e2140f","last_reissued_at":"2026-07-05T06:01:17.109888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:01:17.109888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.05016","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:01:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cCkHJT+gRTfe5wAjDwsPsSDmlHyjcaFhwCoHK99Ew8oJ55cV0goAyC/nB9BcxToYQDgD2hZ1ZLOny5omD9RqAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:12:10.928354Z"},"content_sha256":"c2e88741605cee7ec9372c6f727d75386d08caec08ee3a5ef136a9c3b429e71b","schema_version":"1.0","event_id":"sha256:c2e88741605cee7ec9372c6f727d75386d08caec08ee3a5ef136a9c3b429e71b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:L4VSSIR5ZLGFCY4SBT6EZU55DS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is Multimodal Vision Supervision Beneficial to Language?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Avinash Madasu, Vasudev Lal","submitted_at":"2023-02-10T02:22:44Z","abstract_excerpt":"Vision (image and video) - Language (VL) pre-training is the recent popular paradigm that achieved state-of-the-art results on multi-modal tasks like image-retrieval, video-retrieval, visual question answering etc. These models are trained in an unsupervised way and greatly benefit from the complementary modality supervision. In this paper, we explore if the language representations trained using vision supervision perform better than vanilla language representations on Natural Language Understanding and commonsense reasoning benchmarks. We experiment with a diverse set of image-text models su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05016","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/2302.05016/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":"2026-07-05T06:01:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R2KMzUVaR58aQM8GzoZ48uyllNX/6MVFIA/Ok0p5GbRoL3k+oC9mQsTqAX8H9kgchvecubUrqRTMpw1m49ILAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:12:10.928780Z"},"content_sha256":"077d83534e5055e62d32dac0e4029883e38e6b2a53c05b600096b5a7bff395db","schema_version":"1.0","event_id":"sha256:077d83534e5055e62d32dac0e4029883e38e6b2a53c05b600096b5a7bff395db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L4VSSIR5ZLGFCY4SBT6EZU55DS/bundle.json","state_url":"https://pith.science/pith/L4VSSIR5ZLGFCY4SBT6EZU55DS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L4VSSIR5ZLGFCY4SBT6EZU55DS/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":"2026-07-07T04:12:10Z","links":{"resolver":"https://pith.science/pith/L4VSSIR5ZLGFCY4SBT6EZU55DS","bundle":"https://pith.science/pith/L4VSSIR5ZLGFCY4SBT6EZU55DS/bundle.json","state":"https://pith.science/pith/L4VSSIR5ZLGFCY4SBT6EZU55DS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L4VSSIR5ZLGFCY4SBT6EZU55DS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:L4VSSIR5ZLGFCY4SBT6EZU55DS","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":"27b2247a940b93609c130bbf8fb9ae48c59e31751fe6cef4111947e03397ae4f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-10T02:22:44Z","title_canon_sha256":"415cdd632406317bd7370d262ba25cab57a69cb5aedc6869af99e1dc1d5e8727"},"schema_version":"1.0","source":{"id":"2302.05016","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.05016","created_at":"2026-07-05T06:01:17Z"},{"alias_kind":"arxiv_version","alias_value":"2302.05016v2","created_at":"2026-07-05T06:01:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05016","created_at":"2026-07-05T06:01:17Z"},{"alias_kind":"pith_short_12","alias_value":"L4VSSIR5ZLGF","created_at":"2026-07-05T06:01:17Z"},{"alias_kind":"pith_short_16","alias_value":"L4VSSIR5ZLGFCY4S","created_at":"2026-07-05T06:01:17Z"},{"alias_kind":"pith_short_8","alias_value":"L4VSSIR5","created_at":"2026-07-05T06:01:17Z"}],"graph_snapshots":[{"event_id":"sha256:077d83534e5055e62d32dac0e4029883e38e6b2a53c05b600096b5a7bff395db","target":"graph","created_at":"2026-07-05T06:01:17Z","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/2302.05016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision (image and video) - Language (VL) pre-training is the recent popular paradigm that achieved state-of-the-art results on multi-modal tasks like image-retrieval, video-retrieval, visual question answering etc. These models are trained in an unsupervised way and greatly benefit from the complementary modality supervision. In this paper, we explore if the language representations trained using vision supervision perform better than vanilla language representations on Natural Language Understanding and commonsense reasoning benchmarks. We experiment with a diverse set of image-text models su","authors_text":"Avinash Madasu, Vasudev Lal","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-10T02:22:44Z","title":"Is Multimodal Vision Supervision Beneficial to Language?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05016","kind":"arxiv","version":2},"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:c2e88741605cee7ec9372c6f727d75386d08caec08ee3a5ef136a9c3b429e71b","target":"record","created_at":"2026-07-05T06:01:17Z","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":"27b2247a940b93609c130bbf8fb9ae48c59e31751fe6cef4111947e03397ae4f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-10T02:22:44Z","title_canon_sha256":"415cdd632406317bd7370d262ba25cab57a69cb5aedc6869af99e1dc1d5e8727"},"schema_version":"1.0","source":{"id":"2302.05016","kind":"arxiv","version":2}},"canonical_sha256":"5f2b29223dcacc5163920cfc4cd3bd1c9607c0774747adf8b92bef3526e2140f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f2b29223dcacc5163920cfc4cd3bd1c9607c0774747adf8b92bef3526e2140f","first_computed_at":"2026-07-05T06:01:17.109888Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:01:17.109888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4VK2pvpPA9edzY4zoo92Ns0Jy62wRIpolV6AiFHBAUFssexMKV/M9q+x2CK/1KuMP0B0pRTBH5jyjl6uvJ06Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:01:17.110558Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.05016","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2e88741605cee7ec9372c6f727d75386d08caec08ee3a5ef136a9c3b429e71b","sha256:077d83534e5055e62d32dac0e4029883e38e6b2a53c05b600096b5a7bff395db"],"state_sha256":"7b31a18c7dbeb86f60715d6a6093c331db259b3131f2326dde97e31b3b457c18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6GMwRw9pAJVeyJWsbX+9Jg7ZWtGA8kf3HSyez5d7nXE87RcT+hTfDNNtlm8MCKVQAek7aBPRaNd3N3L6zX3ECQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:12:10.930810Z","bundle_sha256":"820426cd769a274e38a20041410326876af811c0bcc73531c275002ae033ae63"}}