{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:H65WPHL7QWUUDUGYXNI577BSQT","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":"78211f637218fc886f39ed8c2a23cf59fe3a406633f968c4c3d3a045ff3ec566","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-15T18:45:35Z","title_canon_sha256":"fa08ee801dfb0f4e0cfa609094d05a427565369b29331b24a89fd8f3a44ac1ac"},"schema_version":"1.0","source":{"id":"2006.08686","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.08686","created_at":"2026-07-05T01:10:42Z"},{"alias_kind":"arxiv_version","alias_value":"2006.08686v1","created_at":"2026-07-05T01:10:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.08686","created_at":"2026-07-05T01:10:42Z"},{"alias_kind":"pith_short_12","alias_value":"H65WPHL7QWUU","created_at":"2026-07-05T01:10:42Z"},{"alias_kind":"pith_short_16","alias_value":"H65WPHL7QWUUDUGY","created_at":"2026-07-05T01:10:42Z"},{"alias_kind":"pith_short_8","alias_value":"H65WPHL7","created_at":"2026-07-05T01:10:42Z"}],"graph_snapshots":[{"event_id":"sha256:5ff7d4f71d419a64722aab4988492272538620c775d8a7fc6f1a212f4bd16448","target":"graph","created_at":"2026-07-05T01:10:42Z","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/2006.08686/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-sentence summarization is a well studied problem in NLP, while generating image descriptions for a single image is a well studied problem in Computer Vision. However, for applications such as image cluster labeling or web page summarization, summarizing a set of images is also a useful and challenging task. This paper proposes the new task of multi-image summarization, which aims to generate a concise and descriptive textual summary given a coherent set of input images. We propose a model that extends the image-captioning Transformer-based architecture for single image to multi-image. A ","authors_text":"Kazoo Sone, Nicholas Trieu, Pradyumna Narayana, Radu Soricut, Sebastian Goodman","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-15T18:45:35Z","title":"Multi-Image Summarization: Textual Summary from a Set of Cohesive Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.08686","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":"sha256:36a2640d315a6d3674c66be201598ad81c983d3fe7bd1274846d60e9f8bef7a8","target":"record","created_at":"2026-07-05T01:10:42Z","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":"78211f637218fc886f39ed8c2a23cf59fe3a406633f968c4c3d3a045ff3ec566","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-15T18:45:35Z","title_canon_sha256":"fa08ee801dfb0f4e0cfa609094d05a427565369b29331b24a89fd8f3a44ac1ac"},"schema_version":"1.0","source":{"id":"2006.08686","kind":"arxiv","version":1}},"canonical_sha256":"3fbb679d7f85a941d0d8bb51dffc3284eac0ede40c1376f6e3e2a60a69c80ca4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3fbb679d7f85a941d0d8bb51dffc3284eac0ede40c1376f6e3e2a60a69c80ca4","first_computed_at":"2026-07-05T01:10:42.051294Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:10:42.051294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eB2EoZYYx0poAzG6HXJH3SeDAZ6yiq3IR3qrtw9+Qfn4IZte4dkK0MfcOr7a81eKaZcytaQlM7JaD0CvC1vpAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:10:42.051716Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.08686","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36a2640d315a6d3674c66be201598ad81c983d3fe7bd1274846d60e9f8bef7a8","sha256:5ff7d4f71d419a64722aab4988492272538620c775d8a7fc6f1a212f4bd16448"],"state_sha256":"fc4c21bdb8b2d2d5ea1aad7c9a3d14f0340d72853390751e4b235d8fcd57f2b2"}