{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:SKRJ5VI7QBGTGGR75YIVUYQKBZ","short_pith_number":"pith:SKRJ5VI7","canonical_record":{"source":{"id":"2207.13061","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-26T17:34:11Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"373f1cbadd4c37f607c53b90dc7dceb34b512f68f6deb4e51a446d223b5680b5","abstract_canon_sha256":"5af5a457842a153b738992fd17cac2caebe6eb84412a172ace7bf606233d4b5e"},"schema_version":"1.0"},"canonical_sha256":"92a29ed51f804d331a3fee115a620a0e7a5c738f27521a0781d45268f5f58b3f","source":{"kind":"arxiv","id":"2207.13061","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.13061","created_at":"2026-07-05T04:48:15Z"},{"alias_kind":"arxiv_version","alias_value":"2207.13061v2","created_at":"2026-07-05T04:48:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.13061","created_at":"2026-07-05T04:48:15Z"},{"alias_kind":"pith_short_12","alias_value":"SKRJ5VI7QBGT","created_at":"2026-07-05T04:48:15Z"},{"alias_kind":"pith_short_16","alias_value":"SKRJ5VI7QBGTGGR7","created_at":"2026-07-05T04:48:15Z"},{"alias_kind":"pith_short_8","alias_value":"SKRJ5VI7","created_at":"2026-07-05T04:48:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:SKRJ5VI7QBGTGGR75YIVUYQKBZ","target":"record","payload":{"canonical_record":{"source":{"id":"2207.13061","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-26T17:34:11Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"373f1cbadd4c37f607c53b90dc7dceb34b512f68f6deb4e51a446d223b5680b5","abstract_canon_sha256":"5af5a457842a153b738992fd17cac2caebe6eb84412a172ace7bf606233d4b5e"},"schema_version":"1.0"},"canonical_sha256":"92a29ed51f804d331a3fee115a620a0e7a5c738f27521a0781d45268f5f58b3f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:48:15.295656Z","signature_b64":"iF0YUuubaa7nepQSSi45+9RiCS7fvFHTbtRu+cgoYsjqDJIv/oVqSkow/SGAjBjOXdVMp87sYkMTLP/sp26mBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92a29ed51f804d331a3fee115a620a0e7a5c738f27521a0781d45268f5f58b3f","last_reissued_at":"2026-07-05T04:48:15.295152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:48:15.295152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.13061","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":"2026-07-05T04:48:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uFjVDDonjWL8EHXwh9fbfETmG+Gm9/vBBsqt5rnJcUDDQmMUEJewJvHIN0rXCmPfE3UtzGLN/kV2Sa7qEb+3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:13:44.537624Z"},"content_sha256":"61265c76949fd2da6e48705d2aa87d1106135bd27ef60b04c50698b941eb3e54","schema_version":"1.0","event_id":"sha256:61265c76949fd2da6e48705d2aa87d1106135bd27ef60b04c50698b941eb3e54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:SKRJ5VI7QBGTGGR75YIVUYQKBZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NewsStories: Illustrating articles with visual summaries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Avneesh Sud, Bryan A. Plummer, JP Lewis, Kate Saenko, Reuben Tan, Thomas Leung","submitted_at":"2022-07-26T17:34:11Z","abstract_excerpt":"Recent self-supervised approaches have used large-scale image-text datasets to learn powerful representations that transfer to many tasks without finetuning. These methods often assume that there is one-to-one correspondence between its images and their (short) captions. However, many tasks require reasoning about multiple images and long text narratives, such as describing news articles with visual summaries. Thus, we explore a novel setting where the goal is to learn a self-supervised visual-language representation that is robust to varying text length and the number of images. In addition, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.13061","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/2207.13061/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":"2026-07-05T04:48:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jhOMWN2/XrMRZedF3CFr1DEczwLd4CU18zN9YcGkXsTqZLq3KOKlpgDCnXlWPlfTQE6FlyutsUuEEojq4ujABg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:13:44.538422Z"},"content_sha256":"12ecdebaf9a3d44899abc753fef725b3e45060f66e68c20bb4f14df903f88122","schema_version":"1.0","event_id":"sha256:12ecdebaf9a3d44899abc753fef725b3e45060f66e68c20bb4f14df903f88122"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SKRJ5VI7QBGTGGR75YIVUYQKBZ/bundle.json","state_url":"https://pith.science/pith/SKRJ5VI7QBGTGGR75YIVUYQKBZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SKRJ5VI7QBGTGGR75YIVUYQKBZ/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":"2026-08-05T06:13:44Z","links":{"resolver":"https://pith.science/pith/SKRJ5VI7QBGTGGR75YIVUYQKBZ","bundle":"https://pith.science/pith/SKRJ5VI7QBGTGGR75YIVUYQKBZ/bundle.json","state":"https://pith.science/pith/SKRJ5VI7QBGTGGR75YIVUYQKBZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SKRJ5VI7QBGTGGR75YIVUYQKBZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SKRJ5VI7QBGTGGR75YIVUYQKBZ","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":"5af5a457842a153b738992fd17cac2caebe6eb84412a172ace7bf606233d4b5e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-26T17:34:11Z","title_canon_sha256":"373f1cbadd4c37f607c53b90dc7dceb34b512f68f6deb4e51a446d223b5680b5"},"schema_version":"1.0","source":{"id":"2207.13061","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.13061","created_at":"2026-07-05T04:48:15Z"},{"alias_kind":"arxiv_version","alias_value":"2207.13061v2","created_at":"2026-07-05T04:48:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.13061","created_at":"2026-07-05T04:48:15Z"},{"alias_kind":"pith_short_12","alias_value":"SKRJ5VI7QBGT","created_at":"2026-07-05T04:48:15Z"},{"alias_kind":"pith_short_16","alias_value":"SKRJ5VI7QBGTGGR7","created_at":"2026-07-05T04:48:15Z"},{"alias_kind":"pith_short_8","alias_value":"SKRJ5VI7","created_at":"2026-07-05T04:48:15Z"}],"graph_snapshots":[{"event_id":"sha256:12ecdebaf9a3d44899abc753fef725b3e45060f66e68c20bb4f14df903f88122","target":"graph","created_at":"2026-07-05T04:48:15Z","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/2207.13061/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent self-supervised approaches have used large-scale image-text datasets to learn powerful representations that transfer to many tasks without finetuning. These methods often assume that there is one-to-one correspondence between its images and their (short) captions. However, many tasks require reasoning about multiple images and long text narratives, such as describing news articles with visual summaries. Thus, we explore a novel setting where the goal is to learn a self-supervised visual-language representation that is robust to varying text length and the number of images. In addition, ","authors_text":"Avneesh Sud, Bryan A. Plummer, JP Lewis, Kate Saenko, Reuben Tan, Thomas Leung","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-26T17:34:11Z","title":"NewsStories: Illustrating articles with visual summaries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.13061","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":"sha256:61265c76949fd2da6e48705d2aa87d1106135bd27ef60b04c50698b941eb3e54","target":"record","created_at":"2026-07-05T04:48:15Z","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":"5af5a457842a153b738992fd17cac2caebe6eb84412a172ace7bf606233d4b5e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-26T17:34:11Z","title_canon_sha256":"373f1cbadd4c37f607c53b90dc7dceb34b512f68f6deb4e51a446d223b5680b5"},"schema_version":"1.0","source":{"id":"2207.13061","kind":"arxiv","version":2}},"canonical_sha256":"92a29ed51f804d331a3fee115a620a0e7a5c738f27521a0781d45268f5f58b3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92a29ed51f804d331a3fee115a620a0e7a5c738f27521a0781d45268f5f58b3f","first_computed_at":"2026-07-05T04:48:15.295152Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:48:15.295152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iF0YUuubaa7nepQSSi45+9RiCS7fvFHTbtRu+cgoYsjqDJIv/oVqSkow/SGAjBjOXdVMp87sYkMTLP/sp26mBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:48:15.295656Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.13061","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61265c76949fd2da6e48705d2aa87d1106135bd27ef60b04c50698b941eb3e54","sha256:12ecdebaf9a3d44899abc753fef725b3e45060f66e68c20bb4f14df903f88122"],"state_sha256":"dbca8bf2d92fb703be1832ebefcfe5210f8a00514d69b0f4f951d7f781554045"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bQdSOneAfHh0rQKYq6fK/2RXYWUEZrwhQGVwawdUU5UWar3CGH/NA/m7yzjURX60NnpjKdPLBL3pUM70Pg0tCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:13:44.544804Z","bundle_sha256":"c3f33d358042275fa6fc847d5cd997d532db5fc2b2c699735369ccd2db1e80f4"}}