{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:LNNURA2N7PMCPFN5SKTAC3MRKJ","short_pith_number":"pith:LNNURA2N","canonical_record":{"source":{"id":"2012.04446","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2020-12-08T14:32:05Z","cross_cats_sorted":[],"title_canon_sha256":"58b818ad23a0a2b588a5741db99b947d4dc388b3851eb16905d89ede458fe7fb","abstract_canon_sha256":"bed06796fc51ac8044bda638a9c393f18b3bf56000510ab1b4a34a06b29be3e4"},"schema_version":"1.0"},"canonical_sha256":"5b5b48834dfbd82795bd92a6016d91525ae3ed0e69c57af4f858fd335c7b9caa","source":{"kind":"arxiv","id":"2012.04446","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.04446","created_at":"2026-07-05T01:58:04Z"},{"alias_kind":"arxiv_version","alias_value":"2012.04446v1","created_at":"2026-07-05T01:58:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04446","created_at":"2026-07-05T01:58:04Z"},{"alias_kind":"pith_short_12","alias_value":"LNNURA2N7PMC","created_at":"2026-07-05T01:58:04Z"},{"alias_kind":"pith_short_16","alias_value":"LNNURA2N7PMCPFN5","created_at":"2026-07-05T01:58:04Z"},{"alias_kind":"pith_short_8","alias_value":"LNNURA2N","created_at":"2026-07-05T01:58:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:LNNURA2N7PMCPFN5SKTAC3MRKJ","target":"record","payload":{"canonical_record":{"source":{"id":"2012.04446","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2020-12-08T14:32:05Z","cross_cats_sorted":[],"title_canon_sha256":"58b818ad23a0a2b588a5741db99b947d4dc388b3851eb16905d89ede458fe7fb","abstract_canon_sha256":"bed06796fc51ac8044bda638a9c393f18b3bf56000510ab1b4a34a06b29be3e4"},"schema_version":"1.0"},"canonical_sha256":"5b5b48834dfbd82795bd92a6016d91525ae3ed0e69c57af4f858fd335c7b9caa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:04.233161Z","signature_b64":"YZ8YysEI9ePRaBid1iECmAduE7/JXQBK+9bWSckLOz0k52BoM+IjILuuPLTjR5lineDLwUQ/L7y65K93ivgdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b5b48834dfbd82795bd92a6016d91525ae3ed0e69c57af4f858fd335c7b9caa","last_reissued_at":"2026-07-05T01:58:04.232786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:04.232786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.04446","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":"2026-07-05T01:58:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lycMtFNeXMUzMX20JG/3Wg6RJblwMw+8mvMIoCXge98QSf1UkE+/dbfO8rz2rzu4Fg/gWLzbtJOEJiOVpR7hDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T15:43:46.078701Z"},"content_sha256":"f9bce068a51b6377a4badf83315b3d256fd3a97f920aa662ea8bff6fa3f791d1","schema_version":"1.0","event_id":"sha256:f9bce068a51b6377a4badf83315b3d256fd3a97f920aa662ea8bff6fa3f791d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:LNNURA2N7PMCPFN5SKTAC3MRKJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LAMP: Label Augmented Multimodal Pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Chen Zhu, Deng Cai, Heda Wang, Jia Guo, Xiaofei He, Yao Hu, Yilun Zhao","submitted_at":"2020-12-08T14:32:05Z","abstract_excerpt":"Multi-modal representation learning by pretraining has become an increasing interest due to its easy-to-use and potential benefit for various Visual-and-Language~(V-L) tasks. However its requirement of large volume and high-quality vision-language pairs highly hinders its values in practice. In this paper, we proposed a novel label-augmented V-L pretraining model, named LAMP, to address this problem. Specifically, we leveraged auto-generated labels of visual objects to enrich vision-language pairs with fine-grained alignment and correspondingly designed a novel pretraining task. Besides, we al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04446","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/2012.04446/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":"2026-07-05T01:58:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IpD5vHDYrkcrv2EEin5fFg/vLi/Dau7efmb/qa8ppZSVcmMs0nkAwn1iclcGa8IxKfeOzhOBZmw3jZfVu3U9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T15:43:46.079059Z"},"content_sha256":"917bba90954d77da653865e35ee79c375716f9787942e0b2d1e56d53c145312d","schema_version":"1.0","event_id":"sha256:917bba90954d77da653865e35ee79c375716f9787942e0b2d1e56d53c145312d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LNNURA2N7PMCPFN5SKTAC3MRKJ/bundle.json","state_url":"https://pith.science/pith/LNNURA2N7PMCPFN5SKTAC3MRKJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LNNURA2N7PMCPFN5SKTAC3MRKJ/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":"2026-07-17T15:43:46Z","links":{"resolver":"https://pith.science/pith/LNNURA2N7PMCPFN5SKTAC3MRKJ","bundle":"https://pith.science/pith/LNNURA2N7PMCPFN5SKTAC3MRKJ/bundle.json","state":"https://pith.science/pith/LNNURA2N7PMCPFN5SKTAC3MRKJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LNNURA2N7PMCPFN5SKTAC3MRKJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LNNURA2N7PMCPFN5SKTAC3MRKJ","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":"bed06796fc51ac8044bda638a9c393f18b3bf56000510ab1b4a34a06b29be3e4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2020-12-08T14:32:05Z","title_canon_sha256":"58b818ad23a0a2b588a5741db99b947d4dc388b3851eb16905d89ede458fe7fb"},"schema_version":"1.0","source":{"id":"2012.04446","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.04446","created_at":"2026-07-05T01:58:04Z"},{"alias_kind":"arxiv_version","alias_value":"2012.04446v1","created_at":"2026-07-05T01:58:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04446","created_at":"2026-07-05T01:58:04Z"},{"alias_kind":"pith_short_12","alias_value":"LNNURA2N7PMC","created_at":"2026-07-05T01:58:04Z"},{"alias_kind":"pith_short_16","alias_value":"LNNURA2N7PMCPFN5","created_at":"2026-07-05T01:58:04Z"},{"alias_kind":"pith_short_8","alias_value":"LNNURA2N","created_at":"2026-07-05T01:58:04Z"}],"graph_snapshots":[{"event_id":"sha256:917bba90954d77da653865e35ee79c375716f9787942e0b2d1e56d53c145312d","target":"graph","created_at":"2026-07-05T01:58:04Z","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/2012.04446/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal representation learning by pretraining has become an increasing interest due to its easy-to-use and potential benefit for various Visual-and-Language~(V-L) tasks. However its requirement of large volume and high-quality vision-language pairs highly hinders its values in practice. In this paper, we proposed a novel label-augmented V-L pretraining model, named LAMP, to address this problem. Specifically, we leveraged auto-generated labels of visual objects to enrich vision-language pairs with fine-grained alignment and correspondingly designed a novel pretraining task. Besides, we al","authors_text":"Chen Zhu, Deng Cai, Heda Wang, Jia Guo, Xiaofei He, Yao Hu, Yilun Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2020-12-08T14:32:05Z","title":"LAMP: Label Augmented Multimodal Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04446","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:f9bce068a51b6377a4badf83315b3d256fd3a97f920aa662ea8bff6fa3f791d1","target":"record","created_at":"2026-07-05T01:58:04Z","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":"bed06796fc51ac8044bda638a9c393f18b3bf56000510ab1b4a34a06b29be3e4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2020-12-08T14:32:05Z","title_canon_sha256":"58b818ad23a0a2b588a5741db99b947d4dc388b3851eb16905d89ede458fe7fb"},"schema_version":"1.0","source":{"id":"2012.04446","kind":"arxiv","version":1}},"canonical_sha256":"5b5b48834dfbd82795bd92a6016d91525ae3ed0e69c57af4f858fd335c7b9caa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b5b48834dfbd82795bd92a6016d91525ae3ed0e69c57af4f858fd335c7b9caa","first_computed_at":"2026-07-05T01:58:04.232786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:58:04.232786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YZ8YysEI9ePRaBid1iECmAduE7/JXQBK+9bWSckLOz0k52BoM+IjILuuPLTjR5lineDLwUQ/L7y65K93ivgdDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:58:04.233161Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.04446","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9bce068a51b6377a4badf83315b3d256fd3a97f920aa662ea8bff6fa3f791d1","sha256:917bba90954d77da653865e35ee79c375716f9787942e0b2d1e56d53c145312d"],"state_sha256":"c969b1e12e6df07ad3418a655b1800fb2deec62584f84705cca2fc7f2f87d753"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lOyYsxVN7BOPKrByYKC5k86iFENY7qEz3PaH8vX4pZGs7gZI79q8ufsUqTj39NW7U1O89OM8svaUOekFqwBtDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T15:43:46.081553Z","bundle_sha256":"77e6ba123e2f0b1c09b402ef70805abb45eccfce8565b51544601460ea439786"}}