{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZNRXALNNK36A6GTTNNARZ6OLMJ","short_pith_number":"pith:ZNRXALNN","canonical_record":{"source":{"id":"2508.14045","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-31T16:44:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b3af69c0c9ab63a6f6afbd6589980a608ebd008af4671dfb817ea00f0dbc228a","abstract_canon_sha256":"c50e7f27bb5868eded2a981af3883e8a4b3d288c5cde3c7795ab8ca1b4859570"},"schema_version":"1.0"},"canonical_sha256":"cb63702dad56fc0f1a736b411cf9cb624be94b67d156160f167958a730c41f60","source":{"kind":"arxiv","id":"2508.14045","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.14045","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"arxiv_version","alias_value":"2508.14045v1","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14045","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"pith_short_12","alias_value":"ZNRXALNNK36A","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"pith_short_16","alias_value":"ZNRXALNNK36A6GTT","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"pith_short_8","alias_value":"ZNRXALNN","created_at":"2026-07-05T11:56:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZNRXALNNK36A6GTTNNARZ6OLMJ","target":"record","payload":{"canonical_record":{"source":{"id":"2508.14045","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-31T16:44:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b3af69c0c9ab63a6f6afbd6589980a608ebd008af4671dfb817ea00f0dbc228a","abstract_canon_sha256":"c50e7f27bb5868eded2a981af3883e8a4b3d288c5cde3c7795ab8ca1b4859570"},"schema_version":"1.0"},"canonical_sha256":"cb63702dad56fc0f1a736b411cf9cb624be94b67d156160f167958a730c41f60","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:23.869584Z","signature_b64":"y0sPSwVN7lEHiWU4I04H1z0rAFvRHfccA89PqXfOSFhOdm/wiUXcMLFsrFzhPMqIdeK9EPsTpcwz5eNgjPd6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb63702dad56fc0f1a736b411cf9cb624be94b67d156160f167958a730c41f60","last_reissued_at":"2026-07-05T11:56:23.869145Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:23.869145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.14045","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:56:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iND+JAUdZxFuM692wEKWlHAiBafUCyuRckLcHQLFbLTWIMhnkWljKjbsupWX81KmjljG6Jq8s/FGxVD/BsNSCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:25:57.316636Z"},"content_sha256":"ee0451fd06fc2adc6497eb44f89b202bc1e13faab91e52a1bf4ed79d8faa5462","schema_version":"1.0","event_id":"sha256:ee0451fd06fc2adc6497eb44f89b202bc1e13faab91e52a1bf4ed79d8faa5462"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZNRXALNNK36A6GTTNNARZ6OLMJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Image Captioning to Visual Storytelling","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Admitos Passadakis, Albert Gatt, Yingjin Song","submitted_at":"2025-07-31T16:44:23Z","abstract_excerpt":"Visual Storytelling is a challenging multimodal task between Vision & Language, where the purpose is to generate a story for a stream of images. Its difficulty lies on the fact that the story should be both grounded to the image sequence but also narrative and coherent. The aim of this work is to balance between these aspects, by treating Visual Storytelling as a superset of Image Captioning, an approach quite different compared to most of prior relevant studies. This means that we firstly employ a vision-to-language model for obtaining captions of the input images, and then, these captions ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14045","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/2508.14045/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":"2026-07-05T11:56:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u1Mgx67J5DarYdCpgiot6ZyZRjHzrz1IiyDN5sbhVfIlgxuZ3mOQbsbm0bQV6K/b0y1F7FJg4eCp/28lmXiiCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:25:57.317656Z"},"content_sha256":"c263a8f8dd53b4d3fd0f07ce112fd4ff19a11c6df6d400ac9b0fbec21828b12a","schema_version":"1.0","event_id":"sha256:c263a8f8dd53b4d3fd0f07ce112fd4ff19a11c6df6d400ac9b0fbec21828b12a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZNRXALNNK36A6GTTNNARZ6OLMJ/bundle.json","state_url":"https://pith.science/pith/ZNRXALNNK36A6GTTNNARZ6OLMJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZNRXALNNK36A6GTTNNARZ6OLMJ/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":"2026-08-06T17:25:57Z","links":{"resolver":"https://pith.science/pith/ZNRXALNNK36A6GTTNNARZ6OLMJ","bundle":"https://pith.science/pith/ZNRXALNNK36A6GTTNNARZ6OLMJ/bundle.json","state":"https://pith.science/pith/ZNRXALNNK36A6GTTNNARZ6OLMJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZNRXALNNK36A6GTTNNARZ6OLMJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZNRXALNNK36A6GTTNNARZ6OLMJ","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":"c50e7f27bb5868eded2a981af3883e8a4b3d288c5cde3c7795ab8ca1b4859570","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-31T16:44:23Z","title_canon_sha256":"b3af69c0c9ab63a6f6afbd6589980a608ebd008af4671dfb817ea00f0dbc228a"},"schema_version":"1.0","source":{"id":"2508.14045","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.14045","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"arxiv_version","alias_value":"2508.14045v1","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14045","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"pith_short_12","alias_value":"ZNRXALNNK36A","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"pith_short_16","alias_value":"ZNRXALNNK36A6GTT","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"pith_short_8","alias_value":"ZNRXALNN","created_at":"2026-07-05T11:56:23Z"}],"graph_snapshots":[{"event_id":"sha256:c263a8f8dd53b4d3fd0f07ce112fd4ff19a11c6df6d400ac9b0fbec21828b12a","target":"graph","created_at":"2026-07-05T11:56:23Z","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/2508.14045/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Storytelling is a challenging multimodal task between Vision & Language, where the purpose is to generate a story for a stream of images. Its difficulty lies on the fact that the story should be both grounded to the image sequence but also narrative and coherent. The aim of this work is to balance between these aspects, by treating Visual Storytelling as a superset of Image Captioning, an approach quite different compared to most of prior relevant studies. This means that we firstly employ a vision-to-language model for obtaining captions of the input images, and then, these captions ar","authors_text":"Admitos Passadakis, Albert Gatt, Yingjin Song","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-31T16:44:23Z","title":"From Image Captioning to Visual Storytelling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14045","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:ee0451fd06fc2adc6497eb44f89b202bc1e13faab91e52a1bf4ed79d8faa5462","target":"record","created_at":"2026-07-05T11:56:23Z","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":"c50e7f27bb5868eded2a981af3883e8a4b3d288c5cde3c7795ab8ca1b4859570","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-31T16:44:23Z","title_canon_sha256":"b3af69c0c9ab63a6f6afbd6589980a608ebd008af4671dfb817ea00f0dbc228a"},"schema_version":"1.0","source":{"id":"2508.14045","kind":"arxiv","version":1}},"canonical_sha256":"cb63702dad56fc0f1a736b411cf9cb624be94b67d156160f167958a730c41f60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb63702dad56fc0f1a736b411cf9cb624be94b67d156160f167958a730c41f60","first_computed_at":"2026-07-05T11:56:23.869145Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:23.869145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y0sPSwVN7lEHiWU4I04H1z0rAFvRHfccA89PqXfOSFhOdm/wiUXcMLFsrFzhPMqIdeK9EPsTpcwz5eNgjPd6Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:23.869584Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.14045","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee0451fd06fc2adc6497eb44f89b202bc1e13faab91e52a1bf4ed79d8faa5462","sha256:c263a8f8dd53b4d3fd0f07ce112fd4ff19a11c6df6d400ac9b0fbec21828b12a"],"state_sha256":"df5fd4a6cf63988c3ed6fb56a46de15c85ea86f9d58fa0433b891e32da8c7ed8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x/V5GsN+13+BUM+j/QTuR8hk9Vh6bsoXwb/W3E5EX4TdLrcL+7sYJDFp21/MWotZ1qZ6Fq2TaJ/0VYdk6rAxBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:25:57.326753Z","bundle_sha256":"b65ff32799a405efbbe9c48a7a0f7a1617a492d78418ab7b45ee0c45048cedfc"}}