{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:IE65CX73DJYBBH6C6OKPCYUJAB","short_pith_number":"pith:IE65CX73","schema_version":"1.0","canonical_sha256":"413dd15ffb1a70109fc2f394f1628900663d546a0c3d7e193cab908e26d3435d","source":{"kind":"arxiv","id":"1606.07493","version":5},"attestation_state":"computed","paper":{"title":"Sort Story: Sorting Jumbled Images and Captions into Stories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Arjun Chandrasekaran, Devi Parikh, Dhruv Batra, Harsh Agrawal, Mohit Bansal","submitted_at":"2016-06-23T21:54:44Z","abstract_excerpt":"Temporal common sense has applications in AI tasks such as QA, multi-document summarization, and human-AI communication. We propose the task of sequencing -- given a jumbled set of aligned image-caption pairs that belong to a story, the task is to sort them such that the output sequence forms a coherent story. We present multiple approaches, via unary (position) and pairwise (order) predictions, and their ensemble-based combinations, achieving strong results on this task. We use both text-based and image-based features, which depict complementary improvements. Using qualitative examples, we de"},"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":"1606.07493","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-23T21:54:44Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"5e8a09e303eb4dab43a361be2805b2f6bb011bc2e5500401a10fb53ef717089b","abstract_canon_sha256":"bdce4f3a39e3fa2af88a4f84c94d0defb6c88519b42de976929c6027f98df5a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:03.067418Z","signature_b64":"fBX14yfx+oyROwDEvRBDbwJG5V8knlnFK1ixpAS7iJTFDj4zfaHfcZY5+qY8FOeeEtwdczUdDZiul4/Ba9/ZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"413dd15ffb1a70109fc2f394f1628900663d546a0c3d7e193cab908e26d3435d","last_reissued_at":"2026-05-18T01:00:03.066900Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:03.066900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sort Story: Sorting Jumbled Images and Captions into Stories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Arjun Chandrasekaran, Devi Parikh, Dhruv Batra, Harsh Agrawal, Mohit Bansal","submitted_at":"2016-06-23T21:54:44Z","abstract_excerpt":"Temporal common sense has applications in AI tasks such as QA, multi-document summarization, and human-AI communication. We propose the task of sequencing -- given a jumbled set of aligned image-caption pairs that belong to a story, the task is to sort them such that the output sequence forms a coherent story. We present multiple approaches, via unary (position) and pairwise (order) predictions, and their ensemble-based combinations, achieving strong results on this task. We use both text-based and image-based features, which depict complementary improvements. Using qualitative examples, we de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.07493","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1606.07493","created_at":"2026-05-18T01:00:03.066974+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.07493v5","created_at":"2026-05-18T01:00:03.066974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.07493","created_at":"2026-05-18T01:00:03.066974+00:00"},{"alias_kind":"pith_short_12","alias_value":"IE65CX73DJYB","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_16","alias_value":"IE65CX73DJYBBH6C","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_8","alias_value":"IE65CX73","created_at":"2026-05-18T12:30:22.444734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IE65CX73DJYBBH6C6OKPCYUJAB","json":"https://pith.science/pith/IE65CX73DJYBBH6C6OKPCYUJAB.json","graph_json":"https://pith.science/api/pith-number/IE65CX73DJYBBH6C6OKPCYUJAB/graph.json","events_json":"https://pith.science/api/pith-number/IE65CX73DJYBBH6C6OKPCYUJAB/events.json","paper":"https://pith.science/paper/IE65CX73"},"agent_actions":{"view_html":"https://pith.science/pith/IE65CX73DJYBBH6C6OKPCYUJAB","download_json":"https://pith.science/pith/IE65CX73DJYBBH6C6OKPCYUJAB.json","view_paper":"https://pith.science/paper/IE65CX73","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.07493&json=true","fetch_graph":"https://pith.science/api/pith-number/IE65CX73DJYBBH6C6OKPCYUJAB/graph.json","fetch_events":"https://pith.science/api/pith-number/IE65CX73DJYBBH6C6OKPCYUJAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IE65CX73DJYBBH6C6OKPCYUJAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IE65CX73DJYBBH6C6OKPCYUJAB/action/storage_attestation","attest_author":"https://pith.science/pith/IE65CX73DJYBBH6C6OKPCYUJAB/action/author_attestation","sign_citation":"https://pith.science/pith/IE65CX73DJYBBH6C6OKPCYUJAB/action/citation_signature","submit_replication":"https://pith.science/pith/IE65CX73DJYBBH6C6OKPCYUJAB/action/replication_record"}},"created_at":"2026-05-18T01:00:03.066974+00:00","updated_at":"2026-05-18T01:00:03.066974+00:00"}