{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:B4RVDFVV7OY33VSVLZMCTEYBS5","short_pith_number":"pith:B4RVDFVV","schema_version":"1.0","canonical_sha256":"0f235196b5fbb1bdd6555e58299301976d90bb850f3ecbbd8984c00e35b95d07","source":{"kind":"arxiv","id":"2308.16534","version":3},"attestation_state":"computed","paper":{"title":"Zero-Shot Conditioning of Score-Based Diffusion Models by Neuro-Symbolic Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Davide Scassola, Ginevra Carbone, Luca Bortolussi, Sebastiano Saccani","submitted_at":"2023-08-31T08:25:47Z","abstract_excerpt":"Score-based diffusion models have emerged as effective approaches for both conditional and unconditional generation. Still conditional generation is based on either a specific training of a conditional model or classifier guidance, which requires training a noise-dependent classifier, even when a classifier for uncorrupted data is given. We propose a method that, given a pre-trained unconditional score-based generative model, samples from the conditional distribution under arbitrary logical constraints, without requiring additional training. Differently from other zero-shot techniques, that ra"},"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":"2308.16534","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-31T08:25:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1068f8c02b97d128aa9cfc2778a90da12c5c8b3436e76011f04b573ca6ba423c","abstract_canon_sha256":"57a0f3a35dd09ef50af0728741187588c93822b0e4d7a1a1cf43c81bd7bde8e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:39.080129Z","signature_b64":"DP7vXMNLt+/arz2/i7NpgaGSEkHiUKCGnlRRkfnDyveSPrE8rygrvSJMlnxtzovWVplrdy2qYUFbpvTdrX4YBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f235196b5fbb1bdd6555e58299301976d90bb850f3ecbbd8984c00e35b95d07","last_reissued_at":"2026-07-05T09:53:39.079700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:39.079700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Conditioning of Score-Based Diffusion Models by Neuro-Symbolic Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Davide Scassola, Ginevra Carbone, Luca Bortolussi, Sebastiano Saccani","submitted_at":"2023-08-31T08:25:47Z","abstract_excerpt":"Score-based diffusion models have emerged as effective approaches for both conditional and unconditional generation. Still conditional generation is based on either a specific training of a conditional model or classifier guidance, which requires training a noise-dependent classifier, even when a classifier for uncorrupted data is given. We propose a method that, given a pre-trained unconditional score-based generative model, samples from the conditional distribution under arbitrary logical constraints, without requiring additional training. Differently from other zero-shot techniques, that ra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16534","kind":"arxiv","version":3},"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/2308.16534/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":"2308.16534","created_at":"2026-07-05T09:53:39.079749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.16534v3","created_at":"2026-07-05T09:53:39.079749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16534","created_at":"2026-07-05T09:53:39.079749+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4RVDFVV7OY3","created_at":"2026-07-05T09:53:39.079749+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4RVDFVV7OY33VSV","created_at":"2026-07-05T09:53:39.079749+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4RVDFVV","created_at":"2026-07-05T09:53:39.079749+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01338","citing_title":"Conformal Predictive Monitoring for Multi-Modal Scenarios","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4RVDFVV7OY33VSVLZMCTEYBS5","json":"https://pith.science/pith/B4RVDFVV7OY33VSVLZMCTEYBS5.json","graph_json":"https://pith.science/api/pith-number/B4RVDFVV7OY33VSVLZMCTEYBS5/graph.json","events_json":"https://pith.science/api/pith-number/B4RVDFVV7OY33VSVLZMCTEYBS5/events.json","paper":"https://pith.science/paper/B4RVDFVV"},"agent_actions":{"view_html":"https://pith.science/pith/B4RVDFVV7OY33VSVLZMCTEYBS5","download_json":"https://pith.science/pith/B4RVDFVV7OY33VSVLZMCTEYBS5.json","view_paper":"https://pith.science/paper/B4RVDFVV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.16534&json=true","fetch_graph":"https://pith.science/api/pith-number/B4RVDFVV7OY33VSVLZMCTEYBS5/graph.json","fetch_events":"https://pith.science/api/pith-number/B4RVDFVV7OY33VSVLZMCTEYBS5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4RVDFVV7OY33VSVLZMCTEYBS5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4RVDFVV7OY33VSVLZMCTEYBS5/action/storage_attestation","attest_author":"https://pith.science/pith/B4RVDFVV7OY33VSVLZMCTEYBS5/action/author_attestation","sign_citation":"https://pith.science/pith/B4RVDFVV7OY33VSVLZMCTEYBS5/action/citation_signature","submit_replication":"https://pith.science/pith/B4RVDFVV7OY33VSVLZMCTEYBS5/action/replication_record"}},"created_at":"2026-07-05T09:53:39.079749+00:00","updated_at":"2026-07-05T09:53:39.079749+00:00"}