{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S47YFGI3W32MJKXXHJ67AOXUH2","short_pith_number":"pith:S47YFGI3","schema_version":"1.0","canonical_sha256":"973f82991bb6f4c4aaf73a7df03af43eb3a70688925f3e67d41add056d69498e","source":{"kind":"arxiv","id":"2503.11509","version":3},"attestation_state":"computed","paper":{"title":"TikZero: Zero-Shot Text-Guided Graphics Program Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Eddy Ilg, Hideki Tanaka, Jonas Belouadi, Margret Keuper, Masao Utiyama, Raj Dabre, Simone Paolo Ponzetto, Steffen Eger","submitted_at":"2025-03-14T15:29:58Z","abstract_excerpt":"Automatically synthesizing figures from text captions is a compelling capability. However, achieving high geometric precision and editability requires representing figures as graphics programs in languages like TikZ, and aligned training data (i.e., graphics programs with captions) remains scarce. Meanwhile, large amounts of unaligned graphics programs and captioned raster images are more readily available. We reconcile these disparate data sources by presenting TikZero, which decouples graphics program generation from text understanding by using image representations as an intermediary bridge"},"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":"2503.11509","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-14T15:29:58Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4ccda4a18e32f20438f9d4f4af7666b9e038c2b216370b5eebaedd47c8fd042e","abstract_canon_sha256":"5b3bf22ee3bc0ac583e34bf65a749caedee575a6a2da4b653fd25c842dee2361"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:44.892255Z","signature_b64":"RaqEzQklEyBa27UdTG/mNE7cNfJGdllwEcQCw/cXqgOFaW+lxzmRrAU2QED+t/DvqV03V9+Xzo6DX2XOjeB7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"973f82991bb6f4c4aaf73a7df03af43eb3a70688925f3e67d41add056d69498e","last_reissued_at":"2026-07-05T11:53:44.891770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:44.891770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TikZero: Zero-Shot Text-Guided Graphics Program Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Eddy Ilg, Hideki Tanaka, Jonas Belouadi, Margret Keuper, Masao Utiyama, Raj Dabre, Simone Paolo Ponzetto, Steffen Eger","submitted_at":"2025-03-14T15:29:58Z","abstract_excerpt":"Automatically synthesizing figures from text captions is a compelling capability. However, achieving high geometric precision and editability requires representing figures as graphics programs in languages like TikZ, and aligned training data (i.e., graphics programs with captions) remains scarce. Meanwhile, large amounts of unaligned graphics programs and captioned raster images are more readily available. We reconcile these disparate data sources by presenting TikZero, which decouples graphics program generation from text understanding by using image representations as an intermediary bridge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11509","kind":"arxiv","version":3},"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/2503.11509/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":"2503.11509","created_at":"2026-07-05T11:53:44.891829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.11509v3","created_at":"2026-07-05T11:53:44.891829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11509","created_at":"2026-07-05T11:53:44.891829+00:00"},{"alias_kind":"pith_short_12","alias_value":"S47YFGI3W32M","created_at":"2026-07-05T11:53:44.891829+00:00"},{"alias_kind":"pith_short_16","alias_value":"S47YFGI3W32MJKXX","created_at":"2026-07-05T11:53:44.891829+00:00"},{"alias_kind":"pith_short_8","alias_value":"S47YFGI3","created_at":"2026-07-05T11:53:44.891829+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20576","citing_title":"$\\Delta$ynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videos","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S47YFGI3W32MJKXXHJ67AOXUH2","json":"https://pith.science/pith/S47YFGI3W32MJKXXHJ67AOXUH2.json","graph_json":"https://pith.science/api/pith-number/S47YFGI3W32MJKXXHJ67AOXUH2/graph.json","events_json":"https://pith.science/api/pith-number/S47YFGI3W32MJKXXHJ67AOXUH2/events.json","paper":"https://pith.science/paper/S47YFGI3"},"agent_actions":{"view_html":"https://pith.science/pith/S47YFGI3W32MJKXXHJ67AOXUH2","download_json":"https://pith.science/pith/S47YFGI3W32MJKXXHJ67AOXUH2.json","view_paper":"https://pith.science/paper/S47YFGI3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.11509&json=true","fetch_graph":"https://pith.science/api/pith-number/S47YFGI3W32MJKXXHJ67AOXUH2/graph.json","fetch_events":"https://pith.science/api/pith-number/S47YFGI3W32MJKXXHJ67AOXUH2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S47YFGI3W32MJKXXHJ67AOXUH2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S47YFGI3W32MJKXXHJ67AOXUH2/action/storage_attestation","attest_author":"https://pith.science/pith/S47YFGI3W32MJKXXHJ67AOXUH2/action/author_attestation","sign_citation":"https://pith.science/pith/S47YFGI3W32MJKXXHJ67AOXUH2/action/citation_signature","submit_replication":"https://pith.science/pith/S47YFGI3W32MJKXXHJ67AOXUH2/action/replication_record"}},"created_at":"2026-07-05T11:53:44.891829+00:00","updated_at":"2026-07-05T11:53:44.891829+00:00"}