{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FU5627QHTIAWXXKJAB7HWJ3KLZ","short_pith_number":"pith:FU5627QH","schema_version":"1.0","canonical_sha256":"2d3bed7e079a016bdd49007e7b276a5e572d31bf997051db6251accc1b793046","source":{"kind":"arxiv","id":"2605.19690","version":1},"attestation_state":"computed","paper":{"title":"D-CLING: Prior-Preserving Depth-Conditioned Fine-Tuning for Navigation Foundation Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Kazuhito Tanaka, Shintaro Nakaoka, Takayuki Kanai","submitted_at":"2026-05-19T11:23:04Z","abstract_excerpt":"Navigation Foundation Models (NFMs) trained on large cross-embodied datasets have demonstrated powerful generalizability in various scenarios. Adopting in-domain fine-tuning for an NFM efficiently calibrates the visuomotor policy, promising further improvement even in a novel scenario. However, the fine-tuned models still suffer from poor obstacle avoidance or fail to properly reach the provided goals. Furthermore, model updates using a small subset of data typically erode the pre-trained prior, compromising the pre-training generalization. Consequently, fine-tuning deteriorates the capability"},"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":"2605.19690","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-19T11:23:04Z","cross_cats_sorted":[],"title_canon_sha256":"d01e7f058f535b9e66e87e73b9a6be8cac525dbd7f3bf84d0027957babec52e8","abstract_canon_sha256":"ec90487bb677cb1e572df2ed8540aca36afbbc8947ebe51214df2751c0d9530b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:57.872226Z","signature_b64":"b41G2Wa7VR4iQSiNzXbTP5Ln9DENx5b6kF2AU5RWQeTcnh1W5yU+ahSpDJdBILtZR++eUGlf9/dvF4pQ8EsgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d3bed7e079a016bdd49007e7b276a5e572d31bf997051db6251accc1b793046","last_reissued_at":"2026-05-20T01:05:57.871580Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:57.871580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"D-CLING: Prior-Preserving Depth-Conditioned Fine-Tuning for Navigation Foundation Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Kazuhito Tanaka, Shintaro Nakaoka, Takayuki Kanai","submitted_at":"2026-05-19T11:23:04Z","abstract_excerpt":"Navigation Foundation Models (NFMs) trained on large cross-embodied datasets have demonstrated powerful generalizability in various scenarios. Adopting in-domain fine-tuning for an NFM efficiently calibrates the visuomotor policy, promising further improvement even in a novel scenario. However, the fine-tuned models still suffer from poor obstacle avoidance or fail to properly reach the provided goals. Furthermore, model updates using a small subset of data typically erode the pre-trained prior, compromising the pre-training generalization. Consequently, fine-tuning deteriorates the capability"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19690","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/2605.19690/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":"2605.19690","created_at":"2026-05-20T01:05:57.871697+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19690v1","created_at":"2026-05-20T01:05:57.871697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19690","created_at":"2026-05-20T01:05:57.871697+00:00"},{"alias_kind":"pith_short_12","alias_value":"FU5627QHTIAW","created_at":"2026-05-20T01:05:57.871697+00:00"},{"alias_kind":"pith_short_16","alias_value":"FU5627QHTIAWXXKJ","created_at":"2026-05-20T01:05:57.871697+00:00"},{"alias_kind":"pith_short_8","alias_value":"FU5627QH","created_at":"2026-05-20T01:05:57.871697+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/FU5627QHTIAWXXKJAB7HWJ3KLZ","json":"https://pith.science/pith/FU5627QHTIAWXXKJAB7HWJ3KLZ.json","graph_json":"https://pith.science/api/pith-number/FU5627QHTIAWXXKJAB7HWJ3KLZ/graph.json","events_json":"https://pith.science/api/pith-number/FU5627QHTIAWXXKJAB7HWJ3KLZ/events.json","paper":"https://pith.science/paper/FU5627QH"},"agent_actions":{"view_html":"https://pith.science/pith/FU5627QHTIAWXXKJAB7HWJ3KLZ","download_json":"https://pith.science/pith/FU5627QHTIAWXXKJAB7HWJ3KLZ.json","view_paper":"https://pith.science/paper/FU5627QH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19690&json=true","fetch_graph":"https://pith.science/api/pith-number/FU5627QHTIAWXXKJAB7HWJ3KLZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FU5627QHTIAWXXKJAB7HWJ3KLZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FU5627QHTIAWXXKJAB7HWJ3KLZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FU5627QHTIAWXXKJAB7HWJ3KLZ/action/storage_attestation","attest_author":"https://pith.science/pith/FU5627QHTIAWXXKJAB7HWJ3KLZ/action/author_attestation","sign_citation":"https://pith.science/pith/FU5627QHTIAWXXKJAB7HWJ3KLZ/action/citation_signature","submit_replication":"https://pith.science/pith/FU5627QHTIAWXXKJAB7HWJ3KLZ/action/replication_record"}},"created_at":"2026-05-20T01:05:57.871697+00:00","updated_at":"2026-05-20T01:05:57.871697+00:00"}