{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XH4RBJ2Z7GKQVHSASIBAKTUVD4","short_pith_number":"pith:XH4RBJ2Z","schema_version":"1.0","canonical_sha256":"b9f910a759f9950a9e409202054e951f161cd9590c365342e72da5babf183c4b","source":{"kind":"arxiv","id":"2506.16623","version":1},"attestation_state":"computed","paper":{"title":"History-Augmented Vision-Language Models for Frontier-Based Zero-Shot Object Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Fatemeh Afghah, Mobin Habibpour","submitted_at":"2025-06-19T21:50:16Z","abstract_excerpt":"Object Goal Navigation (ObjectNav) challenges robots to find objects in unseen environments, demanding sophisticated reasoning. While Vision-Language Models (VLMs) show potential, current ObjectNav methods often employ them superficially, primarily using vision-language embeddings for object-scene similarity checks rather than leveraging deeper reasoning. This limits contextual understanding and leads to practical issues like repetitive navigation behaviors. This paper introduces a novel zero-shot ObjectNav framework that pioneers the use of dynamic, history-aware prompting to more deeply inte"},"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":"2506.16623","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-19T21:50:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ca90ca84da07e33c671f54b301127c6925645e5583d15e67bc76a63697a571e8","abstract_canon_sha256":"10d915c471d641b8c76fe9317b12376267f2ede0323f6d8b71a80001dda14cba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:39.605152Z","signature_b64":"tZ3m9Ipt1cD/yLvfXXin0L4p7cCxiNVhgh19JSzfs3WNSXg/I40s5s+C0G3bDw6MjF65eZ3NMwuGVB/DibP/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9f910a759f9950a9e409202054e951f161cd9590c365342e72da5babf183c4b","last_reissued_at":"2026-07-05T11:24:39.604666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:39.604666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"History-Augmented Vision-Language Models for Frontier-Based Zero-Shot Object Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Fatemeh Afghah, Mobin Habibpour","submitted_at":"2025-06-19T21:50:16Z","abstract_excerpt":"Object Goal Navigation (ObjectNav) challenges robots to find objects in unseen environments, demanding sophisticated reasoning. While Vision-Language Models (VLMs) show potential, current ObjectNav methods often employ them superficially, primarily using vision-language embeddings for object-scene similarity checks rather than leveraging deeper reasoning. This limits contextual understanding and leads to practical issues like repetitive navigation behaviors. This paper introduces a novel zero-shot ObjectNav framework that pioneers the use of dynamic, history-aware prompting to more deeply inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16623","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/2506.16623/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":"2506.16623","created_at":"2026-07-05T11:24:39.604731+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.16623v1","created_at":"2026-07-05T11:24:39.604731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16623","created_at":"2026-07-05T11:24:39.604731+00:00"},{"alias_kind":"pith_short_12","alias_value":"XH4RBJ2Z7GKQ","created_at":"2026-07-05T11:24:39.604731+00:00"},{"alias_kind":"pith_short_16","alias_value":"XH4RBJ2Z7GKQVHSA","created_at":"2026-07-05T11:24:39.604731+00:00"},{"alias_kind":"pith_short_8","alias_value":"XH4RBJ2Z","created_at":"2026-07-05T11:24:39.604731+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02417","citing_title":"LIME: Learning Intent-aware Camera Motion from Egocentric Video","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XH4RBJ2Z7GKQVHSASIBAKTUVD4","json":"https://pith.science/pith/XH4RBJ2Z7GKQVHSASIBAKTUVD4.json","graph_json":"https://pith.science/api/pith-number/XH4RBJ2Z7GKQVHSASIBAKTUVD4/graph.json","events_json":"https://pith.science/api/pith-number/XH4RBJ2Z7GKQVHSASIBAKTUVD4/events.json","paper":"https://pith.science/paper/XH4RBJ2Z"},"agent_actions":{"view_html":"https://pith.science/pith/XH4RBJ2Z7GKQVHSASIBAKTUVD4","download_json":"https://pith.science/pith/XH4RBJ2Z7GKQVHSASIBAKTUVD4.json","view_paper":"https://pith.science/paper/XH4RBJ2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.16623&json=true","fetch_graph":"https://pith.science/api/pith-number/XH4RBJ2Z7GKQVHSASIBAKTUVD4/graph.json","fetch_events":"https://pith.science/api/pith-number/XH4RBJ2Z7GKQVHSASIBAKTUVD4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XH4RBJ2Z7GKQVHSASIBAKTUVD4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XH4RBJ2Z7GKQVHSASIBAKTUVD4/action/storage_attestation","attest_author":"https://pith.science/pith/XH4RBJ2Z7GKQVHSASIBAKTUVD4/action/author_attestation","sign_citation":"https://pith.science/pith/XH4RBJ2Z7GKQVHSASIBAKTUVD4/action/citation_signature","submit_replication":"https://pith.science/pith/XH4RBJ2Z7GKQVHSASIBAKTUVD4/action/replication_record"}},"created_at":"2026-07-05T11:24:39.604731+00:00","updated_at":"2026-07-05T11:24:39.604731+00:00"}