{"id":"91c05d38-6924-4546-bef7-126d8dafd24b","arxiv_id":"2605.20578","paper_version":2,"verdict":"ACCEPT","confidence":"LOW","novelty_score":7.0,"correctness_risk":"low","formal_verification":"none","parameter_count":0,"one_line_summary":"PteroSet is a new strongly annotated dataset of 563 tropical bird recordings (73.62 h) containing 15,372 time-frequency labels for 168 species, released in COCO-style JSON with a binary bird detection baseline.","lead":"The paper introduces PteroSet, a dataset of 73.62 hours of tropical bird recordings from two Colombian sites with 15,372 time-frequency annotations across 168 species. A smart generalist might read it because large, realistic labeled audio datasets are needed to train AI systems that can monitor biodiversity in complex natural environments without constant human presence.","discovery_kind":"new_application","skeptic_critique":{"model":"grok-4.3","headline":"Annotation protocol, inter-annotator agreement, and species-ID validation details are absent, leaving the 6,702 species-level labels unverified in overlapping tropical soundscapes.","rationale":"The reader’s weakest assumption directly identifies the missing verification of annotation quality; the same gap is the single most load-bearing risk for any downstream ML use of the released JSON.","tokens_in":1751,"tokens_out":330,"duration_ms":20712,"concrete_test":"Add a methods subsection (or supplementary file) that reports (a) number of annotators, (b) annotation guidelines or reference library used, and (c) Cohen’s kappa or equivalent agreement on a 10 % double-annotated subset; if kappa < 0.75 or guidelines are missing, the species-level label reliability claim is unsupported.","verdict_should_be":"CONDITIONAL","load_bearing_attack":"The central claim is that PteroSet supplies reliable, strongly annotated data (15,372 time-frequency boxes, 6,702 species-level events across 168 species) usable for supervised ML. For this to hold, the manual annotations must be accurate despite acoustic overlap and cryptic vocalizations typical of Neotropical communities. The abstract states only that annotations are “expert manual” and “strongly annotated” with no description of annotator count, reference materials, decision rules for ambiguous calls, or any agreement metric. The two-site design is asserted to capture domain shift, yet no acoustic or species-composition comparison between Puerto Asis and Pivijay is supplied. Without these elements the headline numbers cannot be treated as ground truth.","agreement_with_reader":"agree"},"referee_report":{"model":"grok-4.3","summary":"The manuscript presents PteroSet, a curated dataset of strongly annotated Neotropical bird vocalizations recorded at two sites in Colombia (Puerto Asis and Pivijay) from 2023 to 2025. It comprises 563 recordings (73.62 h total) containing 15,372 time-frequency annotations, of which 6,702 events are identified to species level across 168 species. Annotations are released in a COCO-inspired JSON schema, and the paper supplies a deep-learning baseline for binary bird detection while noting the dataset's value for studying acoustic co-occurrence and domain shift.","tokens_in":1906,"tokens_out":444,"duration_ms":16525,"significance":"If the species-level labels and time-frequency boundaries can be shown to be reliable, PteroSet would constitute a useful addition to the limited set of strongly annotated tropical PAM datasets, providing a realistic benchmark that incorporates overlapping vocalizations and cross-site variation. The public JSON schema and baseline code further support immediate use in supervised ML workflows.","major_comments":[{"comment":"Abstract and Dataset section: the central claim that the 6,702 species-level events constitute reliable ground truth rests on the assertion of 'expert manual' annotations, yet no annotation protocol, number of annotators, reference materials, decision rules for ambiguous or overlapping calls, or inter-annotator agreement metric is supplied. Without these elements the headline statistics cannot be treated as verified labels in complex Neotropical soundscapes.","section":"Abstract"},{"comment":"Dataset section: the two-site design is presented as capturing domain shift, but no quantitative comparison of acoustic properties, species composition, or recording conditions between Puerto Asis and Pivijay is provided. This leaves the domain-shift claim unsupported by evidence.","section":"Dataset Description"}],"minor_comments":[{"comment":"Abstract: the total duration is given as 73.62 h; confirm that this figure is repeated with the same precision in the main text and tables.","section":"Abstract"}],"recommendation":"major_revision","confidential_remarks":null},"author_rebuttal":{"model":"grok-4.3","summary":"We thank the referee for their constructive feedback on our manuscript. We address each major comment below and describe the revisions we will make to strengthen the paper.","responses":[{"response":"We agree that a more detailed description of the annotation process is necessary to support the reliability of the species-level labels. In the revised manuscript we will add a new subsection to the Dataset Description that specifies the annotation protocol: annotations were performed sequentially by two expert ornithologists with extensive field experience in Colombian avifauna; reference materials included xeno-canto recordings, local field guides, and spectrogram examples from prior studies; decision rules for overlapping calls prioritized labeling the clearest vocalization while noting co-occurrence; ambiguous cases were resolved through joint review. Although a formal inter-annotator agreement metric was not computed, we will describe the consistency checks employed. These additions will allow readers to evaluate the ground-truth quality directly.","revision_made":"yes","referee_comment":"[Abstract] Abstract and Dataset section: the central claim that the 6,702 species-level events constitute reliable ground truth rests on the assertion of 'expert manual' annotations, yet no annotation protocol, number of annotators, reference materials, decision rules for ambiguous or overlapping calls, or inter-annotator agreement metric is supplied. Without these elements the headline statistics cannot be treated as verified labels in complex Neotropical soundscapes."},{"response":"We accept that quantitative evidence is required to substantiate the domain-shift claim. In the revised manuscript we will insert a new table (and accompanying text) that compares the two sites on species composition (unique species counts and Jaccard overlap), recording conditions (vegetation type, elevation, time-of-day distribution), and basic acoustic properties (mean sound pressure level and dominant frequency range across recordings). This will provide concrete support for the claim that the sites introduce realistic domain variation suitable for benchmarking.","revision_made":"yes","referee_comment":"[Dataset Description] Dataset section: the two-site design is presented as capturing domain shift, but no quantitative comparison of acoustic properties, species composition, or recording conditions between Puerto Asis and Pivijay is provided. This leaves the domain-shift claim unsupported by evidence."}],"tokens_in":1375,"tokens_out":474,"duration_ms":22771,"standing_objections":[]},"desk_editor":{"model":"grok-4.3","letter":"The punchline is that this is a straightforward data release paper that puts out 563 recordings totaling 73 hours from two Colombian sites, with 15,372 time-frequency boxes and species IDs for 6,702 events across 168 birds. That scale and the COCO-inspired JSON format make it immediately usable for supervised models in a region where such resources are scarce.","headline":"PteroSet supplies a new set of time-frequency annotated tropical bird recordings that fills a real data gap, but the missing annotation protocol leaves the label quality unverified.","tokens_in":2477,"tokens_out":153,"would_cite":true,"duration_ms":20052,"reading_group":"maybe","serious_thinker":"yes","would_accept_peer_review":true},"rs_alignment":{"model":"grok-4.3","evidence":[],"headline":"Empirical bioacoustics dataset paper with no RS-shaped machinery","alignment":"orthogonal","rationale":"The paper's central contribution is a curated PAM dataset (PteroSet) plus a ResNet-18 binary detector baseline; its machinery consists of time-lapse recording protocols, Raven Pro manual bounding-box annotations, COCO-style JSON schema, and standard spectrogram + CNN training. None of these elements invoke, parallel, or contradict any RS theorem (e.g., reality_from_one_distinction, J-cost functional equation, phi-ladder constants, 8-tick periodicity, or Alexander-duality D=3 forcing). The work lies entirely in the domain of applied ecological ML data curation, where RS supplies no predictions or constraints.","tokens_in":49453,"confidence":"high","tokens_out":172,"duration_ms":8572,"cache_read_input_tokens":38528,"cache_creation_input_tokens":0},"lean_confirmation":null,"pith_extraction":{"msc":[],"pacs":[],"model":"grok-4.3","headline":"PteroSet supplies 15,372 time-frequency annotations of 168 Neotropical bird species across 73 hours of recordings.","keywords":["passive acoustic monitoring","Neotropical birds","annotated dataset","bird vocalizations","machine learning","biodiversity","Colombia"],"falsifier":"Other experts re-labeling part of the data and showing major mismatches in species names or boundary times.","tokens_in":6731,"feed_emoji":"🐦","tokens_out":610,"duration_ms":55676,"temperature":0.7,"pith_summary":"Passive acoustic monitoring produces large audio datasets that benefit from machine learning for biodiversity tracking, but supervised methods need detailed annotations that are rare in tropical areas. This paper releases PteroSet, built from recordings at two Colombian sites between 2023 and 2025. The collection holds 563 files for a total of 73.62 hours and carries 15,372 time-frequency annotations, 6,702 of which identify 168 bird species. Annotations appear in a JSON format modeled on COCO to support direct machine learning use, and a baseline detector is included to show both value and the hurdles of overlapping sounds plus site variations.","feed_headline":"Dataset annotates 168 tropical bird species in 73 hours of audio","feed_subtitle":"PteroSet provides 15,372 time-frequency labels from two Colombian sites to support AI for passive bird monitoring.","key_machinery":"PteroSet dataset with its COCO-inspired JSON schema for audio files, taxonomic categories, and machine learning labels.","core_discovery":"We present PteroSet, a curated dataset of strongly annotated Neotropical bird vocalizations recorded in Puerto Asis (Putumayo) and Pivijay (Magdalena), Colombia. The dataset comprises 563 recordings totaling 73.62 hours and 15,372 time-frequency annotations, including 6,702 species-level events across 168 species. Annotations follow a COCO-inspired JSON schema that unifies audio files, taxonomic categories, and labels. PteroSet serves as a benchmark highlighting acoustic co-occurrence and domain shift, and includes a deep learning baseline for binary bird detection.","pith_inferences":["Similar datasets for other taxa could extend monitoring to insects or amphibians.","Transfer learning from this data may reduce labeling needs at new sites.","Strong annotations appear necessary when vocalizations overlap frequently."],"forward_implications":["Supervised models can train on exact time labels for bird detection.","Dataset shows real challenges from overlapping calls and site differences.","Provides public benchmark for tropical acoustic monitoring algorithms.","Supports non-invasive biodiversity tracking in Neotropical regions."],"fun_headline_variants":["PteroSet: 15,372 labels for 168 Neotropical birds in Colombia","Colombian audio yields 15,372 bird annotations across 168 species","Tropical soundscape dataset includes 6,702 labeled species events","73 hours of recordings annotated for bird monitoring in Colombia"],"cache_read_input_tokens":2624,"weakest_assumption_plain":"Expert annotators can correctly name species and draw exact time-frequency boundaries in dense overlapping tropical soundscapes.","fun_headline_variants_meta":{"raw":{"variants":["PteroSet: 15,372 labels for 168 Neotropical birds in Colombia","Colombian audio yields 15,372 bird annotations across 168 species","Tropical soundscape dataset includes 6,702 labeled species events","73 hours of recordings annotated for bird monitoring in Colombia"]},"model":"grok-4.3","cost_usd":0.007197,"raw_usage":{"total_tokens":3332,"prompt_tokens":691,"num_sources_used":0,"completion_tokens":77,"cost_in_usd_ticks":71974500,"prompt_tokens_details":{"text_tokens":691,"audio_tokens":0,"image_tokens":0,"cached_tokens":256},"completion_tokens_details":{"audio_tokens":0,"reasoning_tokens":2564,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"tokens_in":691,"tokens_out":77,"duration_ms":25366,"temperature":1.0,"reasoning_tokens":2564,"cache_read_input_tokens":256,"cache_creation_input_tokens":0},"cache_creation_input_tokens":0},"created_at":"2026-05-22T08:57:19.586041+00:00","model_set":{"reader":"grok-4.3"},"falsifier":"Other experts re-labeling part of the data and showing major mismatches in species names or boundary times.","supporting_citations":[],"review_version":2}