{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S2FXT7L4FNOW4ZO5O54WIZITXG","short_pith_number":"pith:S2FXT7L4","schema_version":"1.0","canonical_sha256":"968b79fd7c2b5d6e65dd7779646513b9879c4d661d96bc98833eaf961c0ca9e7","source":{"kind":"arxiv","id":"2506.09847","version":1},"attestation_state":"computed","paper":{"title":"Dataset of News Articles with Provenance Metadata for Media Relevance Assessment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.CY"],"primary_cat":"cs.CL","authors_text":"Matyas Bohacek, Tomas Peterka","submitted_at":"2025-06-11T15:21:05Z","abstract_excerpt":"Out-of-context and misattributed imagery is the leading form of media manipulation in today's misinformation and disinformation landscape. The existing methods attempting to detect this practice often only consider whether the semantics of the imagery corresponds to the text narrative, missing manipulation so long as the depicted objects or scenes somewhat correspond to the narrative at hand. To tackle this, we introduce News Media Provenance Dataset, a dataset of news articles with provenance-tagged images. We formulate two tasks on this dataset, location of origin relevance (LOR) and date an"},"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":"2506.09847","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T15:21:05Z","cross_cats_sorted":["cs.AI","cs.CV","cs.CY"],"title_canon_sha256":"477cdd2cbc5258779cb87a353ea3868e6935a3f338b4faefa3f11f09a78350fa","abstract_canon_sha256":"fea09a31df59bceff805809428680b8c66e0b2faa9711d14639569b8e5ccbf7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:57.959092Z","signature_b64":"pvzbqsk/5x/2HHI/qooqDHb3FYYoykvzC5IhbFB3+qQf3QKQFUB0FZH4a92/D8hUGk/LnnFk+myTtuvXfR7dBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"968b79fd7c2b5d6e65dd7779646513b9879c4d661d96bc98833eaf961c0ca9e7","last_reissued_at":"2026-07-05T11:19:57.958620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:57.958620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dataset of News Articles with Provenance Metadata for Media Relevance Assessment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.CY"],"primary_cat":"cs.CL","authors_text":"Matyas Bohacek, Tomas Peterka","submitted_at":"2025-06-11T15:21:05Z","abstract_excerpt":"Out-of-context and misattributed imagery is the leading form of media manipulation in today's misinformation and disinformation landscape. The existing methods attempting to detect this practice often only consider whether the semantics of the imagery corresponds to the text narrative, missing manipulation so long as the depicted objects or scenes somewhat correspond to the narrative at hand. To tackle this, we introduce News Media Provenance Dataset, a dataset of news articles with provenance-tagged images. We formulate two tasks on this dataset, location of origin relevance (LOR) and date an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09847","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/2506.09847/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.09847","created_at":"2026-07-05T11:19:57.958677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09847v1","created_at":"2026-07-05T11:19:57.958677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09847","created_at":"2026-07-05T11:19:57.958677+00:00"},{"alias_kind":"pith_short_12","alias_value":"S2FXT7L4FNOW","created_at":"2026-07-05T11:19:57.958677+00:00"},{"alias_kind":"pith_short_16","alias_value":"S2FXT7L4FNOW4ZO5","created_at":"2026-07-05T11:19:57.958677+00:00"},{"alias_kind":"pith_short_8","alias_value":"S2FXT7L4","created_at":"2026-07-05T11:19:57.958677+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S2FXT7L4FNOW4ZO5O54WIZITXG","json":"https://pith.science/pith/S2FXT7L4FNOW4ZO5O54WIZITXG.json","graph_json":"https://pith.science/api/pith-number/S2FXT7L4FNOW4ZO5O54WIZITXG/graph.json","events_json":"https://pith.science/api/pith-number/S2FXT7L4FNOW4ZO5O54WIZITXG/events.json","paper":"https://pith.science/paper/S2FXT7L4"},"agent_actions":{"view_html":"https://pith.science/pith/S2FXT7L4FNOW4ZO5O54WIZITXG","download_json":"https://pith.science/pith/S2FXT7L4FNOW4ZO5O54WIZITXG.json","view_paper":"https://pith.science/paper/S2FXT7L4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09847&json=true","fetch_graph":"https://pith.science/api/pith-number/S2FXT7L4FNOW4ZO5O54WIZITXG/graph.json","fetch_events":"https://pith.science/api/pith-number/S2FXT7L4FNOW4ZO5O54WIZITXG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S2FXT7L4FNOW4ZO5O54WIZITXG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S2FXT7L4FNOW4ZO5O54WIZITXG/action/storage_attestation","attest_author":"https://pith.science/pith/S2FXT7L4FNOW4ZO5O54WIZITXG/action/author_attestation","sign_citation":"https://pith.science/pith/S2FXT7L4FNOW4ZO5O54WIZITXG/action/citation_signature","submit_replication":"https://pith.science/pith/S2FXT7L4FNOW4ZO5O54WIZITXG/action/replication_record"}},"created_at":"2026-07-05T11:19:57.958677+00:00","updated_at":"2026-07-05T11:19:57.958677+00:00"}