{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GNUQMJ7O3Q43ULBABBPQ5AWKIO","short_pith_number":"pith:GNUQMJ7O","canonical_record":{"source":{"id":"2201.05078","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-13T17:03:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f53a2ca60b7dc7c53d2228461241368ed460715b11e636e391ead85a65c99d02","abstract_canon_sha256":"2b1ada6ca504bde13ea53b8a697feb992c24874c66368dd18eabc23319ba5f8d"},"schema_version":"1.0"},"canonical_sha256":"33690627eedc39ba2c20085f0e82ca43a99caebfbd75cac3cea8109f30b4fc2e","source":{"kind":"arxiv","id":"2201.05078","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.05078","created_at":"2026-07-05T04:18:50Z"},{"alias_kind":"arxiv_version","alias_value":"2201.05078v2","created_at":"2026-07-05T04:18:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05078","created_at":"2026-07-05T04:18:50Z"},{"alias_kind":"pith_short_12","alias_value":"GNUQMJ7O3Q43","created_at":"2026-07-05T04:18:50Z"},{"alias_kind":"pith_short_16","alias_value":"GNUQMJ7O3Q43ULBA","created_at":"2026-07-05T04:18:50Z"},{"alias_kind":"pith_short_8","alias_value":"GNUQMJ7O","created_at":"2026-07-05T04:18:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GNUQMJ7O3Q43ULBABBPQ5AWKIO","target":"record","payload":{"canonical_record":{"source":{"id":"2201.05078","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-13T17:03:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f53a2ca60b7dc7c53d2228461241368ed460715b11e636e391ead85a65c99d02","abstract_canon_sha256":"2b1ada6ca504bde13ea53b8a697feb992c24874c66368dd18eabc23319ba5f8d"},"schema_version":"1.0"},"canonical_sha256":"33690627eedc39ba2c20085f0e82ca43a99caebfbd75cac3cea8109f30b4fc2e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:18:50.546525Z","signature_b64":"R3bkuO1PqX8V0NRWwpF6zOGxboeDCO7rLVMFwiZuozn7Ok2QGD3O4ABYC8tBKuyVzfKjjL73vVm2lfXF08C/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33690627eedc39ba2c20085f0e82ca43a99caebfbd75cac3cea8109f30b4fc2e","last_reissued_at":"2026-07-05T04:18:50.545970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:18:50.545970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.05078","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":"2026-07-05T04:18:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JjRMaFOEklXH0bn6W+LmeU3it1oEUaxj5Ld+rJ6i8Wk/rlyJSAvpib29abOylfWNs1PAcXg8w6vIeCQf6u/mAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:00:25.485765Z"},"content_sha256":"2b9bc830d20e04c88a5d2c1dfbec934058acb25ffc21316a82aa148aa41ca6b0","schema_version":"1.0","event_id":"sha256:2b9bc830d20e04c88a5d2c1dfbec934058acb25ffc21316a82aa148aa41ca6b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GNUQMJ7O3Q43ULBABBPQ5AWKIO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLIP-Event: Connecting Text and Images with Event Structures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenguang Zhu, Heng Ji, Luowei Zhou, Manling Li, Michael Zeng, Ruochen Xu, Shih-Fu Chang, Shuohang Wang, Xudong Lin","submitted_at":"2022-01-13T17:03:57Z","abstract_excerpt":"Vision-language (V+L) pretraining models have achieved great success in supporting multimedia applications by understanding the alignments between images and text. While existing vision-language pretraining models primarily focus on understanding objects in images or entities in text, they often ignore the alignment at the level of events and their argument structures. In this work, we propose a contrastive learning framework to enforce vision-language pretraining models to comprehend events and associated argument (participant) roles. To achieve this, we take advantage of text information ext"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05078","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/2201.05078/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":"2026-07-05T04:18:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3FVP2xaWMcHmZfb2z2mGhx7Xa4TvJjhm8nxhA1aeNo8vy64GpOymbuXMcQLWu8PAYemkv8xDQOAVw9DAFJ6fCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:00:25.486175Z"},"content_sha256":"98c35a978c737f78ebfafdd79c1e4f168a1f052a42dcd6068741bfc9e7c92eec","schema_version":"1.0","event_id":"sha256:98c35a978c737f78ebfafdd79c1e4f168a1f052a42dcd6068741bfc9e7c92eec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GNUQMJ7O3Q43ULBABBPQ5AWKIO/bundle.json","state_url":"https://pith.science/pith/GNUQMJ7O3Q43ULBABBPQ5AWKIO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GNUQMJ7O3Q43ULBABBPQ5AWKIO/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":"2026-08-06T05:00:25Z","links":{"resolver":"https://pith.science/pith/GNUQMJ7O3Q43ULBABBPQ5AWKIO","bundle":"https://pith.science/pith/GNUQMJ7O3Q43ULBABBPQ5AWKIO/bundle.json","state":"https://pith.science/pith/GNUQMJ7O3Q43ULBABBPQ5AWKIO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GNUQMJ7O3Q43ULBABBPQ5AWKIO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GNUQMJ7O3Q43ULBABBPQ5AWKIO","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":"2b1ada6ca504bde13ea53b8a697feb992c24874c66368dd18eabc23319ba5f8d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-13T17:03:57Z","title_canon_sha256":"f53a2ca60b7dc7c53d2228461241368ed460715b11e636e391ead85a65c99d02"},"schema_version":"1.0","source":{"id":"2201.05078","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.05078","created_at":"2026-07-05T04:18:50Z"},{"alias_kind":"arxiv_version","alias_value":"2201.05078v2","created_at":"2026-07-05T04:18:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05078","created_at":"2026-07-05T04:18:50Z"},{"alias_kind":"pith_short_12","alias_value":"GNUQMJ7O3Q43","created_at":"2026-07-05T04:18:50Z"},{"alias_kind":"pith_short_16","alias_value":"GNUQMJ7O3Q43ULBA","created_at":"2026-07-05T04:18:50Z"},{"alias_kind":"pith_short_8","alias_value":"GNUQMJ7O","created_at":"2026-07-05T04:18:50Z"}],"graph_snapshots":[{"event_id":"sha256:98c35a978c737f78ebfafdd79c1e4f168a1f052a42dcd6068741bfc9e7c92eec","target":"graph","created_at":"2026-07-05T04:18:50Z","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/2201.05078/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language (V+L) pretraining models have achieved great success in supporting multimedia applications by understanding the alignments between images and text. While existing vision-language pretraining models primarily focus on understanding objects in images or entities in text, they often ignore the alignment at the level of events and their argument structures. In this work, we propose a contrastive learning framework to enforce vision-language pretraining models to comprehend events and associated argument (participant) roles. To achieve this, we take advantage of text information ext","authors_text":"Chenguang Zhu, Heng Ji, Luowei Zhou, Manling Li, Michael Zeng, Ruochen Xu, Shih-Fu Chang, Shuohang Wang, Xudong Lin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-13T17:03:57Z","title":"CLIP-Event: Connecting Text and Images with Event Structures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05078","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":"sha256:2b9bc830d20e04c88a5d2c1dfbec934058acb25ffc21316a82aa148aa41ca6b0","target":"record","created_at":"2026-07-05T04:18:50Z","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":"2b1ada6ca504bde13ea53b8a697feb992c24874c66368dd18eabc23319ba5f8d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-13T17:03:57Z","title_canon_sha256":"f53a2ca60b7dc7c53d2228461241368ed460715b11e636e391ead85a65c99d02"},"schema_version":"1.0","source":{"id":"2201.05078","kind":"arxiv","version":2}},"canonical_sha256":"33690627eedc39ba2c20085f0e82ca43a99caebfbd75cac3cea8109f30b4fc2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33690627eedc39ba2c20085f0e82ca43a99caebfbd75cac3cea8109f30b4fc2e","first_computed_at":"2026-07-05T04:18:50.545970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:18:50.545970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R3bkuO1PqX8V0NRWwpF6zOGxboeDCO7rLVMFwiZuozn7Ok2QGD3O4ABYC8tBKuyVzfKjjL73vVm2lfXF08C/BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:18:50.546525Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.05078","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b9bc830d20e04c88a5d2c1dfbec934058acb25ffc21316a82aa148aa41ca6b0","sha256:98c35a978c737f78ebfafdd79c1e4f168a1f052a42dcd6068741bfc9e7c92eec"],"state_sha256":"89e544b60e5521ae1999bdd2437f87019dbf719941231e7aab59176128095d03"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"opGT4bP2yjlVbF46GtEq0OVFPcvId2AtywEHVvCtGAtTxfio0IuUTjCTAC4tiUSyUHo5gB5x+CbLDG9Us90WAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:00:25.490018Z","bundle_sha256":"41de0ec3a296945554f6df5626cbb0022d3d0f03a312f9558842372b8971ffb3"}}