{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YLXT4MISYLYEYQ7LGGGZEBZUE3","short_pith_number":"pith:YLXT4MIS","schema_version":"1.0","canonical_sha256":"c2ef3e3112c2f04c43eb318d92073426d7292d6c90690848dd77a913cd824f99","source":{"kind":"arxiv","id":"2607.02846","version":1},"attestation_state":"computed","paper":{"title":"Object-Centric Environment Modeling for Agentic Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Tianyi Ma, Yanfang Ye, Yijun Ma, Yiyang Li, Zehong Wang","submitted_at":"2026-07-03T00:49:45Z","abstract_excerpt":"Large language model (LLM) agents can improve through accumulated experience, but free-form textual memories become difficult to maintain, validate, and reuse as interactions grow. Recent symbolic approaches learn executable skills or programmatic world models, yet often store local procedures or assume simplified dynamics. We propose Object-Centric Environment Modeling (OCM), which organizes experience into an executable object-centric environment model. OCM maintains two connected code bases: object knowledge, which defines environment entities and mechanisms as Python classes, and procedure"},"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":"2607.02846","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-03T00:49:45Z","cross_cats_sorted":[],"title_canon_sha256":"b6ba1d6bed49ad8efc3497b0fda2b3bae9fa639f9ab69fc8c82f405632d6be9e","abstract_canon_sha256":"12dbde6acc29e11319e6867a3afc6f964241daa9fd314fe3d96b4e16dcd43307"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T00:16:20.459248Z","signature_b64":"U95Gx6v/e9aRJUMQAXTLJJu4v06l9W+wJUen0eENbBWAym2BiKpUWSE10ZM3w2MsTRxb+ADemVoe1tX3Ua4IAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2ef3e3112c2f04c43eb318d92073426d7292d6c90690848dd77a913cd824f99","last_reissued_at":"2026-07-07T00:16:20.458576Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T00:16:20.458576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Object-Centric Environment Modeling for Agentic Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Tianyi Ma, Yanfang Ye, Yijun Ma, Yiyang Li, Zehong Wang","submitted_at":"2026-07-03T00:49:45Z","abstract_excerpt":"Large language model (LLM) agents can improve through accumulated experience, but free-form textual memories become difficult to maintain, validate, and reuse as interactions grow. Recent symbolic approaches learn executable skills or programmatic world models, yet often store local procedures or assume simplified dynamics. We propose Object-Centric Environment Modeling (OCM), which organizes experience into an executable object-centric environment model. OCM maintains two connected code bases: object knowledge, which defines environment entities and mechanisms as Python classes, and procedure"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02846","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/2607.02846/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":"2607.02846","created_at":"2026-07-07T00:16:20.458686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02846v1","created_at":"2026-07-07T00:16:20.458686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02846","created_at":"2026-07-07T00:16:20.458686+00:00"},{"alias_kind":"pith_short_12","alias_value":"YLXT4MISYLYE","created_at":"2026-07-07T00:16:20.458686+00:00"},{"alias_kind":"pith_short_16","alias_value":"YLXT4MISYLYEYQ7L","created_at":"2026-07-07T00:16:20.458686+00:00"},{"alias_kind":"pith_short_8","alias_value":"YLXT4MIS","created_at":"2026-07-07T00:16:20.458686+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YLXT4MISYLYEYQ7LGGGZEBZUE3","json":"https://pith.science/pith/YLXT4MISYLYEYQ7LGGGZEBZUE3.json","graph_json":"https://pith.science/api/pith-number/YLXT4MISYLYEYQ7LGGGZEBZUE3/graph.json","events_json":"https://pith.science/api/pith-number/YLXT4MISYLYEYQ7LGGGZEBZUE3/events.json","paper":"https://pith.science/paper/YLXT4MIS"},"agent_actions":{"view_html":"https://pith.science/pith/YLXT4MISYLYEYQ7LGGGZEBZUE3","download_json":"https://pith.science/pith/YLXT4MISYLYEYQ7LGGGZEBZUE3.json","view_paper":"https://pith.science/paper/YLXT4MIS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02846&json=true","fetch_graph":"https://pith.science/api/pith-number/YLXT4MISYLYEYQ7LGGGZEBZUE3/graph.json","fetch_events":"https://pith.science/api/pith-number/YLXT4MISYLYEYQ7LGGGZEBZUE3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YLXT4MISYLYEYQ7LGGGZEBZUE3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YLXT4MISYLYEYQ7LGGGZEBZUE3/action/storage_attestation","attest_author":"https://pith.science/pith/YLXT4MISYLYEYQ7LGGGZEBZUE3/action/author_attestation","sign_citation":"https://pith.science/pith/YLXT4MISYLYEYQ7LGGGZEBZUE3/action/citation_signature","submit_replication":"https://pith.science/pith/YLXT4MISYLYEYQ7LGGGZEBZUE3/action/replication_record"}},"created_at":"2026-07-07T00:16:20.458686+00:00","updated_at":"2026-07-07T00:16:20.458686+00:00"}