{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EK73MLMY3V2WEYIEZIGL2JNXPO","short_pith_number":"pith:EK73MLMY","schema_version":"1.0","canonical_sha256":"22bfb62d98dd75626104ca0cbd25b77b972064a97d18440dcde33a114b327eda","source":{"kind":"arxiv","id":"2403.10187","version":1},"attestation_state":"computed","paper":{"title":"Grasp Anything: Combining Teacher-Augmented Policy Gradient Learning with Instance Segmentation to Grasp Arbitrary Objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Malte Mosbach, Sven Behnke","submitted_at":"2024-03-15T10:48:16Z","abstract_excerpt":"Interactive grasping from clutter, akin to human dexterity, is one of the longest-standing problems in robot learning. Challenges stem from the intricacies of visual perception, the demand for precise motor skills, and the complex interplay between the two. In this work, we present Teacher-Augmented Policy Gradient (TAPG), a novel two-stage learning framework that synergizes reinforcement learning and policy distillation. After training a teacher policy to master the motor control based on object pose information, TAPG facilitates guided, yet adaptive, learning of a sensorimotor policy, based "},"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":"2403.10187","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-03-15T10:48:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c6de69a61cd31c508491edf8c5e4a67baf00032ef77abd7b7880486cccb05d6c","abstract_canon_sha256":"6bc09f5b4fe5c0595b2cf39e390b2d349a49e7819d3cb72d49861c2e06838afb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:31.390200Z","signature_b64":"iXJ+xj4PY6ezIlkAwyBD7vkABNf43FxS/lkSFzbSno8r1FSAPydt0Cj0V6HZ3Sv2MenZtf0npvWqad22HUVcAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22bfb62d98dd75626104ca0cbd25b77b972064a97d18440dcde33a114b327eda","last_reissued_at":"2026-07-05T07:56:31.389838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:31.389838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grasp Anything: Combining Teacher-Augmented Policy Gradient Learning with Instance Segmentation to Grasp Arbitrary Objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Malte Mosbach, Sven Behnke","submitted_at":"2024-03-15T10:48:16Z","abstract_excerpt":"Interactive grasping from clutter, akin to human dexterity, is one of the longest-standing problems in robot learning. Challenges stem from the intricacies of visual perception, the demand for precise motor skills, and the complex interplay between the two. In this work, we present Teacher-Augmented Policy Gradient (TAPG), a novel two-stage learning framework that synergizes reinforcement learning and policy distillation. After training a teacher policy to master the motor control based on object pose information, TAPG facilitates guided, yet adaptive, learning of a sensorimotor policy, based "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10187","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/2403.10187/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":"2403.10187","created_at":"2026-07-05T07:56:31.389895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10187v1","created_at":"2026-07-05T07:56:31.389895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10187","created_at":"2026-07-05T07:56:31.389895+00:00"},{"alias_kind":"pith_short_12","alias_value":"EK73MLMY3V2W","created_at":"2026-07-05T07:56:31.389895+00:00"},{"alias_kind":"pith_short_16","alias_value":"EK73MLMY3V2WEYIE","created_at":"2026-07-05T07:56:31.389895+00:00"},{"alias_kind":"pith_short_8","alias_value":"EK73MLMY","created_at":"2026-07-05T07:56:31.389895+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/EK73MLMY3V2WEYIEZIGL2JNXPO","json":"https://pith.science/pith/EK73MLMY3V2WEYIEZIGL2JNXPO.json","graph_json":"https://pith.science/api/pith-number/EK73MLMY3V2WEYIEZIGL2JNXPO/graph.json","events_json":"https://pith.science/api/pith-number/EK73MLMY3V2WEYIEZIGL2JNXPO/events.json","paper":"https://pith.science/paper/EK73MLMY"},"agent_actions":{"view_html":"https://pith.science/pith/EK73MLMY3V2WEYIEZIGL2JNXPO","download_json":"https://pith.science/pith/EK73MLMY3V2WEYIEZIGL2JNXPO.json","view_paper":"https://pith.science/paper/EK73MLMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10187&json=true","fetch_graph":"https://pith.science/api/pith-number/EK73MLMY3V2WEYIEZIGL2JNXPO/graph.json","fetch_events":"https://pith.science/api/pith-number/EK73MLMY3V2WEYIEZIGL2JNXPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EK73MLMY3V2WEYIEZIGL2JNXPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EK73MLMY3V2WEYIEZIGL2JNXPO/action/storage_attestation","attest_author":"https://pith.science/pith/EK73MLMY3V2WEYIEZIGL2JNXPO/action/author_attestation","sign_citation":"https://pith.science/pith/EK73MLMY3V2WEYIEZIGL2JNXPO/action/citation_signature","submit_replication":"https://pith.science/pith/EK73MLMY3V2WEYIEZIGL2JNXPO/action/replication_record"}},"created_at":"2026-07-05T07:56:31.389895+00:00","updated_at":"2026-07-05T07:56:31.389895+00:00"}