{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WHKDVF3UCOPVRLS5HYTBR4QZL7","short_pith_number":"pith:WHKDVF3U","schema_version":"1.0","canonical_sha256":"b1d43a9774139f58ae5d3e2618f2195fcdbea2b1cfdb096b688cb9fa3165d2e2","source":{"kind":"arxiv","id":"2607.29600","version":1},"attestation_state":"computed","paper":{"title":"HAM-VLN: Harnessing Hierarchical Agentic Memory for Zero-Shot Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"An Liu, Bingxi Liu, Cong Leng, Fulin Tang, Hongyu Ding, Hong Zhang, Jian Cheng, Yaran Chen, Yixuan Jiang","submitted_at":"2026-07-31T16:32:38Z","abstract_excerpt":"Vision-and-language navigation (VLN) enables robots to follow instructions in previously unseen environments. Recently, a training-free paradigm has emerged: the robot queries a multimodal LLM to understand its observations and plan the next action. However, long-horizon navigation based on either image streams or dense map inevitably introduces a growing memory and reasoning bottleneck. We present HAM-VLN, a decision-coupled, agent-authored memory that equips the robot with a persistent, depth-grounded world graph. In the same model call used to select the next action, HAM-VLN also records se"},"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":"2607.29600","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-31T16:32:38Z","cross_cats_sorted":[],"title_canon_sha256":"5df2862bffa416505e4e31b1d0ab79352524abc3328c0514c132ce027381b4d2","abstract_canon_sha256":"08940775d7b47945598a5246fe1790b30a873c6fe631a4d2ce6f5d6298d09c37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:40:05.401913Z","signature_b64":"kC7iyP+mzoi3JLczkmwBdylw71X7FdcChWaWe/AzccgS1/NZ95l6zOWBmvViFIogcNP4HIMZRo7Z8JBgL0K+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1d43a9774139f58ae5d3e2618f2195fcdbea2b1cfdb096b688cb9fa3165d2e2","last_reissued_at":"2026-08-03T01:40:05.400361Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:40:05.400361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HAM-VLN: Harnessing Hierarchical Agentic Memory for Zero-Shot Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"An Liu, Bingxi Liu, Cong Leng, Fulin Tang, Hongyu Ding, Hong Zhang, Jian Cheng, Yaran Chen, Yixuan Jiang","submitted_at":"2026-07-31T16:32:38Z","abstract_excerpt":"Vision-and-language navigation (VLN) enables robots to follow instructions in previously unseen environments. Recently, a training-free paradigm has emerged: the robot queries a multimodal LLM to understand its observations and plan the next action. However, long-horizon navigation based on either image streams or dense map inevitably introduces a growing memory and reasoning bottleneck. We present HAM-VLN, a decision-coupled, agent-authored memory that equips the robot with a persistent, depth-grounded world graph. In the same model call used to select the next action, HAM-VLN also records se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29600","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/2607.29600/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":"2607.29600","created_at":"2026-08-03T01:40:05.401243+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.29600v1","created_at":"2026-08-03T01:40:05.401243+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29600","created_at":"2026-08-03T01:40:05.401243+00:00"},{"alias_kind":"pith_short_12","alias_value":"WHKDVF3UCOPV","created_at":"2026-08-03T01:40:05.401243+00:00"},{"alias_kind":"pith_short_16","alias_value":"WHKDVF3UCOPVRLS5","created_at":"2026-08-03T01:40:05.401243+00:00"},{"alias_kind":"pith_short_8","alias_value":"WHKDVF3U","created_at":"2026-08-03T01:40:05.401243+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/WHKDVF3UCOPVRLS5HYTBR4QZL7","json":"https://pith.science/pith/WHKDVF3UCOPVRLS5HYTBR4QZL7.json","graph_json":"https://pith.science/api/pith-number/WHKDVF3UCOPVRLS5HYTBR4QZL7/graph.json","events_json":"https://pith.science/api/pith-number/WHKDVF3UCOPVRLS5HYTBR4QZL7/events.json","paper":"https://pith.science/paper/WHKDVF3U"},"agent_actions":{"view_html":"https://pith.science/pith/WHKDVF3UCOPVRLS5HYTBR4QZL7","download_json":"https://pith.science/pith/WHKDVF3UCOPVRLS5HYTBR4QZL7.json","view_paper":"https://pith.science/paper/WHKDVF3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.29600&json=true","fetch_graph":"https://pith.science/api/pith-number/WHKDVF3UCOPVRLS5HYTBR4QZL7/graph.json","fetch_events":"https://pith.science/api/pith-number/WHKDVF3UCOPVRLS5HYTBR4QZL7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WHKDVF3UCOPVRLS5HYTBR4QZL7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WHKDVF3UCOPVRLS5HYTBR4QZL7/action/storage_attestation","attest_author":"https://pith.science/pith/WHKDVF3UCOPVRLS5HYTBR4QZL7/action/author_attestation","sign_citation":"https://pith.science/pith/WHKDVF3UCOPVRLS5HYTBR4QZL7/action/citation_signature","submit_replication":"https://pith.science/pith/WHKDVF3UCOPVRLS5HYTBR4QZL7/action/replication_record"}},"created_at":"2026-08-03T01:40:05.401243+00:00","updated_at":"2026-08-03T01:40:05.401243+00:00"}