{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PY7FNUI5R5B6SVWGHWN7X3M7YC","short_pith_number":"pith:PY7FNUI5","schema_version":"1.0","canonical_sha256":"7e3e56d11d8f43e956c63d9bfbed9fc0a4b58c7c8e7fdd41a6035b46fbc00e19","source":{"kind":"arxiv","id":"2505.20106","version":1},"attestation_state":"computed","paper":{"title":"From Data to Modeling: Fully Open-vocabulary Scene Graph Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Wen Chen, Jinlin Wu, Zhen Lei, Zuyao Chen","submitted_at":"2025-05-26T15:11:23Z","abstract_excerpt":"We present OvSGTR, a novel transformer-based framework for fully open-vocabulary scene graph generation that overcomes the limitations of traditional closed-set models. Conventional methods restrict both object and relationship recognition to a fixed vocabulary, hindering their applicability to real-world scenarios where novel concepts frequently emerge. In contrast, our approach jointly predicts objects (nodes) and their inter-relationships (edges) beyond predefined categories. OvSGTR leverages a DETR-like architecture featuring a frozen image backbone and text encoder to extract high-quality"},"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":"2505.20106","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T15:11:23Z","cross_cats_sorted":[],"title_canon_sha256":"5552ee8a4d937a9ed1f6a09fa3107c73c93f4654bc7429adccf52b613a8ba1b5","abstract_canon_sha256":"0ee5833b777162eaed775989aec417c93b92ebb46cbde63bfcd776d9b0068538"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:52.765882Z","signature_b64":"VDRrhhhDODisyNoZmSc6T5GltA1bWfqSDMlWKAzg9HtV3qSe9W5gO8wtxAFwOIA7nBn9katf46oMfgv5Z/u2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e3e56d11d8f43e956c63d9bfbed9fc0a4b58c7c8e7fdd41a6035b46fbc00e19","last_reissued_at":"2026-07-05T11:09:52.765386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:52.765386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Data to Modeling: Fully Open-vocabulary Scene Graph Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Wen Chen, Jinlin Wu, Zhen Lei, Zuyao Chen","submitted_at":"2025-05-26T15:11:23Z","abstract_excerpt":"We present OvSGTR, a novel transformer-based framework for fully open-vocabulary scene graph generation that overcomes the limitations of traditional closed-set models. Conventional methods restrict both object and relationship recognition to a fixed vocabulary, hindering their applicability to real-world scenarios where novel concepts frequently emerge. In contrast, our approach jointly predicts objects (nodes) and their inter-relationships (edges) beyond predefined categories. OvSGTR leverages a DETR-like architecture featuring a frozen image backbone and text encoder to extract high-quality"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20106","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/2505.20106/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":"2505.20106","created_at":"2026-07-05T11:09:52.765446+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20106v1","created_at":"2026-07-05T11:09:52.765446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20106","created_at":"2026-07-05T11:09:52.765446+00:00"},{"alias_kind":"pith_short_12","alias_value":"PY7FNUI5R5B6","created_at":"2026-07-05T11:09:52.765446+00:00"},{"alias_kind":"pith_short_16","alias_value":"PY7FNUI5R5B6SVWG","created_at":"2026-07-05T11:09:52.765446+00:00"},{"alias_kind":"pith_short_8","alias_value":"PY7FNUI5","created_at":"2026-07-05T11:09:52.765446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09368","citing_title":"PhysScene: A Scene Graph Dataset for Scientific Visual Reasoning in Physics Experiments","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16932","citing_title":"MORN: Metacognitive Object-Goal Regulation for Resource-Rational Long-Horizon Navigation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PY7FNUI5R5B6SVWGHWN7X3M7YC","json":"https://pith.science/pith/PY7FNUI5R5B6SVWGHWN7X3M7YC.json","graph_json":"https://pith.science/api/pith-number/PY7FNUI5R5B6SVWGHWN7X3M7YC/graph.json","events_json":"https://pith.science/api/pith-number/PY7FNUI5R5B6SVWGHWN7X3M7YC/events.json","paper":"https://pith.science/paper/PY7FNUI5"},"agent_actions":{"view_html":"https://pith.science/pith/PY7FNUI5R5B6SVWGHWN7X3M7YC","download_json":"https://pith.science/pith/PY7FNUI5R5B6SVWGHWN7X3M7YC.json","view_paper":"https://pith.science/paper/PY7FNUI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20106&json=true","fetch_graph":"https://pith.science/api/pith-number/PY7FNUI5R5B6SVWGHWN7X3M7YC/graph.json","fetch_events":"https://pith.science/api/pith-number/PY7FNUI5R5B6SVWGHWN7X3M7YC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PY7FNUI5R5B6SVWGHWN7X3M7YC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PY7FNUI5R5B6SVWGHWN7X3M7YC/action/storage_attestation","attest_author":"https://pith.science/pith/PY7FNUI5R5B6SVWGHWN7X3M7YC/action/author_attestation","sign_citation":"https://pith.science/pith/PY7FNUI5R5B6SVWGHWN7X3M7YC/action/citation_signature","submit_replication":"https://pith.science/pith/PY7FNUI5R5B6SVWGHWN7X3M7YC/action/replication_record"}},"created_at":"2026-07-05T11:09:52.765446+00:00","updated_at":"2026-07-05T11:09:52.765446+00:00"}