{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IB5D3HQ7XL64HGQ4G4FD6A3TUW","short_pith_number":"pith:IB5D3HQ7","schema_version":"1.0","canonical_sha256":"407a3d9e1fbafdc39a1c370a3f0373a581bf094979bb8b8deb0e5f44ca2913ca","source":{"kind":"arxiv","id":"2509.23212","version":2},"attestation_state":"computed","paper":{"title":"Replication and Information Extraction in a Minimal Agent-Environment Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","nlin.AO"],"primary_cat":"cond-mat.dis-nn","authors_text":"Davide Straziota, Jerome Garnier-Brun, Luca Saglietti, Sebastiano Ariosto","submitted_at":"2025-09-27T09:49:11Z","abstract_excerpt":"How can information be extracted from data without explicit guidance or rewards? We investigate this question in a minimal setting where a classifying agent is exposed to a stream of structured data produced by a generative environment, and evolves by seeking consistency of its own labels in time. We find that imposing a simplicity bias on the classification rule can drive the dynamics toward label-coherent steady states, which we coin functional replicators. Remarkably, these persistent labeling rules align with the latent structure of the data. Using analytical tools from statistical mechani"},"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":"2509.23212","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2025-09-27T09:49:11Z","cross_cats_sorted":["cond-mat.stat-mech","nlin.AO"],"title_canon_sha256":"36da4ed72eeaf47dbadf9e2d5602d62c6e1b12bfb8fa454dcf1fe0f251baf703","abstract_canon_sha256":"9a63c0731b6526cc1b54530886ff2ce1e93ba8e96bbad9838c3ece28f2920172"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:18:20.503058Z","signature_b64":"UZ+xa6ya3kAOVopH3MR5nmMacZN0M9hP+nJRMQV5TwGWvEMwvmEw5KALqwjlrMj9kvD82I2HExcTbjsVeulNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"407a3d9e1fbafdc39a1c370a3f0373a581bf094979bb8b8deb0e5f44ca2913ca","last_reissued_at":"2026-07-08T01:18:20.502517Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:18:20.502517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Replication and Information Extraction in a Minimal Agent-Environment Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","nlin.AO"],"primary_cat":"cond-mat.dis-nn","authors_text":"Davide Straziota, Jerome Garnier-Brun, Luca Saglietti, Sebastiano Ariosto","submitted_at":"2025-09-27T09:49:11Z","abstract_excerpt":"How can information be extracted from data without explicit guidance or rewards? We investigate this question in a minimal setting where a classifying agent is exposed to a stream of structured data produced by a generative environment, and evolves by seeking consistency of its own labels in time. We find that imposing a simplicity bias on the classification rule can drive the dynamics toward label-coherent steady states, which we coin functional replicators. Remarkably, these persistent labeling rules align with the latent structure of the data. Using analytical tools from statistical mechani"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.23212","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/2509.23212/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":"2509.23212","created_at":"2026-07-08T01:18:20.502581+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.23212v2","created_at":"2026-07-08T01:18:20.502581+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.23212","created_at":"2026-07-08T01:18:20.502581+00:00"},{"alias_kind":"pith_short_12","alias_value":"IB5D3HQ7XL64","created_at":"2026-07-08T01:18:20.502581+00:00"},{"alias_kind":"pith_short_16","alias_value":"IB5D3HQ7XL64HGQ4","created_at":"2026-07-08T01:18:20.502581+00:00"},{"alias_kind":"pith_short_8","alias_value":"IB5D3HQ7","created_at":"2026-07-08T01:18:20.502581+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.02171","citing_title":"Theory of collective learning in populations of adaptive agents","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IB5D3HQ7XL64HGQ4G4FD6A3TUW","json":"https://pith.science/pith/IB5D3HQ7XL64HGQ4G4FD6A3TUW.json","graph_json":"https://pith.science/api/pith-number/IB5D3HQ7XL64HGQ4G4FD6A3TUW/graph.json","events_json":"https://pith.science/api/pith-number/IB5D3HQ7XL64HGQ4G4FD6A3TUW/events.json","paper":"https://pith.science/paper/IB5D3HQ7"},"agent_actions":{"view_html":"https://pith.science/pith/IB5D3HQ7XL64HGQ4G4FD6A3TUW","download_json":"https://pith.science/pith/IB5D3HQ7XL64HGQ4G4FD6A3TUW.json","view_paper":"https://pith.science/paper/IB5D3HQ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.23212&json=true","fetch_graph":"https://pith.science/api/pith-number/IB5D3HQ7XL64HGQ4G4FD6A3TUW/graph.json","fetch_events":"https://pith.science/api/pith-number/IB5D3HQ7XL64HGQ4G4FD6A3TUW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IB5D3HQ7XL64HGQ4G4FD6A3TUW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IB5D3HQ7XL64HGQ4G4FD6A3TUW/action/storage_attestation","attest_author":"https://pith.science/pith/IB5D3HQ7XL64HGQ4G4FD6A3TUW/action/author_attestation","sign_citation":"https://pith.science/pith/IB5D3HQ7XL64HGQ4G4FD6A3TUW/action/citation_signature","submit_replication":"https://pith.science/pith/IB5D3HQ7XL64HGQ4G4FD6A3TUW/action/replication_record"}},"created_at":"2026-07-08T01:18:20.502581+00:00","updated_at":"2026-07-08T01:18:20.502581+00:00"}