{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XUGK5RKLXVPEKJVALXB3BE2Z6C","short_pith_number":"pith:XUGK5RKL","schema_version":"1.0","canonical_sha256":"bd0caec54bbd5e4526a05dc3b09359f08a7c96bf896b19f02a3459343d2e604a","source":{"kind":"arxiv","id":"2507.10566","version":1},"attestation_state":"computed","paper":{"title":"AI Mother Tongue: Self-Emergent Communication in MARL via Endogenous Symbol Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.LG","cs.MA","cs.NE"],"primary_cat":"cs.AI","authors_text":"Hung Ming Liu","submitted_at":"2025-07-07T09:52:49Z","abstract_excerpt":"In Decentralized Multi-Agent Reinforcement Learning (MARL), the development of Emergent Communication has long been constrained by the ``Joint Exploration Dilemma'', leading agents to fall into a ``Communication Vacuum Equilibrium'' . Traditional methods address this by introducing inductive biases to facilitate communication emergence . This study fundamentally questions whether such artificial inductive biases are, in fact, over-engineering. Through experiments with the ``AI Mother Tongue'' (AIM) framework, based on a Vector Quantized Variational Autoencoder (VQ-VAE), we demonstrate that whe"},"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":"2507.10566","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-07T09:52:49Z","cross_cats_sorted":["cs.GT","cs.LG","cs.MA","cs.NE"],"title_canon_sha256":"b5f443e92d2da691c2861ca85ad635316319e2cea500eda8d0c5b6c9e733daf2","abstract_canon_sha256":"9e6f9d1c6f193aa206ebb30d0272a6669d4ef3dd47629f3cec637aa6a6f27f42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:56.720269Z","signature_b64":"GOIpMNjLdOrbCaDhSagbJpkb10zDo7vNGIqHfFgHRNyLzkmw4bEVDes23mXvvrGK/Ytp0Vy3M/34h5/X7HpTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd0caec54bbd5e4526a05dc3b09359f08a7c96bf896b19f02a3459343d2e604a","last_reissued_at":"2026-07-05T11:36:56.719582Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:56.719582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI Mother Tongue: Self-Emergent Communication in MARL via Endogenous Symbol Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.LG","cs.MA","cs.NE"],"primary_cat":"cs.AI","authors_text":"Hung Ming Liu","submitted_at":"2025-07-07T09:52:49Z","abstract_excerpt":"In Decentralized Multi-Agent Reinforcement Learning (MARL), the development of Emergent Communication has long been constrained by the ``Joint Exploration Dilemma'', leading agents to fall into a ``Communication Vacuum Equilibrium'' . Traditional methods address this by introducing inductive biases to facilitate communication emergence . This study fundamentally questions whether such artificial inductive biases are, in fact, over-engineering. Through experiments with the ``AI Mother Tongue'' (AIM) framework, based on a Vector Quantized Variational Autoencoder (VQ-VAE), we demonstrate that whe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10566","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/2507.10566/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":"2507.10566","created_at":"2026-07-05T11:36:56.719674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.10566v1","created_at":"2026-07-05T11:36:56.719674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10566","created_at":"2026-07-05T11:36:56.719674+00:00"},{"alias_kind":"pith_short_12","alias_value":"XUGK5RKLXVPE","created_at":"2026-07-05T11:36:56.719674+00:00"},{"alias_kind":"pith_short_16","alias_value":"XUGK5RKLXVPEKJVA","created_at":"2026-07-05T11:36:56.719674+00:00"},{"alias_kind":"pith_short_8","alias_value":"XUGK5RKL","created_at":"2026-07-05T11:36:56.719674+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23075","citing_title":"Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XUGK5RKLXVPEKJVALXB3BE2Z6C","json":"https://pith.science/pith/XUGK5RKLXVPEKJVALXB3BE2Z6C.json","graph_json":"https://pith.science/api/pith-number/XUGK5RKLXVPEKJVALXB3BE2Z6C/graph.json","events_json":"https://pith.science/api/pith-number/XUGK5RKLXVPEKJVALXB3BE2Z6C/events.json","paper":"https://pith.science/paper/XUGK5RKL"},"agent_actions":{"view_html":"https://pith.science/pith/XUGK5RKLXVPEKJVALXB3BE2Z6C","download_json":"https://pith.science/pith/XUGK5RKLXVPEKJVALXB3BE2Z6C.json","view_paper":"https://pith.science/paper/XUGK5RKL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.10566&json=true","fetch_graph":"https://pith.science/api/pith-number/XUGK5RKLXVPEKJVALXB3BE2Z6C/graph.json","fetch_events":"https://pith.science/api/pith-number/XUGK5RKLXVPEKJVALXB3BE2Z6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XUGK5RKLXVPEKJVALXB3BE2Z6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XUGK5RKLXVPEKJVALXB3BE2Z6C/action/storage_attestation","attest_author":"https://pith.science/pith/XUGK5RKLXVPEKJVALXB3BE2Z6C/action/author_attestation","sign_citation":"https://pith.science/pith/XUGK5RKLXVPEKJVALXB3BE2Z6C/action/citation_signature","submit_replication":"https://pith.science/pith/XUGK5RKLXVPEKJVALXB3BE2Z6C/action/replication_record"}},"created_at":"2026-07-05T11:36:56.719674+00:00","updated_at":"2026-07-05T11:36:56.719674+00:00"}