{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:TNU6T3Q7EGSM7PR3HNYNCZSC5U","short_pith_number":"pith:TNU6T3Q7","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"},"canonical_sha256":"9b69e9ee1f21a4cfbe3b3b70d16642ed034b64a96ceb86ce521234c043bfc568","source":{"kind":"arxiv","id":"1808.10584","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.10584","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"arxiv_version","alias_value":"1808.10584v1","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.10584","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"pith_short_12","alias_value":"TNU6T3Q7EGSM","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"TNU6T3Q7EGSM7PR3","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"TNU6T3Q7","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:TNU6T3Q7EGSM7PR3HNYNCZSC5U","target":"record","payload":{"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"},"canonical_sha256":"9b69e9ee1f21a4cfbe3b3b70d16642ed034b64a96ceb86ce521234c043bfc568","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"},"source_kind":"arxiv","source_id":"1808.10584","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":"2026-05-18T00:06:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4m+/Uhf2zYOdKvg974TGbK3lu872Jd6mNghuEb2YNyBF8BbkaOwh8dQKQYwHTKp9XZPZkA/j1ZU/bopuwhunCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T18:01:32.555208Z"},"content_sha256":"8f620975c5bfc6671926fb06209dcdeafc5c7ae919be5d53b56e63a9801e3d66","schema_version":"1.0","event_id":"sha256:8f620975c5bfc6671926fb06209dcdeafc5c7ae919be5d53b56e63a9801e3d66"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:TNU6T3Q7EGSM7PR3HNYNCZSC5U","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:06:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RHH6FpPTTrdVDbKSu67wo9mP8U90Rh5aocuHUbnGt0WsJxYCnCJsW2f1AN7tScgY5BdLkT/lSfXzkCL9ms0kAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T18:01:32.555844Z"},"content_sha256":"9c65ddd21e3b65a0c899845729b876cc9a0be2bf69b685eb83a9a8cab589074b","schema_version":"1.0","event_id":"sha256:9c65ddd21e3b65a0c899845729b876cc9a0be2bf69b685eb83a9a8cab589074b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TNU6T3Q7EGSM7PR3HNYNCZSC5U/bundle.json","state_url":"https://pith.science/pith/TNU6T3Q7EGSM7PR3HNYNCZSC5U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TNU6T3Q7EGSM7PR3HNYNCZSC5U/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":"2026-06-07T18:01:32Z","links":{"resolver":"https://pith.science/pith/TNU6T3Q7EGSM7PR3HNYNCZSC5U","bundle":"https://pith.science/pith/TNU6T3Q7EGSM7PR3HNYNCZSC5U/bundle.json","state":"https://pith.science/pith/TNU6T3Q7EGSM7PR3HNYNCZSC5U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TNU6T3Q7EGSM7PR3HNYNCZSC5U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:TNU6T3Q7EGSM7PR3HNYNCZSC5U","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":"5b5a265a3b95fefff9c8f5c679cf9908dd72227a3341eca74f7bddfcf6761b50","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-31T03:15:28Z","title_canon_sha256":"31b5577017d3abf28e196584b4b3bea5031d9a3bd02ce6c553cf716df38a29f2"},"schema_version":"1.0","source":{"id":"1808.10584","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.10584","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"arxiv_version","alias_value":"1808.10584v1","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.10584","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"pith_short_12","alias_value":"TNU6T3Q7EGSM","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"TNU6T3Q7EGSM7PR3","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"TNU6T3Q7","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:9c65ddd21e3b65a0c899845729b876cc9a0be2bf69b685eb83a9a8cab589074b","target":"graph","created_at":"2026-05-18T00:06:45Z","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"},"paper":{"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","authors_text":"Harsh Jhamtani, Taylor Berg-Kirkpatrick","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-31T03:15:28Z","title":"Learning to Describe Differences Between Pairs of Similar Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.10584","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":"sha256:8f620975c5bfc6671926fb06209dcdeafc5c7ae919be5d53b56e63a9801e3d66","target":"record","created_at":"2026-05-18T00:06:45Z","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":"5b5a265a3b95fefff9c8f5c679cf9908dd72227a3341eca74f7bddfcf6761b50","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-31T03:15:28Z","title_canon_sha256":"31b5577017d3abf28e196584b4b3bea5031d9a3bd02ce6c553cf716df38a29f2"},"schema_version":"1.0","source":{"id":"1808.10584","kind":"arxiv","version":1}},"canonical_sha256":"9b69e9ee1f21a4cfbe3b3b70d16642ed034b64a96ceb86ce521234c043bfc568","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b69e9ee1f21a4cfbe3b3b70d16642ed034b64a96ceb86ce521234c043bfc568","first_computed_at":"2026-05-18T00:06:45.305487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:45.305487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q5KkenSBGaTgGLXTFdzfpAd/sgXqIIER4V6d2ZxPsv9IRDcUqTUyFDkVSaQNS3PTlX11HIKP0nnYQOTVIeyNAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:45.306015Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.10584","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f620975c5bfc6671926fb06209dcdeafc5c7ae919be5d53b56e63a9801e3d66","sha256:9c65ddd21e3b65a0c899845729b876cc9a0be2bf69b685eb83a9a8cab589074b"],"state_sha256":"b40cc11c3662d98924456d62ced5f3ecd4ebe104a4e0d5cec9e641a606595ce1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HJctd0aiC9uB4uLvWrUqwTP9WmoLbK8/p03E3HEKbAf+GNdUZN3xx7f2xw/gI75v258J4SYb5dzyvLyEIRpCBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T18:01:32.559784Z","bundle_sha256":"709fe1482030a745043cda259fba8feca058a736037e440470101e56d825dd11"}}