{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7EXM3PXBCBV2TKZS3VERPYDMMM","short_pith_number":"pith:7EXM3PXB","schema_version":"1.0","canonical_sha256":"f92ecdbee1106ba9ab32dd4917e06c633e96e56a4e466e2dec661aa858533b24","source":{"kind":"arxiv","id":"2506.12009","version":2},"attestation_state":"computed","paper":{"title":"Affogato: Open-Vocabulary Affordance Grounding with Automated Data Generation at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunghyun Park, Dahyun Kang, Eunha Park, Junha Lee, Minsu Cho","submitted_at":"2025-06-13T17:57:18Z","abstract_excerpt":"Affordance grounding aims to localize where to interact with an object, a fundamental capability for embodied agents. Yet progress is bottlenecked by data: manual annotation is prohibitively expensive and confines existing datasets to a narrow set of predefined object and affordance categories. We introduce Affogato, a framework for open-vocabulary affordance grounding centered on Affogato-750K, a large-scale dataset of 750K 3D affordance heatmaps paired with natural language queries. We build it with a fully automated pipeline that orchestrates foundation models to generate them at scale with"},"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":"2506.12009","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T17:57:18Z","cross_cats_sorted":[],"title_canon_sha256":"3d20d6269fb9fb5d2d3f73b65147966409eb39198b1f69f601f19c2c3e19bb87","abstract_canon_sha256":"6cdc8e0ca515805855dfa5b60e5fdc0ec507cae9f3755866fb45c802d92347d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:12.691921Z","signature_b64":"RplKRJZReFn+G6I6SNP1KHBW5F3eS2+yMb3i7GHNOZUgMzysisqbbInWStMwCNucELxv5Qj1mJp/taEpezG9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f92ecdbee1106ba9ab32dd4917e06c633e96e56a4e466e2dec661aa858533b24","last_reissued_at":"2026-07-02T01:17:12.691434Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:12.691434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Affogato: Open-Vocabulary Affordance Grounding with Automated Data Generation at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunghyun Park, Dahyun Kang, Eunha Park, Junha Lee, Minsu Cho","submitted_at":"2025-06-13T17:57:18Z","abstract_excerpt":"Affordance grounding aims to localize where to interact with an object, a fundamental capability for embodied agents. Yet progress is bottlenecked by data: manual annotation is prohibitively expensive and confines existing datasets to a narrow set of predefined object and affordance categories. We introduce Affogato, a framework for open-vocabulary affordance grounding centered on Affogato-750K, a large-scale dataset of 750K 3D affordance heatmaps paired with natural language queries. We build it with a fully automated pipeline that orchestrates foundation models to generate them at scale with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12009","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/2506.12009/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":"2506.12009","created_at":"2026-07-02T01:17:12.691488+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12009v2","created_at":"2026-07-02T01:17:12.691488+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12009","created_at":"2026-07-02T01:17:12.691488+00:00"},{"alias_kind":"pith_short_12","alias_value":"7EXM3PXBCBV2","created_at":"2026-07-02T01:17:12.691488+00:00"},{"alias_kind":"pith_short_16","alias_value":"7EXM3PXBCBV2TKZS","created_at":"2026-07-02T01:17:12.691488+00:00"},{"alias_kind":"pith_short_8","alias_value":"7EXM3PXB","created_at":"2026-07-02T01:17:12.691488+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2605.14923","citing_title":"SceneParser: Hierarchical Scene Parsing for Visual Semantics Understanding","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02060","citing_title":"CompassAD: Intent-Driven 3D Affordance Grounding in Functionally Competing Objects","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17517","citing_title":"AffordVLA: Injecting Affordance Representations into Vision-Language-Action Models via Implicit Feature Alignment","ref_index":67,"is_internal_anchor":true},{"citing_arxiv_id":"2601.09211","citing_title":"Affostruction: 3D Affordance Grounding with Generative Reconstruction","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7EXM3PXBCBV2TKZS3VERPYDMMM","json":"https://pith.science/pith/7EXM3PXBCBV2TKZS3VERPYDMMM.json","graph_json":"https://pith.science/api/pith-number/7EXM3PXBCBV2TKZS3VERPYDMMM/graph.json","events_json":"https://pith.science/api/pith-number/7EXM3PXBCBV2TKZS3VERPYDMMM/events.json","paper":"https://pith.science/paper/7EXM3PXB"},"agent_actions":{"view_html":"https://pith.science/pith/7EXM3PXBCBV2TKZS3VERPYDMMM","download_json":"https://pith.science/pith/7EXM3PXBCBV2TKZS3VERPYDMMM.json","view_paper":"https://pith.science/paper/7EXM3PXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12009&json=true","fetch_graph":"https://pith.science/api/pith-number/7EXM3PXBCBV2TKZS3VERPYDMMM/graph.json","fetch_events":"https://pith.science/api/pith-number/7EXM3PXBCBV2TKZS3VERPYDMMM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7EXM3PXBCBV2TKZS3VERPYDMMM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7EXM3PXBCBV2TKZS3VERPYDMMM/action/storage_attestation","attest_author":"https://pith.science/pith/7EXM3PXBCBV2TKZS3VERPYDMMM/action/author_attestation","sign_citation":"https://pith.science/pith/7EXM3PXBCBV2TKZS3VERPYDMMM/action/citation_signature","submit_replication":"https://pith.science/pith/7EXM3PXBCBV2TKZS3VERPYDMMM/action/replication_record"}},"created_at":"2026-07-02T01:17:12.691488+00:00","updated_at":"2026-07-02T01:17:12.691488+00:00"}