{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JAD4GEPQHCHCPHWRJI4H2DJYPH","short_pith_number":"pith:JAD4GEPQ","canonical_record":{"source":{"id":"2301.11030","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-26T10:54:51Z","cross_cats_sorted":[],"title_canon_sha256":"cadbadbbb246b03552aa64581b3d7c46b832ce99751b01182e15702ccdda9180","abstract_canon_sha256":"9b42974c4f8aba18f41668516241d56c808338d1eb8f3db3bb8724eba2f6e32b"},"schema_version":"1.0"},"canonical_sha256":"4807c311f0388e279ed14a387d0d3879eab48c7fceb6730f75d196b80ebef72b","source":{"kind":"arxiv","id":"2301.11030","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.11030","created_at":"2026-07-05T05:42:02Z"},{"alias_kind":"arxiv_version","alias_value":"2301.11030v2","created_at":"2026-07-05T05:42:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11030","created_at":"2026-07-05T05:42:02Z"},{"alias_kind":"pith_short_12","alias_value":"JAD4GEPQHCHC","created_at":"2026-07-05T05:42:02Z"},{"alias_kind":"pith_short_16","alias_value":"JAD4GEPQHCHCPHWR","created_at":"2026-07-05T05:42:02Z"},{"alias_kind":"pith_short_8","alias_value":"JAD4GEPQ","created_at":"2026-07-05T05:42:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JAD4GEPQHCHCPHWRJI4H2DJYPH","target":"record","payload":{"canonical_record":{"source":{"id":"2301.11030","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-26T10:54:51Z","cross_cats_sorted":[],"title_canon_sha256":"cadbadbbb246b03552aa64581b3d7c46b832ce99751b01182e15702ccdda9180","abstract_canon_sha256":"9b42974c4f8aba18f41668516241d56c808338d1eb8f3db3bb8724eba2f6e32b"},"schema_version":"1.0"},"canonical_sha256":"4807c311f0388e279ed14a387d0d3879eab48c7fceb6730f75d196b80ebef72b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:02.658220Z","signature_b64":"+QFgudLiljMMSqRALqmzdCi4yd5eBqp/gukIEXlzn0F70OhYb+d0ma7oR5GAgtisbhczegHTj4MIZ65bdkrlAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4807c311f0388e279ed14a387d0d3879eab48c7fceb6730f75d196b80ebef72b","last_reissued_at":"2026-07-05T05:42:02.657725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:02.657725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.11030","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:42:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YjGI5zGZPbP+VOlChh9g0l9V65xXxVAfL5Vfm6NNYyzELiZXttiHLzu88U8cOQGIno0+TDQgfBnlNT8yM1FHBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:22:11.118926Z"},"content_sha256":"6e18e93be3e5d74c176e59cd3549aaba338e8e7bd9bb5e18f1570aea9bace665","schema_version":"1.0","event_id":"sha256:6e18e93be3e5d74c176e59cd3549aaba338e8e7bd9bb5e18f1570aea9bace665"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JAD4GEPQHCHCPHWRJI4H2DJYPH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Paraphrase Acquisition from Image Captions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benno Stein, Marcel Gohsen, Martin Potthast, Matthias Hagen","submitted_at":"2023-01-26T10:54:51Z","abstract_excerpt":"We propose to use image captions from the Web as a previously underutilized resource for paraphrases (i.e., texts with the same \"message\") and to create and analyze a corresponding dataset. When an image is reused on the Web, an original caption is often assigned. We hypothesize that different captions for the same image naturally form a set of mutual paraphrases. To demonstrate the suitability of this idea, we analyze captions in the English Wikipedia, where editors frequently relabel the same image for different articles. The paper introduces the underlying mining technology, the resulting W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11030","kind":"arxiv","version":2},"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/2301.11030/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":"2026-07-05T05:42:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9gPZR9v/ARPOk+GDnuC2deJyxJSiQ/4ALmdH83hhft+9Cor9OtXrblLwneVfVi2PD4Pf1JTZlv1ANU8SeirqAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:22:11.119519Z"},"content_sha256":"d8e738763e32d67680342a804916f4ba87a50308516e4922aa4b0ebbb74c38a7","schema_version":"1.0","event_id":"sha256:d8e738763e32d67680342a804916f4ba87a50308516e4922aa4b0ebbb74c38a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JAD4GEPQHCHCPHWRJI4H2DJYPH/bundle.json","state_url":"https://pith.science/pith/JAD4GEPQHCHCPHWRJI4H2DJYPH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JAD4GEPQHCHCPHWRJI4H2DJYPH/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":"2026-08-07T06:22:11Z","links":{"resolver":"https://pith.science/pith/JAD4GEPQHCHCPHWRJI4H2DJYPH","bundle":"https://pith.science/pith/JAD4GEPQHCHCPHWRJI4H2DJYPH/bundle.json","state":"https://pith.science/pith/JAD4GEPQHCHCPHWRJI4H2DJYPH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JAD4GEPQHCHCPHWRJI4H2DJYPH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JAD4GEPQHCHCPHWRJI4H2DJYPH","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":"9b42974c4f8aba18f41668516241d56c808338d1eb8f3db3bb8724eba2f6e32b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-26T10:54:51Z","title_canon_sha256":"cadbadbbb246b03552aa64581b3d7c46b832ce99751b01182e15702ccdda9180"},"schema_version":"1.0","source":{"id":"2301.11030","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.11030","created_at":"2026-07-05T05:42:02Z"},{"alias_kind":"arxiv_version","alias_value":"2301.11030v2","created_at":"2026-07-05T05:42:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11030","created_at":"2026-07-05T05:42:02Z"},{"alias_kind":"pith_short_12","alias_value":"JAD4GEPQHCHC","created_at":"2026-07-05T05:42:02Z"},{"alias_kind":"pith_short_16","alias_value":"JAD4GEPQHCHCPHWR","created_at":"2026-07-05T05:42:02Z"},{"alias_kind":"pith_short_8","alias_value":"JAD4GEPQ","created_at":"2026-07-05T05:42:02Z"}],"graph_snapshots":[{"event_id":"sha256:d8e738763e32d67680342a804916f4ba87a50308516e4922aa4b0ebbb74c38a7","target":"graph","created_at":"2026-07-05T05:42:02Z","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/2301.11030/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose to use image captions from the Web as a previously underutilized resource for paraphrases (i.e., texts with the same \"message\") and to create and analyze a corresponding dataset. When an image is reused on the Web, an original caption is often assigned. We hypothesize that different captions for the same image naturally form a set of mutual paraphrases. To demonstrate the suitability of this idea, we analyze captions in the English Wikipedia, where editors frequently relabel the same image for different articles. The paper introduces the underlying mining technology, the resulting W","authors_text":"Benno Stein, Marcel Gohsen, Martin Potthast, Matthias Hagen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-26T10:54:51Z","title":"Paraphrase Acquisition from Image Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11030","kind":"arxiv","version":2},"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":"sha256:6e18e93be3e5d74c176e59cd3549aaba338e8e7bd9bb5e18f1570aea9bace665","target":"record","created_at":"2026-07-05T05:42:02Z","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":"9b42974c4f8aba18f41668516241d56c808338d1eb8f3db3bb8724eba2f6e32b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-26T10:54:51Z","title_canon_sha256":"cadbadbbb246b03552aa64581b3d7c46b832ce99751b01182e15702ccdda9180"},"schema_version":"1.0","source":{"id":"2301.11030","kind":"arxiv","version":2}},"canonical_sha256":"4807c311f0388e279ed14a387d0d3879eab48c7fceb6730f75d196b80ebef72b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4807c311f0388e279ed14a387d0d3879eab48c7fceb6730f75d196b80ebef72b","first_computed_at":"2026-07-05T05:42:02.657725Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:42:02.657725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+QFgudLiljMMSqRALqmzdCi4yd5eBqp/gukIEXlzn0F70OhYb+d0ma7oR5GAgtisbhczegHTj4MIZ65bdkrlAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:42:02.658220Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.11030","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e18e93be3e5d74c176e59cd3549aaba338e8e7bd9bb5e18f1570aea9bace665","sha256:d8e738763e32d67680342a804916f4ba87a50308516e4922aa4b0ebbb74c38a7"],"state_sha256":"350253fa8295cd09408462ad4b6e3a0ccf6428e9158db5ff605cc115f3657e1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sTnEAKrHlA2YhXx3ucF2yTR+7jnPDaJPORLz7c3sZL8jUFfwxUDkLXKwB/fnO35dy6MS3oZbxX462wKElsheAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:22:11.124743Z","bundle_sha256":"50c4c3c57799c92970dc33f639ca49d428f8da8b8025ca933aa5cc03c5ccd58c"}}