{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ESX4V2RRZHHADV5UPN45UDZAPW","short_pith_number":"pith:ESX4V2RR","schema_version":"1.0","canonical_sha256":"24afcaea31c9ce01d7b47b79da0f207d8c8d95750fc39a5c2b3315d974dfeeac","source":{"kind":"arxiv","id":"2404.08937","version":1},"attestation_state":"computed","paper":{"title":"ChimpVLM: Ethogram-Enhanced Chimpanzee Behaviour Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hjalmar Kuhl, Majid Mirmehdi, Otto Brookes, Tilo Burghardt","submitted_at":"2024-04-13T09:17:51Z","abstract_excerpt":"We show that chimpanzee behaviour understanding from camera traps can be enhanced by providing visual architectures with access to an embedding of text descriptions that detail species behaviours. In particular, we present a vision-language model which employs multi-modal decoding of visual features extracted directly from camera trap videos to process query tokens representing behaviours and output class predictions. Query tokens are initialised using a standardised ethogram of chimpanzee behaviour, rather than using random or name-based initialisations. In addition, the effect of initialisin"},"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":"2404.08937","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-13T09:17:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"53bbb976faa881c3565c6e4bea58e76cad3d509bb3f3491a3d2b28828fb2a3a1","abstract_canon_sha256":"acf0a0954a1a92a3efddf3f9704214cba63bc48905e40332ae3a63545902e2b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:42.471994Z","signature_b64":"+F6GO8MH9y53WdPRYmTiAOP/7nzpsSdnfPe2OPYp+ikr0YFeqMqGb35kP4lL9V4nai1eiajAWnqXzJNE+L6nCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24afcaea31c9ce01d7b47b79da0f207d8c8d95750fc39a5c2b3315d974dfeeac","last_reissued_at":"2026-07-05T08:07:42.471657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:42.471657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChimpVLM: Ethogram-Enhanced Chimpanzee Behaviour Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hjalmar Kuhl, Majid Mirmehdi, Otto Brookes, Tilo Burghardt","submitted_at":"2024-04-13T09:17:51Z","abstract_excerpt":"We show that chimpanzee behaviour understanding from camera traps can be enhanced by providing visual architectures with access to an embedding of text descriptions that detail species behaviours. In particular, we present a vision-language model which employs multi-modal decoding of visual features extracted directly from camera trap videos to process query tokens representing behaviours and output class predictions. Query tokens are initialised using a standardised ethogram of chimpanzee behaviour, rather than using random or name-based initialisations. In addition, the effect of initialisin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08937","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/2404.08937/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":"2404.08937","created_at":"2026-07-05T08:07:42.471711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.08937v1","created_at":"2026-07-05T08:07:42.471711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08937","created_at":"2026-07-05T08:07:42.471711+00:00"},{"alias_kind":"pith_short_12","alias_value":"ESX4V2RRZHHA","created_at":"2026-07-05T08:07:42.471711+00:00"},{"alias_kind":"pith_short_16","alias_value":"ESX4V2RRZHHADV5U","created_at":"2026-07-05T08:07:42.471711+00:00"},{"alias_kind":"pith_short_8","alias_value":"ESX4V2RR","created_at":"2026-07-05T08:07:42.471711+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/ESX4V2RRZHHADV5UPN45UDZAPW","json":"https://pith.science/pith/ESX4V2RRZHHADV5UPN45UDZAPW.json","graph_json":"https://pith.science/api/pith-number/ESX4V2RRZHHADV5UPN45UDZAPW/graph.json","events_json":"https://pith.science/api/pith-number/ESX4V2RRZHHADV5UPN45UDZAPW/events.json","paper":"https://pith.science/paper/ESX4V2RR"},"agent_actions":{"view_html":"https://pith.science/pith/ESX4V2RRZHHADV5UPN45UDZAPW","download_json":"https://pith.science/pith/ESX4V2RRZHHADV5UPN45UDZAPW.json","view_paper":"https://pith.science/paper/ESX4V2RR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.08937&json=true","fetch_graph":"https://pith.science/api/pith-number/ESX4V2RRZHHADV5UPN45UDZAPW/graph.json","fetch_events":"https://pith.science/api/pith-number/ESX4V2RRZHHADV5UPN45UDZAPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ESX4V2RRZHHADV5UPN45UDZAPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ESX4V2RRZHHADV5UPN45UDZAPW/action/storage_attestation","attest_author":"https://pith.science/pith/ESX4V2RRZHHADV5UPN45UDZAPW/action/author_attestation","sign_citation":"https://pith.science/pith/ESX4V2RRZHHADV5UPN45UDZAPW/action/citation_signature","submit_replication":"https://pith.science/pith/ESX4V2RRZHHADV5UPN45UDZAPW/action/replication_record"}},"created_at":"2026-07-05T08:07:42.471711+00:00","updated_at":"2026-07-05T08:07:42.471711+00:00"}