{"data":{"event":{"id":"a5b8afcb-6ac6-47e3-a00e-10e8cd03437b","slug":"soft-symbol-grounding-for-prototypical-concepts-b9bc79e41e","title":"Soft Symbol Grounding for Prototypical Concepts","short_summary":"arXiv:2609.12247v1 Announce Type: new \nAbstract: Neuro-symbolic models are usually trained with supervision only on final labels, leaving the intermediate concepts unobserved. Since many concept assignments are consistent with a given label, training can predict labels correctly while recovering the wrong concepts, a failure known as a reasoning shortcut. Prototypical networks reduce shortcuts by anchoring each concept to a few labeled examples, but existing methods still couple perception and reasoning through a hand-crafted, task-specific differentiable loss that must be redesigned for every","full_description":"arXiv:2609.12247v1 Announce Type: new \nAbstract: Neuro-symbolic models are usually trained with supervision only on final labels, leaving the intermediate concepts unobserved. Since many concept assignments are consistent with a given label, training can predict labels correctly while recovering the wrong concepts, a failure known as a reasoning shortcut. Prototypical networks reduce shortcuts by anchoring each concept to a few labeled examples, but existing methods still couple perception and reasoning through a hand-crafted, task-specific differentiable loss that must be redesigned for every task. We introduce \\textbf{Soft-PNet}, which removes this loss: it reframes concept grounding as a Metropolis walk over a precomputed cache of feasible symbolic solutions, guided by a prototype distribution built from a single labeled anchor per concept, and trains against one KL objective between the prototype-weighted cache and the network's concept predictions. The objective is identical across tasks and remains applicable when the solution space cannot be enumerated. On \\texttt{MNIST-EvenOdd}, Visual Sudoku, and \\texttt{Kand-Logic} under scarce supervision, Soft-PNet matches loss-engineered prototypical networks at the concept and label levels and recovers concepts that soft-grounding baselines miss, with no loss engineering and lower training time.","ledger_type":"benefit","primary_domain_id":"fc7d617f-c9df-4b9f-b595-4408915ea380","event_status":"provisional","event_date":"2026-09-14T00:00:00.000Z","discovery_date":"2026-09-14T00:00:00.000Z","first_published_date":"2026-09-14T00:00:00.000Z","last_reviewed_date":"2026-09-14T00:00:00.000Z","geographic_scope":"International","affected_population":null,"base_impact_tier":1,"base_score":"1.00","attribution_multiplier":"0.1000","evidence_multiplier":"0.1000","realization_multiplier":"0.2000","durability_multiplier":"0.5000","current_event_score":"0.001000","confidence_level":"low","score_explanation":"Auto-published from news ingest as a provisional placeholder. Score is conservative until a named release is identified and the record is rescored.","methodology_version_id":"d7881163-fb23-4e71-8625-bac1a8662c0f","original_methodology_version_id":"d7881163-fb23-4e71-8625-bac1a8662c0f","published_at":"2026-09-14T04:00:51.299Z","created_at":"2026-09-14T04:00:51.299Z","updated_at":"2026-09-14T04:00:51.299Z","flags":[],"domain_name":"Other","domain_slug":"other","methodology_version":"0.1"},"contributions":[{"id":"b6a4eb50-5c72-47dd-b3cb-4eb6544f423b","event_id":"a5b8afcb-6ac6-47e3-a00e-10e8cd03437b","model_id":"535014f7-c941-4d39-aa9b-8f9c1d3d07b7","role_description":"Unspecified system mentioned or implied by a news item. Remap to a named release when identified.","attribution_multiplier":"0.1000","credit_share":"1.0000","contribution_score":"0.001000","attribution_rationale":"News ingest does not infer a named model from the publisher alone. Attribution stays unspecified until a release is identified.","attribution_confidence":"medium","first_used_date":"2026-09-14T00:00:00.000Z","model_version_if_known":null,"review_status":"approved","created_at":"2026-09-14T04:00:51.308Z","model_slug":"unspecified-ai-system","model_name":"Unspecified AI system","identity_class":"unknown","is_internal":false,"family_name":"Unspecified","family_slug":"unknown-unspecified","organization_name":"Unknown","organization_slug":"unknown"}],"sources":[{"id":"fae2194e-546c-44c7-bdc5-2b5a25e9d505","event_id":"a5b8afcb-6ac6-47e3-a00e-10e8cd03437b","url":"https://arxiv.org/abs/2609.12247","canonical_url":"https://arxiv.org/abs/2609.12247","source_type":"preprint","publisher":"arXiv cs.AI","author":null,"publication_date":"2026-09-14T00:00:00.000Z","retrieved_at":"2026-09-14T04:00:51.315Z","title":"Soft Symbol Grounding for Prototypical Concepts","excerpt":"arXiv:2609.12247v1 Announce Type: new \nAbstract: Neuro-symbolic models are usually trained with supervision only on final labels, leaving the intermediate concepts unobserved. Since many concept assignments are consistent with a given label, training can predict labels correctly while recovering the wrong concepts, a failure known as a reasoning shortcut. Prototypical networks reduce shortcuts by anchoring each concept to a few labeled examples, but existing methods still couple perception and r","content_hash":null,"source_reliability_class":"medium","is_primary_source":true,"is_independent":true,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-14T04:00:51.315Z"}],"claims":[{"id":"a56b9ff3-9cff-4646-9c89-a1d942bd94fd","event_id":"a5b8afcb-6ac6-47e3-a00e-10e8cd03437b","claim_text":"Soft Symbol Grounding for Prototypical Concepts","claim_type":"outcome","claim_status":"supported","confidence_score":null,"created_at":"2026-09-14T04:00:51.321Z","updated_at":"2026-09-14T04:00:51.321Z"}],"revisions":[{"id":"3a9bf67f-5acb-422c-a3d9-8a29fc811c43","event_id":"a5b8afcb-6ac6-47e3-a00e-10e8cd03437b","model_id":null,"previous_score":"0.000000","new_score":"0.001000","previous_factors":{},"new_factors":{"evidence":0.1,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"change_reason":"Auto-published from news ingest.","trigger_type":"news_ingest","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-09-14T04:00:51.331Z"}],"secondary":[]},"methodology_version":"0.1"}