{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VYCB7U3UNLHLXEVHR2UB36WVRJ","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":"f4e2ce5be44952f606dfcfa20b234fb79081289031e38de3ba76a74d421f6eec","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-12T16:15:32Z","title_canon_sha256":"31d70de31811626bf664baf04d53ee2c2b9123cb901f89b07f8a72e8d4a498ac"},"schema_version":"1.0","source":{"id":"2408.06259","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06259","created_at":"2026-07-05T08:54:38Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06259v1","created_at":"2026-07-05T08:54:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06259","created_at":"2026-07-05T08:54:38Z"},{"alias_kind":"pith_short_12","alias_value":"VYCB7U3UNLHL","created_at":"2026-07-05T08:54:38Z"},{"alias_kind":"pith_short_16","alias_value":"VYCB7U3UNLHLXEVH","created_at":"2026-07-05T08:54:38Z"},{"alias_kind":"pith_short_8","alias_value":"VYCB7U3U","created_at":"2026-07-05T08:54:38Z"}],"graph_snapshots":[{"event_id":"sha256:1b43c689e9410365e6182b52bddc94c0f77ccc489cd12ff30b202230dee9aad2","target":"graph","created_at":"2026-07-05T08:54:38Z","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/2408.06259/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual storytelling systems generate multi-sentence stories from image sequences. In this task, capturing contextual information and bridging visual variation bring additional challenges. We propose a simple yet effective framework that leverages the generalization capabilities of pretrained foundation models, only training a lightweight vision-language mapping network to connect modalities, while incorporating context to enhance coherence. We introduce a multimodal contrastive objective that also improves visual relevance and story informativeness. Extensive experimental results, across both ","authors_text":"Albert Gatt, Denis Paperno, Yingjin Song","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-12T16:15:32Z","title":"Context-aware Visual Storytelling with Visual Prefix Tuning and Contrastive Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06259","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":"sha256:4194bd8c0ac9c1e4ead3c70a56430b7a9612b09ef30bf4010b02dfc38bc754e2","target":"record","created_at":"2026-07-05T08:54:38Z","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":"f4e2ce5be44952f606dfcfa20b234fb79081289031e38de3ba76a74d421f6eec","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-12T16:15:32Z","title_canon_sha256":"31d70de31811626bf664baf04d53ee2c2b9123cb901f89b07f8a72e8d4a498ac"},"schema_version":"1.0","source":{"id":"2408.06259","kind":"arxiv","version":1}},"canonical_sha256":"ae041fd3746acebb92a78ea81dfad58a725f75067d8916920ba42b9e3f43df9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae041fd3746acebb92a78ea81dfad58a725f75067d8916920ba42b9e3f43df9f","first_computed_at":"2026-07-05T08:54:38.299845Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:54:38.299845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dhyt6iTf9mR5ZYlDxIYc6Fnd9I+97sO2aWFHXq1cIhMFRAsK2491wk+B3Z2MLnn3xhBllo4R7PDtWRFUmORRBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:54:38.300386Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.06259","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4194bd8c0ac9c1e4ead3c70a56430b7a9612b09ef30bf4010b02dfc38bc754e2","sha256:1b43c689e9410365e6182b52bddc94c0f77ccc489cd12ff30b202230dee9aad2"],"state_sha256":"4440d7355c173ea5c03c9ee230b723cce9b878a63d8b731c83811d5b8843cb03"}