{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HVOFJOAYYRY5CERMZ64ZYCQRIU","short_pith_number":"pith:HVOFJOAY","schema_version":"1.0","canonical_sha256":"3d5c54b818c471d1122ccfb99c0a11451139ce1c8f717329f09eeaf8c09b9ee3","source":{"kind":"arxiv","id":"2506.16129","version":2},"attestation_state":"computed","paper":{"title":"Neurosymbolic Object-Centric Learning with Distant Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Debot, Giuseppe Marra, Stefano Colamonaco","submitted_at":"2025-06-19T08:26:42Z","abstract_excerpt":"Neurosymbolic learning can use symbolic rules to provide supervision for latent concepts from weak labels, but it commonly assumes that the entities referenced by these rules are already specified. Object-centric models decompose images into slot-like representations; however, such slots are not necessarily aligned with the predicates required for symbolic reasoning. We investigate object-centric neurosymbolic learning under distant supervision, where the object-level arguments of a logic program are learned directly from images using only global task labels. We introduce DeepObjectLog, a prob"},"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":"2506.16129","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-19T08:26:42Z","cross_cats_sorted":[],"title_canon_sha256":"0efb6bde50ffcbcf6fddc7f793c1976c797e1a2983219804b61f4d585cc57278","abstract_canon_sha256":"3fbb9ff06b8b1f1e5fd49e2f38d522838c941178d6bd0779018614739f242e1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:34.504599Z","signature_b64":"D/H5gRDXpYmnc+xsO4jGxauD/XzNOTgVL+dYbZ+Mml4SdFqIVZyU7lzImjZEH5sWWGdAypMeU9f1yQhn894RDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d5c54b818c471d1122ccfb99c0a11451139ce1c8f717329f09eeaf8c09b9ee3","last_reissued_at":"2026-05-20T00:01:34.503818Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:34.503818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neurosymbolic Object-Centric Learning with Distant Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Debot, Giuseppe Marra, Stefano Colamonaco","submitted_at":"2025-06-19T08:26:42Z","abstract_excerpt":"Neurosymbolic learning can use symbolic rules to provide supervision for latent concepts from weak labels, but it commonly assumes that the entities referenced by these rules are already specified. Object-centric models decompose images into slot-like representations; however, such slots are not necessarily aligned with the predicates required for symbolic reasoning. We investigate object-centric neurosymbolic learning under distant supervision, where the object-level arguments of a logic program are learned directly from images using only global task labels. We introduce DeepObjectLog, a prob"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16129","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/2506.16129/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":"2506.16129","created_at":"2026-05-20T00:01:34.503944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.16129v2","created_at":"2026-05-20T00:01:34.503944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16129","created_at":"2026-05-20T00:01:34.503944+00:00"},{"alias_kind":"pith_short_12","alias_value":"HVOFJOAYYRY5","created_at":"2026-05-20T00:01:34.503944+00:00"},{"alias_kind":"pith_short_16","alias_value":"HVOFJOAYYRY5CERM","created_at":"2026-05-20T00:01:34.503944+00:00"},{"alias_kind":"pith_short_8","alias_value":"HVOFJOAY","created_at":"2026-05-20T00:01:34.503944+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2604.16076","citing_title":"Prototype-Grounded Concept Models for Verifiable Concept Alignment","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13674","citing_title":"Weakly Supervised Segmentation as Semantic-Based Regularization","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16076","citing_title":"Prototype-Grounded Concept Models for Verifiable Concept Alignment","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HVOFJOAYYRY5CERMZ64ZYCQRIU","json":"https://pith.science/pith/HVOFJOAYYRY5CERMZ64ZYCQRIU.json","graph_json":"https://pith.science/api/pith-number/HVOFJOAYYRY5CERMZ64ZYCQRIU/graph.json","events_json":"https://pith.science/api/pith-number/HVOFJOAYYRY5CERMZ64ZYCQRIU/events.json","paper":"https://pith.science/paper/HVOFJOAY"},"agent_actions":{"view_html":"https://pith.science/pith/HVOFJOAYYRY5CERMZ64ZYCQRIU","download_json":"https://pith.science/pith/HVOFJOAYYRY5CERMZ64ZYCQRIU.json","view_paper":"https://pith.science/paper/HVOFJOAY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.16129&json=true","fetch_graph":"https://pith.science/api/pith-number/HVOFJOAYYRY5CERMZ64ZYCQRIU/graph.json","fetch_events":"https://pith.science/api/pith-number/HVOFJOAYYRY5CERMZ64ZYCQRIU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HVOFJOAYYRY5CERMZ64ZYCQRIU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HVOFJOAYYRY5CERMZ64ZYCQRIU/action/storage_attestation","attest_author":"https://pith.science/pith/HVOFJOAYYRY5CERMZ64ZYCQRIU/action/author_attestation","sign_citation":"https://pith.science/pith/HVOFJOAYYRY5CERMZ64ZYCQRIU/action/citation_signature","submit_replication":"https://pith.science/pith/HVOFJOAYYRY5CERMZ64ZYCQRIU/action/replication_record"}},"created_at":"2026-05-20T00:01:34.503944+00:00","updated_at":"2026-05-20T00:01:34.503944+00:00"}