{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:O7NQHI3HR52UBVG4HAHP6BKO7U","short_pith_number":"pith:O7NQHI3H","canonical_record":{"source":{"id":"2503.07593","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T17:55:22Z","cross_cats_sorted":[],"title_canon_sha256":"b10b32f20f51464eba4cb84fd51fb25347cb72cec7c42e70aefb79eb6e6d07f3","abstract_canon_sha256":"6aa2deb6f5765a37965a21ff8aea349ddf6e11fc5cd8d4616270b5c222fcb326"},"schema_version":"1.0"},"canonical_sha256":"77db03a3678f7540d4dc380eff054efd036add6086fa4b5ca69dc25cb6db2f93","source":{"kind":"arxiv","id":"2503.07593","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.07593","created_at":"2026-07-05T10:28:07Z"},{"alias_kind":"arxiv_version","alias_value":"2503.07593v1","created_at":"2026-07-05T10:28:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07593","created_at":"2026-07-05T10:28:07Z"},{"alias_kind":"pith_short_12","alias_value":"O7NQHI3HR52U","created_at":"2026-07-05T10:28:07Z"},{"alias_kind":"pith_short_16","alias_value":"O7NQHI3HR52UBVG4","created_at":"2026-07-05T10:28:07Z"},{"alias_kind":"pith_short_8","alias_value":"O7NQHI3H","created_at":"2026-07-05T10:28:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:O7NQHI3HR52UBVG4HAHP6BKO7U","target":"record","payload":{"canonical_record":{"source":{"id":"2503.07593","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T17:55:22Z","cross_cats_sorted":[],"title_canon_sha256":"b10b32f20f51464eba4cb84fd51fb25347cb72cec7c42e70aefb79eb6e6d07f3","abstract_canon_sha256":"6aa2deb6f5765a37965a21ff8aea349ddf6e11fc5cd8d4616270b5c222fcb326"},"schema_version":"1.0"},"canonical_sha256":"77db03a3678f7540d4dc380eff054efd036add6086fa4b5ca69dc25cb6db2f93","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:07.540522Z","signature_b64":"OiEUNLjSMPQyvjpCNMEevF69icjS3pLF8Be5SvGPe8j84BXml+OzTVBFgLUuX7Vj2GR+ZGemH7YZYqJiaa5uCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77db03a3678f7540d4dc380eff054efd036add6086fa4b5ca69dc25cb6db2f93","last_reissued_at":"2026-07-05T10:28:07.539742Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:07.539742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.07593","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":"2026-07-05T10:28:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"32n8ccLVOjKkG4zTPia0Rv012qqRKuJ7/aj1FsLn7fzB5TFCOmKGdfJiK7A0ccsrypQxe34Soq4+vW2gdfaXBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:37:54.081406Z"},"content_sha256":"5a2007f3c6e7ccab4d76f904339377c6dcb982afef66d2fce80fb798d3f9c6fd","schema_version":"1.0","event_id":"sha256:5a2007f3c6e7ccab4d76f904339377c6dcb982afef66d2fce80fb798d3f9c6fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:O7NQHI3HR52UBVG4HAHP6BKO7U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Cross-Modal Alignment for Open-Vocabulary 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaying Lin, Rynson W.H. Lau, Youjun Zhao","submitted_at":"2025-03-10T17:55:22Z","abstract_excerpt":"Open-vocabulary 3D object detection (OV-3DOD) aims at localizing and classifying novel objects beyond closed sets. The recent success of vision-language models (VLMs) has demonstrated their remarkable capabilities to understand open vocabularies. Existing works that leverage VLMs for 3D object detection (3DOD) generally resort to representations that lose the rich scene context required for 3D perception. To address this problem, we propose in this paper a hierarchical framework, named HCMA, to simultaneously learn local object and global scene information for OV-3DOD. Specifically, we first d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07593","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/2503.07593/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":"2026-07-05T10:28:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b6URvkOM2B4qgzglsZVo3lK2OyX6rbMoXU3HgjLfNrBSJUqHgga//BTVv9GQYzOYsyMG4sHpd2Pkey814VOXAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:37:54.081921Z"},"content_sha256":"c2dfaeec8b21d10a8f7c6ca86330c4769b8f94d3308c7b06ed042aa98c064c23","schema_version":"1.0","event_id":"sha256:c2dfaeec8b21d10a8f7c6ca86330c4769b8f94d3308c7b06ed042aa98c064c23"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O7NQHI3HR52UBVG4HAHP6BKO7U/bundle.json","state_url":"https://pith.science/pith/O7NQHI3HR52UBVG4HAHP6BKO7U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O7NQHI3HR52UBVG4HAHP6BKO7U/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":"2026-08-04T21:37:54Z","links":{"resolver":"https://pith.science/pith/O7NQHI3HR52UBVG4HAHP6BKO7U","bundle":"https://pith.science/pith/O7NQHI3HR52UBVG4HAHP6BKO7U/bundle.json","state":"https://pith.science/pith/O7NQHI3HR52UBVG4HAHP6BKO7U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O7NQHI3HR52UBVG4HAHP6BKO7U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:O7NQHI3HR52UBVG4HAHP6BKO7U","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":"6aa2deb6f5765a37965a21ff8aea349ddf6e11fc5cd8d4616270b5c222fcb326","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T17:55:22Z","title_canon_sha256":"b10b32f20f51464eba4cb84fd51fb25347cb72cec7c42e70aefb79eb6e6d07f3"},"schema_version":"1.0","source":{"id":"2503.07593","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.07593","created_at":"2026-07-05T10:28:07Z"},{"alias_kind":"arxiv_version","alias_value":"2503.07593v1","created_at":"2026-07-05T10:28:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07593","created_at":"2026-07-05T10:28:07Z"},{"alias_kind":"pith_short_12","alias_value":"O7NQHI3HR52U","created_at":"2026-07-05T10:28:07Z"},{"alias_kind":"pith_short_16","alias_value":"O7NQHI3HR52UBVG4","created_at":"2026-07-05T10:28:07Z"},{"alias_kind":"pith_short_8","alias_value":"O7NQHI3H","created_at":"2026-07-05T10:28:07Z"}],"graph_snapshots":[{"event_id":"sha256:c2dfaeec8b21d10a8f7c6ca86330c4769b8f94d3308c7b06ed042aa98c064c23","target":"graph","created_at":"2026-07-05T10:28:07Z","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/2503.07593/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-vocabulary 3D object detection (OV-3DOD) aims at localizing and classifying novel objects beyond closed sets. The recent success of vision-language models (VLMs) has demonstrated their remarkable capabilities to understand open vocabularies. Existing works that leverage VLMs for 3D object detection (3DOD) generally resort to representations that lose the rich scene context required for 3D perception. To address this problem, we propose in this paper a hierarchical framework, named HCMA, to simultaneously learn local object and global scene information for OV-3DOD. Specifically, we first d","authors_text":"Jiaying Lin, Rynson W.H. Lau, Youjun Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T17:55:22Z","title":"Hierarchical Cross-Modal Alignment for Open-Vocabulary 3D Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07593","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":"sha256:5a2007f3c6e7ccab4d76f904339377c6dcb982afef66d2fce80fb798d3f9c6fd","target":"record","created_at":"2026-07-05T10:28:07Z","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":"6aa2deb6f5765a37965a21ff8aea349ddf6e11fc5cd8d4616270b5c222fcb326","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T17:55:22Z","title_canon_sha256":"b10b32f20f51464eba4cb84fd51fb25347cb72cec7c42e70aefb79eb6e6d07f3"},"schema_version":"1.0","source":{"id":"2503.07593","kind":"arxiv","version":1}},"canonical_sha256":"77db03a3678f7540d4dc380eff054efd036add6086fa4b5ca69dc25cb6db2f93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77db03a3678f7540d4dc380eff054efd036add6086fa4b5ca69dc25cb6db2f93","first_computed_at":"2026-07-05T10:28:07.539742Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:07.539742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OiEUNLjSMPQyvjpCNMEevF69icjS3pLF8Be5SvGPe8j84BXml+OzTVBFgLUuX7Vj2GR+ZGemH7YZYqJiaa5uCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:07.540522Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.07593","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a2007f3c6e7ccab4d76f904339377c6dcb982afef66d2fce80fb798d3f9c6fd","sha256:c2dfaeec8b21d10a8f7c6ca86330c4769b8f94d3308c7b06ed042aa98c064c23"],"state_sha256":"da4fffd5e96f364c27b804edf11e354e33966c250fb98a0ad7dad577b91c604e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NptI4Si+Ufeu2fSCdE5guEV4eSbBFSVc+XvAIMVeLdHoaAroUVX9eCmXR5bdTvEDvGWtAvLC2DaI/M85nwM1CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:37:54.084905Z","bundle_sha256":"1189a3045fce3bc1aad3ca87e6ddb2291dcd0acd2af4858a85379dfb2432b13a"}}