{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:R4DTNHJ25TQB2HT4HGX7KDFTKW","short_pith_number":"pith:R4DTNHJ2","canonical_record":{"source":{"id":"2505.16663","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T13:27:54Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"13068c45ca50e235b558f1e4f6fc2a239e503a4c663a22fbcbfa9749a0d78733","abstract_canon_sha256":"b7b47c5fa70ebf7ea9014576d41f60ced1d87639ae27261b2b2493cf74228186"},"schema_version":"1.0"},"canonical_sha256":"8f07369d3aece01d1e7c39aff50cb35592a5e5dcc0dabc13cb6d8b90dcc4f978","source":{"kind":"arxiv","id":"2505.16663","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16663","created_at":"2026-07-05T11:07:38Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16663v1","created_at":"2026-07-05T11:07:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16663","created_at":"2026-07-05T11:07:38Z"},{"alias_kind":"pith_short_12","alias_value":"R4DTNHJ25TQB","created_at":"2026-07-05T11:07:38Z"},{"alias_kind":"pith_short_16","alias_value":"R4DTNHJ25TQB2HT4","created_at":"2026-07-05T11:07:38Z"},{"alias_kind":"pith_short_8","alias_value":"R4DTNHJ2","created_at":"2026-07-05T11:07:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:R4DTNHJ25TQB2HT4HGX7KDFTKW","target":"record","payload":{"canonical_record":{"source":{"id":"2505.16663","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T13:27:54Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"13068c45ca50e235b558f1e4f6fc2a239e503a4c663a22fbcbfa9749a0d78733","abstract_canon_sha256":"b7b47c5fa70ebf7ea9014576d41f60ced1d87639ae27261b2b2493cf74228186"},"schema_version":"1.0"},"canonical_sha256":"8f07369d3aece01d1e7c39aff50cb35592a5e5dcc0dabc13cb6d8b90dcc4f978","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:38.649333Z","signature_b64":"6w6n0hgNZ6jvYTR67lKcR8UBe+CY+jAA1jxvu78u9Iu4gjcoanKBpj0LrvoPPTfHEnWMqdauY7R6QMhJDAdBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f07369d3aece01d1e7c39aff50cb35592a5e5dcc0dabc13cb6d8b90dcc4f978","last_reissued_at":"2026-07-05T11:07:38.648827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:38.648827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.16663","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:07:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p8UjQ278gzW7bYNDC27jXv32ooMwZBqMEzsjUGesPXBwPx2IW5mJ4Ryp6vciGozzPj1WjDKKdJS0+4gCJ6FcAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:38:57.967481Z"},"content_sha256":"328428ea5775f07748782fe9354ed00528e030ce53429c02c475d1f79c028a80","schema_version":"1.0","event_id":"sha256:328428ea5775f07748782fe9354ed00528e030ce53429c02c475d1f79c028a80"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:R4DTNHJ25TQB2HT4HGX7KDFTKW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Changlin Li, Haihong Hao, Mingfei Han, Xiaojun Chang, Zhihui Li","submitted_at":"2025-05-22T13:27:54Z","abstract_excerpt":"Embodied navigation demands comprehensive scene understanding and precise spatial reasoning. While image-text models excel at interpreting pixel-level color and lighting cues, 3D-text models capture volumetric structure and spatial relationships. However, unified fusion approaches that jointly fuse 2D images, 3D point clouds, and textual instructions face challenges in limited availability of triple-modality data and difficulty resolving conflicting beliefs among modalities. In this work, we introduce CoNav, a collaborative cross-modal reasoning framework where a pretrained 3D-text model expli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16663","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/2505.16663/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:07:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dAHgFqpuKhlzF5W3oLDWa1bwjDvtROECgsCVpdYU8XyE4xyTQZi1vvolEmWjpLs234RmbhOxVmhKf6NEYhvVCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:38:57.967975Z"},"content_sha256":"f5f41c43b9fcaf4490927226be93f1ea34c774b8bf768c80e9d0a340a99b3818","schema_version":"1.0","event_id":"sha256:f5f41c43b9fcaf4490927226be93f1ea34c774b8bf768c80e9d0a340a99b3818"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R4DTNHJ25TQB2HT4HGX7KDFTKW/bundle.json","state_url":"https://pith.science/pith/R4DTNHJ25TQB2HT4HGX7KDFTKW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R4DTNHJ25TQB2HT4HGX7KDFTKW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T03:38:57Z","links":{"resolver":"https://pith.science/pith/R4DTNHJ25TQB2HT4HGX7KDFTKW","bundle":"https://pith.science/pith/R4DTNHJ25TQB2HT4HGX7KDFTKW/bundle.json","state":"https://pith.science/pith/R4DTNHJ25TQB2HT4HGX7KDFTKW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R4DTNHJ25TQB2HT4HGX7KDFTKW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R4DTNHJ25TQB2HT4HGX7KDFTKW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b7b47c5fa70ebf7ea9014576d41f60ced1d87639ae27261b2b2493cf74228186","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T13:27:54Z","title_canon_sha256":"13068c45ca50e235b558f1e4f6fc2a239e503a4c663a22fbcbfa9749a0d78733"},"schema_version":"1.0","source":{"id":"2505.16663","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16663","created_at":"2026-07-05T11:07:38Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16663v1","created_at":"2026-07-05T11:07:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16663","created_at":"2026-07-05T11:07:38Z"},{"alias_kind":"pith_short_12","alias_value":"R4DTNHJ25TQB","created_at":"2026-07-05T11:07:38Z"},{"alias_kind":"pith_short_16","alias_value":"R4DTNHJ25TQB2HT4","created_at":"2026-07-05T11:07:38Z"},{"alias_kind":"pith_short_8","alias_value":"R4DTNHJ2","created_at":"2026-07-05T11:07:38Z"}],"graph_snapshots":[{"event_id":"sha256:f5f41c43b9fcaf4490927226be93f1ea34c774b8bf768c80e9d0a340a99b3818","target":"graph","created_at":"2026-07-05T11:07:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.16663/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Embodied navigation demands comprehensive scene understanding and precise spatial reasoning. While image-text models excel at interpreting pixel-level color and lighting cues, 3D-text models capture volumetric structure and spatial relationships. However, unified fusion approaches that jointly fuse 2D images, 3D point clouds, and textual instructions face challenges in limited availability of triple-modality data and difficulty resolving conflicting beliefs among modalities. In this work, we introduce CoNav, a collaborative cross-modal reasoning framework where a pretrained 3D-text model expli","authors_text":"Changlin Li, Haihong Hao, Mingfei Han, Xiaojun Chang, Zhihui Li","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T13:27:54Z","title":"CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16663","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:328428ea5775f07748782fe9354ed00528e030ce53429c02c475d1f79c028a80","target":"record","created_at":"2026-07-05T11:07:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b7b47c5fa70ebf7ea9014576d41f60ced1d87639ae27261b2b2493cf74228186","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T13:27:54Z","title_canon_sha256":"13068c45ca50e235b558f1e4f6fc2a239e503a4c663a22fbcbfa9749a0d78733"},"schema_version":"1.0","source":{"id":"2505.16663","kind":"arxiv","version":1}},"canonical_sha256":"8f07369d3aece01d1e7c39aff50cb35592a5e5dcc0dabc13cb6d8b90dcc4f978","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f07369d3aece01d1e7c39aff50cb35592a5e5dcc0dabc13cb6d8b90dcc4f978","first_computed_at":"2026-07-05T11:07:38.648827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:38.648827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6w6n0hgNZ6jvYTR67lKcR8UBe+CY+jAA1jxvu78u9Iu4gjcoanKBpj0LrvoPPTfHEnWMqdauY7R6QMhJDAdBCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:38.649333Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16663","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:328428ea5775f07748782fe9354ed00528e030ce53429c02c475d1f79c028a80","sha256:f5f41c43b9fcaf4490927226be93f1ea34c774b8bf768c80e9d0a340a99b3818"],"state_sha256":"5a96c389aa94fbdb9fc9f5a812fa8b45d516d861fe295419f8e4d065c0becb2a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QuSPk9Emi7UcHyC6sZVu+AJ7WwS56eHm5HeKjat5D8UBldYy1+rjViUIY5+6EUiHVE6qchk/GT8W5CzubxySCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T03:38:57.971322Z","bundle_sha256":"3b8db15b39f45aacf775e6329312f6a1a9c343d3c5f072d585557dc2125cd465"}}