{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:H65WPHL7QWUUDUGYXNI577BSQT","short_pith_number":"pith:H65WPHL7","schema_version":"1.0","canonical_sha256":"3fbb679d7f85a941d0d8bb51dffc3284eac0ede40c1376f6e3e2a60a69c80ca4","source":{"kind":"arxiv","id":"2006.08686","version":1},"attestation_state":"computed","paper":{"title":"Multi-Image Summarization: Textual Summary from a Set of Cohesive Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kazoo Sone, Nicholas Trieu, Pradyumna Narayana, Radu Soricut, Sebastian Goodman","submitted_at":"2020-06-15T18:45:35Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2006.08686","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-15T18:45:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fa08ee801dfb0f4e0cfa609094d05a427565369b29331b24a89fd8f3a44ac1ac","abstract_canon_sha256":"78211f637218fc886f39ed8c2a23cf59fe3a406633f968c4c3d3a045ff3ec566"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:10:42.051716Z","signature_b64":"eB2EoZYYx0poAzG6HXJH3SeDAZ6yiq3IR3qrtw9+Qfn4IZte4dkK0MfcOr7a81eKaZcytaQlM7JaD0CvC1vpAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fbb679d7f85a941d0d8bb51dffc3284eac0ede40c1376f6e3e2a60a69c80ca4","last_reissued_at":"2026-07-05T01:10:42.051294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:10:42.051294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Image Summarization: Textual Summary from a Set of Cohesive Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kazoo Sone, Nicholas Trieu, Pradyumna Narayana, Radu Soricut, Sebastian Goodman","submitted_at":"2020-06-15T18:45:35Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.08686","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/2006.08686/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2006.08686","created_at":"2026-07-05T01:10:42.051364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.08686v1","created_at":"2026-07-05T01:10:42.051364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.08686","created_at":"2026-07-05T01:10:42.051364+00:00"},{"alias_kind":"pith_short_12","alias_value":"H65WPHL7QWUU","created_at":"2026-07-05T01:10:42.051364+00:00"},{"alias_kind":"pith_short_16","alias_value":"H65WPHL7QWUUDUGY","created_at":"2026-07-05T01:10:42.051364+00:00"},{"alias_kind":"pith_short_8","alias_value":"H65WPHL7","created_at":"2026-07-05T01:10:42.051364+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13834","citing_title":"Maybe you are looking for CroQS: Cross-modal Query Suggestion for Text-to-Image Retrieval","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H65WPHL7QWUUDUGYXNI577BSQT","json":"https://pith.science/pith/H65WPHL7QWUUDUGYXNI577BSQT.json","graph_json":"https://pith.science/api/pith-number/H65WPHL7QWUUDUGYXNI577BSQT/graph.json","events_json":"https://pith.science/api/pith-number/H65WPHL7QWUUDUGYXNI577BSQT/events.json","paper":"https://pith.science/paper/H65WPHL7"},"agent_actions":{"view_html":"https://pith.science/pith/H65WPHL7QWUUDUGYXNI577BSQT","download_json":"https://pith.science/pith/H65WPHL7QWUUDUGYXNI577BSQT.json","view_paper":"https://pith.science/paper/H65WPHL7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.08686&json=true","fetch_graph":"https://pith.science/api/pith-number/H65WPHL7QWUUDUGYXNI577BSQT/graph.json","fetch_events":"https://pith.science/api/pith-number/H65WPHL7QWUUDUGYXNI577BSQT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H65WPHL7QWUUDUGYXNI577BSQT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H65WPHL7QWUUDUGYXNI577BSQT/action/storage_attestation","attest_author":"https://pith.science/pith/H65WPHL7QWUUDUGYXNI577BSQT/action/author_attestation","sign_citation":"https://pith.science/pith/H65WPHL7QWUUDUGYXNI577BSQT/action/citation_signature","submit_replication":"https://pith.science/pith/H65WPHL7QWUUDUGYXNI577BSQT/action/replication_record"}},"created_at":"2026-07-05T01:10:42.051364+00:00","updated_at":"2026-07-05T01:10:42.051364+00:00"}