{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TNU6T3Q7EGSM7PR3HNYNCZSC5U","short_pith_number":"pith:TNU6T3Q7","schema_version":"1.0","canonical_sha256":"9b69e9ee1f21a4cfbe3b3b70d16642ed034b64a96ceb86ce521234c043bfc568","source":{"kind":"arxiv","id":"1808.10584","version":1},"attestation_state":"computed","paper":{"title":"Learning to Describe Differences Between Pairs of Similar Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Harsh Jhamtani, Taylor Berg-Kirkpatrick","submitted_at":"2018-08-31T03:15:28Z","abstract_excerpt":"In this paper, we introduce the task of automatically generating text to describe the differences between two similar images. We collect a new dataset by crowd-sourcing difference descriptions for pairs of image frames extracted from video-surveillance footage. Annotators were asked to succinctly describe all the differences in a short paragraph. As a result, our novel dataset provides an opportunity to explore models that align language and vision, and capture visual salience. The dataset may also be a useful benchmark for coherent multi-sentence generation. We perform a firstpass visual anal"},"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":"1808.10584","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-31T03:15:28Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"31b5577017d3abf28e196584b4b3bea5031d9a3bd02ce6c553cf716df38a29f2","abstract_canon_sha256":"5b5a265a3b95fefff9c8f5c679cf9908dd72227a3341eca74f7bddfcf6761b50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:45.306015Z","signature_b64":"q5KkenSBGaTgGLXTFdzfpAd/sgXqIIER4V6d2ZxPsv9IRDcUqTUyFDkVSaQNS3PTlX11HIKP0nnYQOTVIeyNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b69e9ee1f21a4cfbe3b3b70d16642ed034b64a96ceb86ce521234c043bfc568","last_reissued_at":"2026-05-18T00:06:45.305487Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:45.305487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Describe Differences Between Pairs of Similar Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Harsh Jhamtani, Taylor Berg-Kirkpatrick","submitted_at":"2018-08-31T03:15:28Z","abstract_excerpt":"In this paper, we introduce the task of automatically generating text to describe the differences between two similar images. We collect a new dataset by crowd-sourcing difference descriptions for pairs of image frames extracted from video-surveillance footage. Annotators were asked to succinctly describe all the differences in a short paragraph. As a result, our novel dataset provides an opportunity to explore models that align language and vision, and capture visual salience. The dataset may also be a useful benchmark for coherent multi-sentence generation. We perform a firstpass visual anal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.10584","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":""},"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":"1808.10584","created_at":"2026-05-18T00:06:45.305570+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.10584v1","created_at":"2026-05-18T00:06:45.305570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.10584","created_at":"2026-05-18T00:06:45.305570+00:00"},{"alias_kind":"pith_short_12","alias_value":"TNU6T3Q7EGSM","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"TNU6T3Q7EGSM7PR3","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"TNU6T3Q7","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.03326","citing_title":"LLaVA-OneVision: Easy Visual Task Transfer","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TNU6T3Q7EGSM7PR3HNYNCZSC5U","json":"https://pith.science/pith/TNU6T3Q7EGSM7PR3HNYNCZSC5U.json","graph_json":"https://pith.science/api/pith-number/TNU6T3Q7EGSM7PR3HNYNCZSC5U/graph.json","events_json":"https://pith.science/api/pith-number/TNU6T3Q7EGSM7PR3HNYNCZSC5U/events.json","paper":"https://pith.science/paper/TNU6T3Q7"},"agent_actions":{"view_html":"https://pith.science/pith/TNU6T3Q7EGSM7PR3HNYNCZSC5U","download_json":"https://pith.science/pith/TNU6T3Q7EGSM7PR3HNYNCZSC5U.json","view_paper":"https://pith.science/paper/TNU6T3Q7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.10584&json=true","fetch_graph":"https://pith.science/api/pith-number/TNU6T3Q7EGSM7PR3HNYNCZSC5U/graph.json","fetch_events":"https://pith.science/api/pith-number/TNU6T3Q7EGSM7PR3HNYNCZSC5U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TNU6T3Q7EGSM7PR3HNYNCZSC5U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TNU6T3Q7EGSM7PR3HNYNCZSC5U/action/storage_attestation","attest_author":"https://pith.science/pith/TNU6T3Q7EGSM7PR3HNYNCZSC5U/action/author_attestation","sign_citation":"https://pith.science/pith/TNU6T3Q7EGSM7PR3HNYNCZSC5U/action/citation_signature","submit_replication":"https://pith.science/pith/TNU6T3Q7EGSM7PR3HNYNCZSC5U/action/replication_record"}},"created_at":"2026-05-18T00:06:45.305570+00:00","updated_at":"2026-05-18T00:06:45.305570+00:00"}