{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GDTMGQ3LH3U7OEF7SI3UTBLJ6P","short_pith_number":"pith:GDTMGQ3L","schema_version":"1.0","canonical_sha256":"30e6c3436b3ee9f710bf9237498569f3ee724fd11cb462dfc1878595f128192e","source":{"kind":"arxiv","id":"2606.06904","version":1},"attestation_state":"computed","paper":{"title":"ActionMap: Robot Policy Learning via Voxel Action Heatmap","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Hai Ci, Han Cai, Mike Zheng Shou, Pei Yang, Qi Lv, Yanzhe Chen","submitted_at":"2026-06-05T04:42:56Z","abstract_excerpt":"Vision-language-action (VLA) models have advanced rapidly across backbones, training recipes, and data scale, yet the action decoder, which converts the backbone's hidden state into a continuous control signal, has barely changed and remains a single-point predictor across the majority of current VLAs. Whether implemented via autoregressive token bins, L1 regression, or flow-matching denoising, the resulting decoder treats the action space as unstructured, leaving the geometric proximity of neighboring actions unexploited during training. To advance this, we introduce ActionMap, a voxel heatma"},"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":"2606.06904","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-05T04:42:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d9d1261230449eeabd8dfac36e95c8310aa2df9c3dd02f81be26d2f5579a0b84","abstract_canon_sha256":"dddfae9cc744e14ff370dfaf495542b78de134b6553c195f7cdfa721333871fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:34.945478Z","signature_b64":"wS1gpq9wWtYR8KRYNdYkz9jJuX3Sld+6Js+pVVYwMUVePOEnqOtZ7lc9mRRZAgADHsr2BgL8I7xaMHOT3/slAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30e6c3436b3ee9f710bf9237498569f3ee724fd11cb462dfc1878595f128192e","last_reissued_at":"2026-06-08T01:04:34.944601Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:34.944601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ActionMap: Robot Policy Learning via Voxel Action Heatmap","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Hai Ci, Han Cai, Mike Zheng Shou, Pei Yang, Qi Lv, Yanzhe Chen","submitted_at":"2026-06-05T04:42:56Z","abstract_excerpt":"Vision-language-action (VLA) models have advanced rapidly across backbones, training recipes, and data scale, yet the action decoder, which converts the backbone's hidden state into a continuous control signal, has barely changed and remains a single-point predictor across the majority of current VLAs. Whether implemented via autoregressive token bins, L1 regression, or flow-matching denoising, the resulting decoder treats the action space as unstructured, leaving the geometric proximity of neighboring actions unexploited during training. To advance this, we introduce ActionMap, a voxel heatma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06904","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/2606.06904/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":"2606.06904","created_at":"2026-06-08T01:04:34.944749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06904v1","created_at":"2026-06-08T01:04:34.944749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06904","created_at":"2026-06-08T01:04:34.944749+00:00"},{"alias_kind":"pith_short_12","alias_value":"GDTMGQ3LH3U7","created_at":"2026-06-08T01:04:34.944749+00:00"},{"alias_kind":"pith_short_16","alias_value":"GDTMGQ3LH3U7OEF7","created_at":"2026-06-08T01:04:34.944749+00:00"},{"alias_kind":"pith_short_8","alias_value":"GDTMGQ3L","created_at":"2026-06-08T01:04:34.944749+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/GDTMGQ3LH3U7OEF7SI3UTBLJ6P","json":"https://pith.science/pith/GDTMGQ3LH3U7OEF7SI3UTBLJ6P.json","graph_json":"https://pith.science/api/pith-number/GDTMGQ3LH3U7OEF7SI3UTBLJ6P/graph.json","events_json":"https://pith.science/api/pith-number/GDTMGQ3LH3U7OEF7SI3UTBLJ6P/events.json","paper":"https://pith.science/paper/GDTMGQ3L"},"agent_actions":{"view_html":"https://pith.science/pith/GDTMGQ3LH3U7OEF7SI3UTBLJ6P","download_json":"https://pith.science/pith/GDTMGQ3LH3U7OEF7SI3UTBLJ6P.json","view_paper":"https://pith.science/paper/GDTMGQ3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06904&json=true","fetch_graph":"https://pith.science/api/pith-number/GDTMGQ3LH3U7OEF7SI3UTBLJ6P/graph.json","fetch_events":"https://pith.science/api/pith-number/GDTMGQ3LH3U7OEF7SI3UTBLJ6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GDTMGQ3LH3U7OEF7SI3UTBLJ6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GDTMGQ3LH3U7OEF7SI3UTBLJ6P/action/storage_attestation","attest_author":"https://pith.science/pith/GDTMGQ3LH3U7OEF7SI3UTBLJ6P/action/author_attestation","sign_citation":"https://pith.science/pith/GDTMGQ3LH3U7OEF7SI3UTBLJ6P/action/citation_signature","submit_replication":"https://pith.science/pith/GDTMGQ3LH3U7OEF7SI3UTBLJ6P/action/replication_record"}},"created_at":"2026-06-08T01:04:34.944749+00:00","updated_at":"2026-06-08T01:04:34.944749+00:00"}