{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W2L63DPEZARJAS7Z4E6JYWKZRI","short_pith_number":"pith:W2L63DPE","schema_version":"1.0","canonical_sha256":"b697ed8de4c822904bf9e13c9c59598a0963a30a108072320b6dc8fb28def6cb","source":{"kind":"arxiv","id":"2504.06661","version":2},"attestation_state":"computed","paper":{"title":"Domain-Conditioned Scene Graphs for State-Grounded Task Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jiangpin Liu, Jonas Herzog, Yue Wang","submitted_at":"2025-04-09T07:51:46Z","abstract_excerpt":"Recent robotic task planning frameworks have integrated large multimodal models (LMMs) such as GPT-4o. To address grounding issues of such models, it has been suggested to split the pipeline into perceptional state grounding and subsequent state-based planning. As we show in this work, the state grounding ability of LMM-based approaches is still limited by weaknesses in granular, structured, domain-specific scene understanding. To address this shortcoming, we develop a more structured state grounding framework that features a domain-conditioned scene graph as its scene representation. We show "},"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":"2504.06661","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-04-09T07:51:46Z","cross_cats_sorted":[],"title_canon_sha256":"a23beb2dfd67f0930bc00b0db4b37b6ab0b003ab6b885456dc7ee062674c38ff","abstract_canon_sha256":"ae5af9cb0545ae5bcb12b7b5a9861709262ae8c4a87eef0c6390d1541768574a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:00.387152Z","signature_b64":"ip60y5pHZs7jdt1rLInr9k6HYJ74o5VbRwBe1T39sIut/FHq+ajECLhDDSvd3kLZhiC37tp8DHIkZwbBtxvfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b697ed8de4c822904bf9e13c9c59598a0963a30a108072320b6dc8fb28def6cb","last_reissued_at":"2026-07-05T12:02:00.386649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:00.386649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain-Conditioned Scene Graphs for State-Grounded Task Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jiangpin Liu, Jonas Herzog, Yue Wang","submitted_at":"2025-04-09T07:51:46Z","abstract_excerpt":"Recent robotic task planning frameworks have integrated large multimodal models (LMMs) such as GPT-4o. To address grounding issues of such models, it has been suggested to split the pipeline into perceptional state grounding and subsequent state-based planning. As we show in this work, the state grounding ability of LMM-based approaches is still limited by weaknesses in granular, structured, domain-specific scene understanding. To address this shortcoming, we develop a more structured state grounding framework that features a domain-conditioned scene graph as its scene representation. We show "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.06661","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/2504.06661/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":"2504.06661","created_at":"2026-07-05T12:02:00.386705+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.06661v2","created_at":"2026-07-05T12:02:00.386705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.06661","created_at":"2026-07-05T12:02:00.386705+00:00"},{"alias_kind":"pith_short_12","alias_value":"W2L63DPEZARJ","created_at":"2026-07-05T12:02:00.386705+00:00"},{"alias_kind":"pith_short_16","alias_value":"W2L63DPEZARJAS7Z","created_at":"2026-07-05T12:02:00.386705+00:00"},{"alias_kind":"pith_short_8","alias_value":"W2L63DPE","created_at":"2026-07-05T12:02:00.386705+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12910","citing_title":"Bounding Boxes as Goals: Language-Conditioned Grasping via Neuro-Symbolic Planning","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W2L63DPEZARJAS7Z4E6JYWKZRI","json":"https://pith.science/pith/W2L63DPEZARJAS7Z4E6JYWKZRI.json","graph_json":"https://pith.science/api/pith-number/W2L63DPEZARJAS7Z4E6JYWKZRI/graph.json","events_json":"https://pith.science/api/pith-number/W2L63DPEZARJAS7Z4E6JYWKZRI/events.json","paper":"https://pith.science/paper/W2L63DPE"},"agent_actions":{"view_html":"https://pith.science/pith/W2L63DPEZARJAS7Z4E6JYWKZRI","download_json":"https://pith.science/pith/W2L63DPEZARJAS7Z4E6JYWKZRI.json","view_paper":"https://pith.science/paper/W2L63DPE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.06661&json=true","fetch_graph":"https://pith.science/api/pith-number/W2L63DPEZARJAS7Z4E6JYWKZRI/graph.json","fetch_events":"https://pith.science/api/pith-number/W2L63DPEZARJAS7Z4E6JYWKZRI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W2L63DPEZARJAS7Z4E6JYWKZRI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W2L63DPEZARJAS7Z4E6JYWKZRI/action/storage_attestation","attest_author":"https://pith.science/pith/W2L63DPEZARJAS7Z4E6JYWKZRI/action/author_attestation","sign_citation":"https://pith.science/pith/W2L63DPEZARJAS7Z4E6JYWKZRI/action/citation_signature","submit_replication":"https://pith.science/pith/W2L63DPEZARJAS7Z4E6JYWKZRI/action/replication_record"}},"created_at":"2026-07-05T12:02:00.386705+00:00","updated_at":"2026-07-05T12:02:00.386705+00:00"}